acl acl2010 acl2010-159 knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Raphael Hoffmann ; Congle Zhang ; Daniel S. Weld
Abstract: Many researchers are trying to use information extraction (IE) to create large-scale knowledge bases from natural language text on the Web. However, the primary approach (supervised learning of relation-specific extractors) requires manually-labeled training data for each relation and doesn’t scale to the thousands of relations encoded in Web text. This paper presents LUCHS, a self-supervised, relation-specific IE system which learns 5025 relations more than an order of magnitude greater than any previous approach with an average F1 score of 61%. Crucial to LUCHS’s performance is an automated system for dynamic lexicon learning, which allows it to learn accurately from heuristically-generated training data, which is often noisy and sparse. — —
Reference: text
sentIndex sentText sentNum sentScore
1 Weld Computer Science & Engineering University of Washington Seattle, WA-98195, USA {raphae lh , cl zhang ,we ld} @ c s . [sent-2, score-0.025]
2 edu Abstract Many researchers are trying to use information extraction (IE) to create large-scale knowledge bases from natural language text on the Web. [sent-4, score-0.036]
3 However, the primary approach (supervised learning of relation-specific extractors) requires manually-labeled training data for each relation and doesn’t scale to the thousands of relations encoded in Web text. [sent-5, score-0.203]
4 This paper presents LUCHS, a self-supervised, relation-specific IE system which learns 5025 relations more than an order of magnitude greater than any previous approach with an average F1 score of 61%. [sent-6, score-0.138]
5 Crucial to LUCHS’s performance is an automated system for dynamic lexicon learning, which allows it to learn accurately from heuristically-generated training data, which is often noisy and sparse. [sent-7, score-0.183]
6 — — 1 Introduction Information extraction (IE), the process of generating relational data from natural-language text, has gained popularity for its potential applications in Web search, question answering and other tasks. [sent-8, score-0.147]
7 Supervised approaches require manually-labeled training data for each relation and hence can’t scale to handle the thousands of relations encoded in Web text. [sent-16, score-0.203]
8 Open extraction is more scalable, but has lower precision and recall. [sent-17, score-0.036]
9 Furthermore, open extraction doesn’t canonicalize relations, so any application using the output must deal with homonymy and synonymy. [sent-18, score-0.036]
10 A third approach, sometimes refered to as weak supervision, is to heuristically match values from — a database to text, thus generating a set of training data for self-supervised learning of relationspecific extractors (Craven and Kumlien, 1999). [sent-19, score-0.455]
11 With the Kylin system (Wu and Weld, 2007) applied this idea to Wikipedia by matching values of an article’s infobox1 attributes to corresponding sentences in the article, and suggested that their approach could extract thousands of relations (Wu et al. [sent-20, score-0.256]
12 Unfortunately, however, they never tested the idea on more than a dozen relations. [sent-22, score-0.028]
13 We note that Wikipedia’s infobox ‘ontology’ is a particularly interesting target for extraction. [sent-24, score-0.239]
14 Unfortunately, the schemata are surprisingly noisy and most are sparsely populated; challenging conditions for extraction. [sent-26, score-0.126]
15 This paper presents LUCHS, an autonomous, self-supervised system, which learns 5025 relational extractors an order of magnitude greater than any previous effort. [sent-27, score-0.512]
16 Like Kylin, LUCHS cre— ates training data by matching Wikipedia attribute values with corresponding sentences, but by itself, this method was insufficient for accurate extraction of most relations. [sent-28, score-0.236]
17 Thus, LUCHS introduces a new technique, dynamic lexicon features, which dramatically improves performance when learning from sparse data and that way enables scalability. [sent-29, score-0.143]
18 1 Dynamic Lexicon Features Figure 1 summarizes the architecture of LUCHS. [sent-31, score-0.026]
19 At the highest level, LUCHS’s offline training process resembles that of Kylin. [sent-32, score-0.079]
20 Wikipedia pages 1A sizable fraction of Wikipedia articles have associated infoboxes relational summaries of the key aspects of the subject of the article. [sent-33, score-0.255]
21 For example, the infobox for Alan Turing’s Wikipedia page lists the values of 10 attributes, including his birthdate, nationality and doctoral advisor. [sent-34, score-0.33]
22 In order to handle sparsity in its heuristically-generated training data, LUCHS generates custom lexicon features when learning each relational extractor. [sent-38, score-0.248]
23 containing infoboxes are used to train a classifier that can predict the appropriate schema for pages missing infoboxes. [sent-39, score-0.229]
24 Additionally, the values of infobox attributes are compared with article sentences to heuristically generate training data. [sent-40, score-0.716]
25 LUCHS’s major innovation is a feature-generation process, which starts by harvesting HTML lists from a 5B document Web crawl, discarding 98% to create a set of 49M semantically-relevant lists. [sent-41, score-0.024]
26 When learning an extractor for relation R, LUCHS extracts seed phrases from R’s training data and uses a semi-supervised learning algorithm to create several relation-specific lexicons at different points on a precision-recall spectrum. [sent-42, score-0.195]
27 These lexicons form Boolean features which, along with lexical and dependency parser-based features, are used to produce a CRF extractor for each relation one which performs much better than lexiconfree extraction on sparse training data. [sent-43, score-0.296]
28 At runtime, LUCHS feeds pages to the article classfier, which predicts which infobox schema is most appropriate for extraction. [sent-44, score-0.684]
29 Then a small set of relation-specific extractors are applied to each sentence, outputting tuples. [sent-45, score-0.331]
30 Our experiments demonstrate a high F1 score, 61%, across the 5025 relational extractors learned. [sent-46, score-0.415]
31 2 Summary This paper makes several contributions: • We present LUCHS, a self-supervised IE sys- • • • Wteme capable of learning more than an order of magnitude more relation-specific extractors than previous systems. [sent-48, score-0.373]
32 We describe the construction and use of dynWaem idce lexicon features, a cntioovnel technique, th dyatenables hyper-lexicalized extractors which cope effectively with sparse training data. [sent-49, score-0.42]
33 We evaluate the overall end-to-end performance oalfu LUCHS, showing an dF-t1o score o pfe r6f1o%rwhen extracting relations from randomly selected Wikipedia pages. [sent-50, score-0.041]
34 We present a comprehensive set of additional experiments, evaluating iLvUeC sHeSt o’sf aindddiivtiidounaall components, measuring the effect of dynamic lexicon features, testing sensitivity to varying amounts of training data, and categorizing the types of relations LUCHS can extract. [sent-51, score-0.238]
35 2 Heuristic Generation of Training Data Wikipedia is an ideal starting point for our longterm goal of creating a massive knowledge base of extracted facts for two reasons. [sent-52, score-0.075]
36 Infoboxes are short, manually-created tabular summaries of many articles’ key facts effectively defining a relational schema for that class of entity. [sent-55, score-0.347]
37 Since the same facts are often expressed in both article and ontology, matching values of the ontology to the article can deliver valuable, though noisy, training data. [sent-56, score-0.743]
38 For example, the Wikipedia article on “Jerry Seinfeld” contains the sentence “Seinfeld was born in Brooklyn, New York. [sent-57, score-0.287]
39 ” and the article’s infobox contains the attribute “birth place = Brooklyn”. [sent-58, score-0.318]
40 By matching the attribute’s value “Brooklyn” to the sentence, we can heuristically generate training data for a birth place extractor. [sent-59, score-0.176]
41 This data is noisy; some attributes will not find matches, while others will find many co-incidental matches. [sent-60, score-0.099]
42 — 3 Learning Extractors We first assume that each Wikipedia infobox attribute corresponds to a unique relation (but see Section 5. [sent-61, score-0.363]
43 Running a relation- specific extractor for each of Wikipedia’s 34,000 unique infobox attributes on each of Wikipedia’s 50 million sentences would require 1. [sent-64, score-0.426]
44 We therefore choose a hierarchical approach that combines both article classifiers and relation extractors. [sent-66, score-0.337]
45 For each infobox schema, LUCHS trains a classifier that predicts if an article is likely to contain that schema. [sent-67, score-0.554]
46 Only when an article 287 is likely to contain a schema, does LUCHS run that schema’s relation extractors. [sent-68, score-0.305]
47 To extract infobox attributes from all of Wikipedia, LUCHS now needs orders of magnitude fewer executions. [sent-69, score-0.407]
48 While this approach does not propagate information from extractors back to article classifiers, experiments confirm that our article classifiers nonetheless deliver accurate results (Section 5. [sent-70, score-0.925]
49 In addition, our approach reduces the need for extractors to keep track of the larger context, thus simplifying the extraction problem. [sent-72, score-0.34]
50 More challenging are the attribute extractors, which we wish to be simple, fast, and able to well capture local dependencies. [sent-75, score-0.105]
51 The states of output variables represent discrete labels l, e. [sent-85, score-0.049]
52 In our case, variables are connected in a chain, following the first-order Markov assumption. [sent-88, score-0.049]
53 We train to maximize conditional likelihood of output variables given an input probability distribution. [sent-89, score-0.049]
54 Feature functions allow complex, overlapping global features with lookahead. [sent-92, score-0.058]
55 Common techniques for learning the weights λk include numeric optimization algorithms such as stochastic gradient descent or L-BFGS. [sent-93, score-0.04]
56 The linear-chain layout enables efficient interence using the dynamic programming-based Viterbi algorithm (Lafferty et al. [sent-95, score-0.088]
57 We evaluate nine kinds of Boolean features: Words For each input word w we introduce feature fww(yt−1 , yt, x, t) := 1[xt=w] . [sent-97, score-0.032]
58 State Transitions For each transition between output labels li, lj we add feature yt, x, t) := 1[yt−1=li∧yt=lj]. [sent-98, score-0.12]
59 fltir,lajn(yt−1, Word Contextualization For parameters p and s we add features fwprev(yt−1 , yt, x, t) := fwsub(yt−1, t) 1[w∈{xt−p,. [sent-99, score-0.064]
60 Digits yt, x, add feature We add feature fdig(yt−1 , yt, x, t) := 1[xtis digits]. [sent-107, score-0.134]
61 Dependencies We set fdep(yt−1 , yt, x, t) to the lemmatized sequence of words from xt to the root of the dependency tree, computed using the Stanford parser (Marneffe et al. [sent-108, score-0.137]
wordName wordTfidf (topN-words)
[('luchs', 0.524), ('yt', 0.456), ('extractors', 0.304), ('article', 0.26), ('infobox', 0.239), ('wikipedia', 0.203), ('schema', 0.128), ('relational', 0.111), ('xt', 0.11), ('attributes', 0.099), ('brooklyn', 0.098), ('extractor', 0.088), ('attribute', 0.079), ('infoboxes', 0.076), ('seinfeld', 0.075), ('xtis', 0.075), ('ie', 0.072), ('magnitude', 0.069), ('kylin', 0.065), ('heuristically', 0.062), ('thousands', 0.059), ('dynamic', 0.058), ('crf', 0.054), ('digits', 0.053), ('lj', 0.053), ('birth', 0.051), ('lexicon', 0.049), ('ontology', 0.049), ('variables', 0.049), ('noisy', 0.045), ('facts', 0.045), ('relation', 0.045), ('unfortunately', 0.042), ('deliver', 0.041), ('relations', 0.041), ('numeric', 0.04), ('weld', 0.038), ('lafferty', 0.037), ('boolean', 0.036), ('sparse', 0.036), ('extraction', 0.036), ('add', 0.035), ('summaries', 0.035), ('contextualization', 0.033), ('fdep', 0.033), ('headers', 0.033), ('nationality', 0.033), ('ates', 0.033), ('classfier', 0.033), ('doctoral', 0.033), ('jerry', 0.033), ('kfk', 0.033), ('raphael', 0.033), ('relationspecific', 0.033), ('sizable', 0.033), ('classifiers', 0.032), ('feature', 0.032), ('doesn', 0.032), ('matching', 0.032), ('training', 0.031), ('comprehensive', 0.031), ('lexicons', 0.031), ('predicts', 0.03), ('sparsely', 0.03), ('craven', 0.03), ('crawl', 0.03), ('trillion', 0.03), ('longterm', 0.03), ('gaussians', 0.03), ('layout', 0.03), ('features', 0.029), ('functions', 0.029), ('web', 0.028), ('custom', 0.028), ('sx', 0.028), ('dozen', 0.028), ('categorizing', 0.028), ('tabular', 0.028), ('propagate', 0.028), ('learns', 0.028), ('encoded', 0.027), ('born', 0.027), ('turing', 0.027), ('hoffmann', 0.027), ('capitalized', 0.027), ('outputting', 0.027), ('lemmatized', 0.027), ('feeds', 0.027), ('challenging', 0.026), ('architecture', 0.026), ('textrunner', 0.025), ('schemata', 0.025), ('freitag', 0.025), ('lh', 0.025), ('values', 0.025), ('classifier', 0.025), ('autonomous', 0.024), ('resembles', 0.024), ('discarding', 0.024), ('offline', 0.024)]
simIndex simValue paperId paperTitle
same-paper 1 0.99999946 159 acl-2010-Learning 5000 Relational Extractors
Author: Raphael Hoffmann ; Congle Zhang ; Daniel S. Weld
Abstract: Many researchers are trying to use information extraction (IE) to create large-scale knowledge bases from natural language text on the Web. However, the primary approach (supervised learning of relation-specific extractors) requires manually-labeled training data for each relation and doesn’t scale to the thousands of relations encoded in Web text. This paper presents LUCHS, a self-supervised, relation-specific IE system which learns 5025 relations more than an order of magnitude greater than any previous approach with an average F1 score of 61%. Crucial to LUCHS’s performance is an automated system for dynamic lexicon learning, which allows it to learn accurately from heuristically-generated training data, which is often noisy and sparse. — —
2 0.22347365 197 acl-2010-Practical Very Large Scale CRFs
Author: Thomas Lavergne ; Olivier Cappe ; Francois Yvon
Abstract: Conditional Random Fields (CRFs) are a widely-used approach for supervised sequence labelling, notably due to their ability to handle large description spaces and to integrate structural dependency between labels. Even for the simple linearchain model, taking structure into account implies a number of parameters and a computational effort that grows quadratically with the cardinality of the label set. In this paper, we address the issue of training very large CRFs, containing up to hun- dreds output labels and several billion features. Efficiency stems here from the sparsity induced by the use of a ‘1 penalty term. Based on our own implementation, we compare three recent proposals for implementing this regularization strategy. Our experiments demonstrate that very large CRFs can be trained efficiently and that very large models are able to improve the accuracy, while delivering compact parameter sets.
3 0.21689536 185 acl-2010-Open Information Extraction Using Wikipedia
Author: Fei Wu ; Daniel S. Weld
Abstract: Information-extraction (IE) systems seek to distill semantic relations from naturallanguage text, but most systems use supervised learning of relation-specific examples and are thus limited by the availability of training data. Open IE systems such as TextRunner, on the other hand, aim to handle the unbounded number of relations found on the Web. But how well can these open systems perform? This paper presents WOE, an open IE system which improves dramatically on TextRunner’s precision and recall. The key to WOE’s performance is a novel form of self-supervised learning for open extractors using heuris— tic matches between Wikipedia infobox attribute values and corresponding sentences to construct training data. Like TextRunner, WOE’s extractor eschews lexicalized features and handles an unbounded set of semantic relations. WOE can operate in two modes: when restricted to POS tag features, it runs as quickly as TextRunner, but when set to use dependency-parse features its precision and recall rise even higher.
4 0.1343917 261 acl-2010-Wikipedia as Sense Inventory to Improve Diversity in Web Search Results
Author: Celina Santamaria ; Julio Gonzalo ; Javier Artiles
Abstract: Is it possible to use sense inventories to improve Web search results diversity for one word queries? To answer this question, we focus on two broad-coverage lexical resources of a different nature: WordNet, as a de-facto standard used in Word Sense Disambiguation experiments; and Wikipedia, as a large coverage, updated encyclopaedic resource which may have a better coverage of relevant senses in Web pages. Our results indicate that (i) Wikipedia has a much better coverage of search results, (ii) the distribution of senses in search results can be estimated using the internal graph structure of the Wikipedia and the relative number of visits received by each sense in Wikipedia, and (iii) associating Web pages to Wikipedia senses with simple and efficient algorithms, we can produce modified rankings that cover 70% more Wikipedia senses than the original search engine rankings. 1 Motivation The application of Word Sense Disambiguation (WSD) to Information Retrieval (IR) has been subject of a significant research effort in the recent past. The essential idea is that, by indexing and matching word senses (or even meanings) , the retrieval process could better handle polysemy and synonymy problems (Sanderson, 2000). In practice, however, there are two main difficulties: (i) for long queries, IR models implicitly perform disambiguation, and thus there is little room for improvement. This is the case with most standard IR benchmarks, such as TREC (trec.nist.gov) or CLEF (www.clef-campaign.org) ad-hoc collections; (ii) for very short queries, disambiguation j ul io @ l i uned . e s j avart s . @bec . uned . e s may not be possible or even desirable. This is often the case with one word and even two word queries in Web search engines. In Web search, there are at least three ways of coping with ambiguity: • • • Promoting diversity in the search results (Clarke negt al., 2008): given th seea query s”uolatssis”, the search engine may try to include representatives for different senses of the word (such as the Oasis band, the Organization for the Advancement of Structured Information Standards, the online fashion store, etc.) among the top results. Search engines are supposed to handle diversity as one of the multiple factors that influence the ranking. Presenting the results as a set of (labelled) cPlruessteenrtsi nragth tehre eth reansu as a a rsan ake sde lti ostf (Carpineto et al., 2009). Complementing search results with search suggestions (e.g. e”oaracshis band”, ”woitahsis s fashion store”) that serve to refine the query in the intended way (Anick, 2003). All of them rely on the ability of the search engine to cluster search results, detecting topic similarities. In all of them, disambiguation is implicit, a side effect of the process but not its explicit target. Clustering may detect that documents about the Oasis band and the Oasis fashion store deal with unrelated topics, but it may as well detect a group of documents discussing why one of the Oasis band members is leaving the band, and another group of documents about Oasis band lyrics; both are different aspects of the broad topic Oasis band. A perfect hierarchical clustering should distinguish between the different Oasis senses at a first level, and then discover different topics within each of the senses. Is it possible to use sense inventories to improve search results for one word queries? To answer 1357 Proce dingUsp opfs thaela 4, 8Stwhe Adnen u,a 1l1- M16e Jtiunlgy o 2f0 t1h0e. A ?c s 2o0c1ia0ti Aosnso focria Ctio nm fpourta Ctoiomnpault Laitniognuaislt Licisn,g puaigsetisc 1s357–136 , this question, we will focus on two broad-coverage lexical resources of a different nature: WordNet (Miller et al., 1990), as a de-facto standard used in Word Sense Disambiguation experiments and many other Natural Language Processing research fields; and Wikipedia (www.wikipedia.org), as a large coverage and updated encyclopedic resource which may have a better coverage of relevant senses in Web pages. Our hypothesis is that, under appropriate conditions, any of the above mechanisms (clustering, search suggestions, diversity) might benefit from an explicit disambiguation (classification of pages in the top search results) using a wide-coverage sense inventory. Our research is focused on four relevant aspects of the problem: 1. Coverage: Are Wikipedia/Wordnet senses representative of search results? Otherwise, trying to make a disambiguation in terms of a fixed sense inventory would be meaningless. 2. If the answer to (1) is positive, the reverse question is also interesting: can we estimate search results diversity using our sense inven- tories? 3. Sense frequencies: knowing sense frequencies in (search results) Web pages is crucial to have a usable sense inventory. Is it possible to estimate Web sense frequencies from currently available information? 4. Classification: The association of Web pages to word senses must be done with some unsupervised algorithm, because it is not possible to hand-tag training material for every possible query word. Can this classification be done accurately? Can it be effective to promote diversity in search results? In order to provide an initial answer to these questions, we have built a corpus consisting of 40 nouns and 100 Google search results per noun, manually annotated with the most appropriate Wordnet and Wikipedia senses. Section 2 describes how this corpus has been created, and in Section 3 we discuss WordNet and Wikipedia coverage of search results according to our testbed. As this initial results clearly discard Wordnet as a sense inventory for the task, the rest of the paper mainly focuses on Wikipedia. In Section 4 we estimate search results diversity from our testbed, finding that the use of Wikipedia could substantially improve diversity in the top results. In Section 5 we use the Wikipedia internal link structure and the number of visits per page to estimate relative frequencies for Wikipedia senses, obtaining an estimation which is highly correlated with actual data in our testbed. Finally, in Section 6 we discuss a few strategies to classify Web pages into word senses, and apply the best classifier to enhance diversity in search results. The paper concludes with a discussion of related work (Section 7) and an overall discussion of our results in Section 8. 2 Test Set 2.1 Set of Words The most crucial step in building our test set is choosing the set of words to be considered. We are looking for words which are susceptible to form a one-word query for a Web search engine, and therefore we should focus on nouns which are used to denote one or more named entities. At the same time we want to have some degree of comparability with previous research on Word Sense Disambiguation, which points to noun sets used in Senseval/SemEval evaluation campaigns1 . Our budget for corpus annotation was enough for two persons-month, which limited us to handle 40 nouns (usually enough to establish statistically significant differences between WSD algorithms, although obviously limited to reach solid figures about the general behaviour of words in the Web). With these arguments in mind, we decided to choose: (i) 15 nouns from the Senseval-3 lexical sample dataset, which have been previously employed by (Mihalcea, 2007) in a related experiment (see Section 7); (ii) 25 additional words which satisfy two conditions: they are all ambiguous, and they are all names for music bands in one of their senses (not necessarily the most salient). The Senseval set is: {argument, arm, atmosphere, bank, degree, difference, disc, irmm-, age, paper, party, performance, plan, shelter, sort, source}. The bands set is {amazon, apple, camel, cell, columbia, cream, foreigner, fox, genesis, jaguar, oasis, pioneer, police, puma, rainbow, shell, skin, sun, tesla, thunder, total, traffic, trapeze, triumph, yes}. Fpoerz e,a trchiu noun, we looked up all its possible senses in WordNet 3.0 and in Wikipedia (using 1http://senseval.org 1358 Table 1: Coverage of Search Results: Wikipedia vs. WordNet Wikiped#ia documents # senses WordNe#t documents Senseval setava2il4a2b/1le0/u0sedassign8e7d7 to (5 s9o%me) senseavai9la2b/5le2/usedassigne6d96 to (4 s6o%m)e sense # senses BaTnodtsa lset868420//21774421323558 ((5546%%))17780/3/9911529995 (2 (342%%)) Wikipedia disambiguation pages). Wikipedia has an average of 22 senses per noun (25.2 in the Bands set and 16. 1in the Senseval set), and Wordnet a much smaller figure, 4.5 (3. 12 for the Bands set and 6.13 for the Senseval set). For a conventional dictionary, a higher ambiguity might indicate an excess of granularity; for an encyclopaedic resource such as Wikipedia, however, it is just an indication of larger coverage. Wikipedia en- tries for camel which are not in WordNet, for instance, include the Apache Camel routing and mediation engine, the British rock band, the brand of cigarettes, the river in Cornwall, and the World World War I fighter biplane. 2.2 Set of Documents We retrieved the 150 first ranked documents for each noun, by submitting the nouns as queries to a Web search engine (Google). Then, for each document, we stored both the snippet (small description of the contents of retrieved document) and the whole HTML document. This collection of documents contain an implicit new inventory of senses, based on Web search, as documents retrieved by a noun query are associated with some sense of the noun. Given that every document in the top Web search results is supposed to be highly relevant for the query word, we assume a ”one sense per document” scenario, although we allow annotators to assign more than one sense per document. In general this assumption turned out to be correct except in a few exceptional cases (such as Wikipedia disambiguation pages): only nine docu- ments received more than one WordNet sense, and 44 (1. 1% of all annotated pages) received more than one Wikipedia sense. 2.3 Manual Annotation We implemented an annotation interface which stored all documents and a short description for every Wordnet and Wikipedia sense. The annotators had to decide, for every document, whether there was one or more appropriate senses in each of the dictionaries. They were instructed to provide annotations for 100 documents per name; if an URL in the list was corrupt or not available, it had to be discarded. We provided 150 documents per name to ensure that the figure of 100 usable documents per name could be reached without problems. Each judge provided annotations for the 4,000 documents in the final data set. In a second round, they met and discussed their independent annotations together, reaching a consensus judgement for every document. 3 Coverage of Web Search Results: Wikipedia vs Wordnet Table 1 shows how Wikipedia and Wordnet cover the senses in search results. We report each noun subset separately (Senseval and bands subsets) as well as aggregated figures. The most relevant fact is that, unsurprisingly, Wikipedia senses cover much more search results (56%) than Wordnet (32%). If we focus on the top ten results, in the bands subset (which should be more representative of plausible web queries) Wikipedia covers 68% of the top ten documents. This is an indication that it can indeed be useful for promoting diversity or help clustering search results: even if 32% of the top ten documents are not covered by Wikipedia, it is still a representative source of senses in the top search results. We have manually examined all documents in the top ten results that are not covered by Wikipedia: a majority of the missing senses consists of names of (generally not well-known) companies (45%) and products or services (26%); the other frequent type (12%) of non annotated doc- ument is disambiguation pages (from Wikipedia and also from other dictionaries). It is also interesting to examine the degree of overlap between Wikipedia and Wordnet senses. Being two different types of lexical resource, they might have some degree of complementarity. Table 2 shows, however, that this is not the case: most of the (annotated) documents either fit Wikipedia senses (26%) or both Wikipedia and Wordnet (29%), and just 3% fit Wordnet only. 1359 Table 2: Overlap between Wikipedia and Wordnet in Search Results # documents annotated with Senseval setWikipe60di7a ( &40 W%o)rdnetWi2k7ip0e (d1i8a% on)lyWo8r9d (n6e%t o)nly534no (3n6e%) BaTnodtsa slet1517729 ( (2239%%))1708566 (3 (216%%))12176 ( (13%%))11614195 ( (4415%%)) Therefore, Wikipedia seems to extend the coverage of Wordnet rather than providing complementary sense information. If we wanted to extend the coverage of Wikipedia, the best strategy seems to be to consider lists ofcompanies, products and services, rather than complementing Wikipedia with additional sense inventories. 4 Diversity in Google Search Results Once we know that Wikipedia senses are a representative subset of actual Web senses (covering more than half of the documents retrieved by the search engine), we can test how well search results respect diversity in terms of this subset of senses. Table 3 displays the number of different senses found at different depths in the search results rank, and the average proportion of total senses that they represent. These results suggest that diversity is not a major priority for ranking results: the top ten results only cover, in average, 3 Wikipedia senses (while the average number of senses listed in Wikipedia is 22). When considering the first 100 documents, this number grows up to 6.85 senses per noun. Another relevant figure is the frequency of the most frequent sense for each word: in average, 63% of the pages in search results belong to the most frequent sense of the query word. This is roughly comparable with most frequent sense figures in standard annotated corpora such as Semcor (Miller et al., 1993) and the Senseval/Semeval data sets, which suggests that diversity may not play a major role in the current Google ranking algorithm. Of course this result must be taken with care, because variability between words is high and unpredictable, and we are using only 40 nouns for our experiment. But what we have is a positive indication that Wikipedia could be used to improve diversity or cluster search results: potentially the first top ten results could cover 6.15 different senses in average (see Section 6.5), which would be a substantial growth. 5 Sense Frequency Estimators for Wikipedia Wikipedia disambiguation pages contain no systematic information about the relative importance of senses for a given word. Such information, however, is crucial in a lexicon, because sense distributions tend to be skewed, and knowing them can help disambiguation algorithms. We have attempted to use two estimators of expected sense distribution: • • Internal relevance of a word sense, measured as incoming alinnckes o ffo ar wthoer U seRnLs o, fm a given sense in Wikipedia. External relevance of a word sense, measured as ttheren naulm rebleevr aonfc vei osifts a f woro trhde s eUnRsLe, mofe a given sense (as reported in http://stats.grok.se). The number of internal incoming links is expected to be relatively stable for Wikipedia articles. As for the number of visits, we performed a comparison of the number of visits received by the bands noun subset in May, June and July 2009, finding a stable-enough scenario with one notorious exception: the number of visits to the noun Tesla raised dramatically in July, because July 10 was the anniversary of the birth of Nicola Tesla, and a special Google logo directed users to the Wikipedia page for the scientist. We have measured correlation between the relative frequencies derived from these two indicators and the actual relative frequencies in our testbed. Therefore, for each noun w and for each sense wi, we consider three values: (i) proportion of documents retrieved for w which are manually assigned to each sense wi; (ii) inlinks(wi) : relative amount of incoming links to each sense wi; and (iii) visits(wi) : relative number of visits to the URL for each sense wi. We have measured the correlation between these three values using a linear regression correlation coefficient, which gives a correlation value of .54 for the number of visits and of .71 for the number of incoming links. Both estimators seem 1360 Table 3: Diversity in Search Results according to Wikipedia F ir s t 12570 docsBave6n425.rd9854a6 s8get#snSe 65sien43. v68a3s27elarcthesTu6543l.o t5083as5lBvaen.r3d2a73s81gectovrSaegnso. 4f32v615aWlsiketpdaTs.3oe249tn01asle to be positively correlated with real relative frequencies in our testbed, with a strong preference for the number of links. We have experimented with weighted combinations of both indicators, using weights of the form (k, 1 k) , k ∈ {0, 0.1, 0.2 . . . 1}, reaching a maxi(mk,a1l c−okrre),lkati ∈on { 0of, .07.13, f0o.r2 t.h.e. following weights: − freq(wi) = 0.9∗inlinks(wi) +0. 1∗visits(wi) (1) This weighted estimator provides a slight advantage over the use of incoming links only (.73 vs .71). Overall, we have an estimator which has a strong correlation with the distribution of senses in our testbed. In the next section we will test its utility for disambiguation purposes. 6 Association of Wikipedia Senses to Web Pages We want to test whether the information provided by Wikipedia can be used to classify search results accurately. Note that we do not want to consider approaches that involve a manual creation of training material, because they can’t be used in practice. Given a Web page p returned by the search engine for the query w, and the set of senses w1 . . . wn listed in Wikipedia, the task is to assign the best candidate sense to p. We consider two different techniques: • A basic Information Retrieval approach, wAhe breas tche I dfoocrmumateionnts Ranetdr tvhael Wikipedia pages are represented using a Vector Space Model (VSM) and compared with a standard cosine measure. This is a basic approach which, if successful, can be used efficiently to classify search results. An approach based on a state-of-the-art supervised oWacShD b system, extracting training examples automatically from Wikipedia content. We also compute two baselines: • • • A random assignment of senses (precision is computed as itghnem ienvnter osfe oenfs tehse ( pnruemcibsieorn o isf senses, for every test case). A most frequent sense heuristic which uses our eosstitm fraetiqoune otf s sense frequencies acnhd u assigns the same sense (the most frequent) to all documents. Both are naive baselines, but it must be noted that the most frequent sense heuristic is usually hard to beat for unsupervised WSD algorithms in most standard data sets. We now describe each of the two main approaches in detail. 6.1 VSM Approach For each word sense, we represent its Wikipedia page in a (unigram) vector space model, assigning standard tf*idf weights to the words in the document. idf weights are computed in two different ways: 1. Experiment VSM computes inverse document frequencies in the collection of retrieved documents (for the word being considered). 2. Experiment VSM-GT uses the statistics provided by the Google Terabyte collection (Brants and Franz, 2006), i.e. it replaces the collection of documents with statistics from a representative snapshot of the Web. 3. Experiment VSM-mixed combines statistics from the collection and from the Google Terabyte collection, following (Chen et al., 2009). The document p is represented in the same vector space as the Wikipedia senses, and it is compared with each of the candidate senses wi via the cosine similarity metric (we have experimented 1361 with other similarity metrics such as χ2, but differences are irrelevant). The sense with the highest similarity to p is assigned to the document. In case of ties (which are rare), we pick the first sense in the Wikipedia disambiguation page (which in practice is like a random decision, because senses in disambiguation pages do not seem to be ordered according to any clear criteria). We have also tested a variant of this approach which uses the estimation of sense frequencies presented above: once the similarities are computed, we consider those cases where two or more senses have a similar score (in particular, all senses with a score greater or equal than 80% of the highest score). In that cases, instead of using the small similarity differences to select a sense, we pick up the one which has the largest frequency according to our estimator. We have applied this strategy to the best performing system, VSM-GT, resulting in experiment VSM-GT+freq. 6.2 WSD Approach We have used TiMBL (Daelemans et al., 2001), a state-of-the-art supervised WSD system which uses Memory-Based Learning. The key, in this case, is how to extract learning examples from the Wikipedia automatically. For each word sense, we basically have three sources of examples: (i) occurrences of the word in the Wikipedia page for the word sense; (ii) occurrences of the word in Wikipedia pages pointing to the page for the word sense; (iii) occurrences of the word in external pages linked in the Wikipedia page for the word sense. After an initial manual inspection, we decided to discard external pages for being too noisy, and we focused on the first two options. We tried three alternatives: • • • TiMBL-core uses only the examples found Tini MtheB page rfoer u tshees sense being atrmaipneleds. TiMBL-inlinks uses the examples found in Wikipedia pages pointing etxoa mthep sense being trained. TiMBL-all uses both sources of examples. In order to classify a page p with respect to the senses for a word w, we first disambiguate all occurrences of w in the page p. Then we choose the sense which appears most frequently in the page according to TiMBL results. In case of ties we pick up the first sense listed in the Wikipedia disambiguation page. We have also experimented with a variant of the approach that uses our estimation of sense frequencies, similarly to what we did with the VSM approach. In this case, (i) when there is a tie between two or more senses (which is much more likely than in the VSM approach), we pick up the sense with the highest frequency according to our estimator; and (ii) when no sense reaches 30% of the cases in the page to be disambiguated, we also resort to the most frequent sense heuristic (among the candidates for the page). This experiment is called TiMBL-core+freq (we discarded ”inlinks” and ”all” versions because they were clearly worse than ”core”). 6.3 Classification Results Table 4 shows classification results. The accuracy of systems is reported as precision, i.e. the number of pages correctly classified divided by the total number of predictions. This is approximately the same as recall (correctly classified pages divided by total number of pages) for our systems, because the algorithms provide an answer for every page containing text (actual coverage is 94% because some pages only contain text as part of an image file such as photographs and logotypes). Table 4: Classification Results Experiment Precision random most frequent sense (estimation) .19 .46 TiMBL-core TiMBL-inlinks TiMBL-all TiMBL-core+freq .60 .50 .58 .67 VSM VSM-GT VSM-mixed VSM-GT+freq .67 .68 .67 .69 All systems are significantly better than the random and most frequent sense baselines (using p < 0.05 for a standard t-test). Overall, both approaches (using TiMBL WSD machinery and using VSM) lead to similar results (.67 vs. .69), which would make VSM preferable because it is a simpler and more efficient approach. Taking a 1362 Figure 1: Precision/Coverage curves for VSM-GT+freq classification algorithm closer look at the results with TiMBL, there are a couple of interesting facts: • There is a substantial difference between using only examples itaalke dnif fferroemnc tehe b Wikipedia Web page for the sense being trained (TiMBL-core, .60) and using examples from the Wikipedia pages pointing to that page (TiMBL-inlinks, .50). Examples taken from related pages (even if the relationship is close as in this case) seem to be too noisy for the task. This result is compatible with findings in (Santamar ı´a et al., 2003) using the Open Directory Project to extract examples automatically. • Our estimation of sense frequencies turns oOuutr rto e tbiem very helpful sfeor f cases wcihesere t our TiMBL-based algorithm cannot provide an answer: precision rises from .60 (TiMBLcore) to .67 (TiMBL-core+freq). The difference is statistically significant (p < 0.05) according to the t-test. As for the experiments with VSM, the variations tested do not provide substantial improvements to the baseline (which is .67). Using idf frequencies obtained from the Google Terabyte corpus (instead of frequencies obtained from the set of retrieved documents) provides only a small improvement (VSM-GT, .68), and adding the estimation of sense frequencies gives another small improvement (.69). Comparing the baseline VSM with the optimal setting (VSM-GT+freq), the difference is small (.67 vs .69) but relatively robust (p = 0.066 according to the t-test). Remarkably, the use of frequency estimations is very helpful for the WSD approach but not for the SVM one, and they both end up with similar performance figures; this might indicate that using frequency estimations is only helpful up to certain precision ceiling. 6.4 Precision/Coverage Trade-off All the above experiments are done at maximal coverage, i.e., all systems assign a sense for every document in the test collection (at least for every document with textual content). But it is possible to enhance search results diversity without annotating every document (in fact, not every document can be assigned to a Wikipedia sense, as we have discussed in Section 3). Thus, it is useful to investigate which is the precision/coverage trade-off in our dataset. We have experimented with the best performing system (VSM-GT+freq), introducing a similarity threshold: assignment of a document to a sense is only done if the similarity of the document to the Wikipedia page for the sense exceeds the similarity threshold. We have computed precision and coverage for every threshold in the range [0.00 −0.90] (beyond 0e.v9e0ry coverage was null) anngde represented 0th] e(b breeysuolntds in Figure 1 (solid line). The graph shows that we 1363 can classify around 20% of the documents with a precision above .90, and around 60% of the documents with a precision of .80. Note that we are reporting disambiguation results using a conventional WSD test set, i.e., one in which every test case (every document) has been manually assigned to some Wikipedia sense. But in our Web Search scenario, 44% of the documents were not assigned to any Wikipedia sense: in practice, our classification algorithm would have to cope with all this noise as well. Figure 1 (dotted line) shows how the precision/coverage curve is affected when the algorithm attempts to disambiguate all documents retrieved by Google, whether they can in fact be assigned to a Wikipedia sense or not. At a coverage of 20%, precision drops approximately from .90 to .70, and at a coverage of 60% it drops from .80 to .50. We now address the question of whether this performance is good enough to improve search re- sults diversity in practice. 6.5 Using Classification to Promote Diversity We now want to estimate how the reported classification accuracy may perform in practice to enhance diversity in search results. In order to provide an initial answer to this question, we have re-ranked the documents for the 40 nouns in our testbed, using our best classifier (VSM-GT+freq) and making a list of the top-ten documents with the primary criterion of maximising the number of senses represented in the set, and the secondary criterion of maximising the similarity scores of the documents to their assigned senses. The algorithm proceeds as follows: we fill each position in the rank (starting at rank 1), with the document which has the highest similarity to some of the senses which are not yet represented in the rank; once all senses are represented, we start choosing a second representative for each sense, following the same criterion. The process goes on until the first ten documents are selected. We have also produced a number of alternative rankings for comparison purposes: clustering (centroids): this method applies eHriiengrarc (hciecnatlr Agglomerative Clustering which proved to be the most competitive clustering algorithm in a similar task (Artiles et al., 2009) to the set of search results, forcing the algorithm to create ten clusters. The centroid of each cluster is then selected Table 5: Enhancement of Search Results Diversity • – – rank@10 # senses coverage Original rank2.8049% Wikipedia 4.75 77% clustering (centroids) 2.50 42% clustering (top ranked) 2.80 46% random 2.45 43% upper bound6.1597% as one of the top ten documents in the new rank. • clustering (top ranked): Applies the same clustering algorithm, db u)t: tAhpisp lti emse t tehe s top ranked document (in the original Google rank) of each cluster is selected. • • random: Randomly selects ten documents frraonmd otmhe: :se Rt aofn dreomtrielyve sde lreecstuslts te. upper bound: This is the maximal diversity tuhpapt can o beu nodb:tai Tnheids iins our mteasxtbiemda. lN doivteer tshitayt coverage is not 100%, because some words have more than ten meanings in Wikipedia and we are only considering the top ten documents. All experiments have been applied on the full set of documents in the testbed, including those which could not be annotated with any Wikipedia sense. Coverage is computed as the ratio of senses that appear in the top ten results compared to the number of senses that appear in all search results. Results are presented in Table 5. Note that diversity in the top ten documents increases from an average of 2.80 Wikipedia senses represented in the original search engine rank, to 4.75 in the modified rank (being 6.15 the upper bound), with the coverage of senses going from 49% to 77%. With a simple VSM algorithm, the coverage of Wikipedia senses in the top ten results is 70% larger than in the original ranking. Using Wikipedia to enhance diversity seems to work much better than clustering: both strategies to select a representative from each cluster are unable to improve the diversity of the original ranking. Note, however, that our evaluation has a bias towards using Wikipedia, because only Wikipedia senses are considered to estimate diversity. Of course our results do not imply that the Wikipedia modified rank is better than the original 1364 Google rank: there are many other factors that influence the final ranking provided by a search engine. What our results indicate is that, with simple and efficient algorithms, Wikipedia can be used as a reference to improve search results diversity for one-word queries. 7 Related Work Web search results clustering and diversity in search results are topics that receive an increasing attention from the research community. Diversity is used both to represent sub-themes in a broad topic, or to consider alternative interpretations for ambiguous queries (Agrawal et al., 2009), which is our interest here. Standard IR test collections do not usually consider ambiguous queries, and are thus inappropriate to test systems that promote diversity (Sanderson, 2008); it is only recently that appropriate test collections are being built, such as (Paramita et al., 2009) for image search and (Artiles et al., 2009) for person name search. We see our testbed as complementary to these ones, and expect that it can contribute to foster research on search results diversity. To our knowledge, Wikipedia has not explicitly been used before to promote diversity in search results; but in (Gollapudi and Sharma, 2009), it is used as a gold standard to evaluate diversification algorithms: given a query with a Wikipedia disambiguation page, an algorithm is evaluated as promoting diversity when different documents in the search results are semantically similar to different Wikipedia pages (describing the alternative senses of the query). Although semantic similarity is measured automatically in this work, our results confirm that this evaluation strategy is sound, because Wikipedia senses are indeed representative of search results. (Clough et al., 2009) analyses query diversity in a Microsoft Live Search, using click entropy and query reformulation as diversity indicators. It was found that at least 9.5% - 16.2% of queries could benefit from diversification, although no correlation was found between the number of senses of a word in Wikipedia and the indicators used to discover diverse queries. This result does not discard, however, that queries where applying diversity is useful cannot benefit from Wikipedia as a sense inventory. In the context of clustering, (Carmel et al., 2009) successfully employ Wikipedia to enhance automatic cluster labeling, finding that Wikipedia labels agree with manual labels associated by humans to a cluster, much more than with signif- icant terms that are extracted directly from the text. In a similar line, both (Gabrilovich and Markovitch, 2007) and (Syed et al., 2008) provide evidence suggesting that categories of Wikipedia articles can successfully describe common concepts in documents. In the field of Natural Language Processing, there has been successful attempts to connect Wikipedia entries to Wordnet senses: (RuizCasado et al., 2005) reports an algorithm that provides an accuracy of 84%. (Mihalcea, 2007) uses internal Wikipedia hyperlinks to derive sensetagged examples. But instead of using Wikipedia directly as sense inventory, Mihalcea then manually maps Wikipedia senses into Wordnet senses (claiming that, at the time of writing the paper, Wikipedia did not consistently report ambiguity in disambiguation pages) and shows that a WSD system based on acquired sense-tagged examples reaches an accuracy well beyond an (informed) most frequent sense heuristic. 8 Conclusions We have investigated whether generic lexical resources can be used to promote diversity in Web search results for one-word, ambiguous queries. We have compared WordNet and Wikipedia and arrived to a number of conclusions: (i) unsurprisingly, Wikipedia has a much better coverage of senses in search results, and is therefore more appropriate for the task; (ii) the distribution of senses in search results can be estimated using the internal graph structure of the Wikipedia and the relative number of visits received by each sense in Wikipedia, and (iii) associating Web pages to Wikipedia senses with simple and efficient algorithms, we can produce modified rankings that cover 70% more Wikipedia senses than the original search engine rankings. We expect that the testbed created for this research will complement the - currently short - set of benchmarking test sets to explore search results diversity and query ambiguity. Our testbed is publicly available for research purposes at http://nlp.uned.es. Our results endorse further investigation on the use of Wikipedia to organize search results. Some limitations of our research, however, must be 1365 noted: (i) the nature of our testbed (with every search result manually annotated in terms of two sense inventories) makes it too small to extract solid conclusions on Web searches (ii) our work does not involve any study of diversity from the point of view of Web users (i.e. when a Web query addresses many different use needs in practice); research in (Clough et al., 2009) suggests that word ambiguity in Wikipedia might not be related with diversity of search needs; (iii) we have tested our classifiers with a simple re-ordering of search results to test how much diversity can be improved, but a search results ranking depends on many other factors, some of them more crucial than diversity; it remains to be tested how can we use document/Wikipedia associations to improve search results clustering (for instance, providing seeds for the clustering process) and to provide search suggestions. Acknowledgments This work has been partially funded by the Spanish Government (project INES/Text-Mess) and the Xunta de Galicia. References R. Agrawal, S. Gollapudi, A. Halverson, and S. Leong. 2009. Diversifying Search Results. In Proc. of WSDM’09. ACM. P. Anick. 2003. Using Terminological Feedback for Web Search Refinement : a Log-based Study. In Proc. ACM SIGIR 2003, pages 88–95. ACM New York, NY, USA. J. Artiles, J. Gonzalo, and S. Sekine. 2009. WePS 2 Evaluation Campaign: overview of the Web People Search Clustering Task. In 2nd Web People Search Evaluation Workshop (WePS 2009), 18th WWW Conference. 2009. T. Brants and A. Franz. 2006. Web 1T 5-gram, version 1. Philadelphia: Linguistic Data Consortium. D. Carmel, H. Roitman, and N. Zwerdling. 2009. Enhancing Cluster Labeling using Wikipedia. In Pro- ceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval, pages 139–146. ACM. C. Carpineto, S. Osinski, G. Romano, and Dawid Weiss. 2009. A Survey of Web Clustering Engines. ACM Computing Surveys, 41(3). Y. Chen, S. Yat Mei Lee, and C. Huang. 2009. PolyUHK: A Robust Information Extraction System for Web Personal Names. In Proc. WWW’09 (WePS2 Workshop). ACM. C. Clarke, M. Kolla, G. Cormack, O. Vechtomova, A. Ashkan, S. B ¨uttcher, and I. MacKinnon. 2008. Novelty and Diversity in Information Retrieval Evaluation. In Proc. SIGIR ’08, pages 659–666. ACM. P. Clough, M. Sanderson, M. Abouammoh, S. Navarro, and M. Paramita. 2009. Multiple Approaches to Analysing Query Diversity. In Proc. of SIGIR 2009. ACM. W. Daelemans, J. Zavrel, K. van der Sloot, and A. van den Bosch. 2001 . TiMBL: Tilburg Memory Based Learner, version 4.0, Reference Guide. Technical report, University of Antwerp. E. Gabrilovich and S. Markovitch. 2007. Computing Semantic Relatedness using Wikipedia-based Explicit Semantic Analysis. In Proceedings of The 20th International Joint Conference on Artificial Intelligence (IJCAI), Hyderabad, India. S. Gollapudi and A. Sharma. 2009. An Axiomatic Approach for Result Diversification. In Proc. WWW 2009, pages 381–390. ACM New York, NY, USA. R. Mihalcea. 2007. Using Wikipedia for Automatic Word Sense Disambiguation. In Proceedings of NAACL HLT, volume 2007. G. Miller, C. R. Beckwith, D. Fellbaum, Gross, and K. Miller. 1990. Wordnet: An on-line lexical database. International Journal of Lexicograph, 3(4). G.A Miller, C. Leacock, R. Tengi, and Bunker R. T. 1993. A Semantic Concordance. In Proceedings of the ARPA WorkShop on Human Language Technology. San Francisco, Morgan Kaufman. M. Paramita, M. Sanderson, and P. Clough. 2009. Diversity in Photo Retrieval: Overview of the ImageCLEFPhoto task 2009. CLEF working notes, 2009. M. Ruiz-Casado, E. Alfonseca, and P. Castells. 2005. Automatic Assignment of Wikipedia Encyclopaedic Entries to Wordnet Synsets. Advances in Web Intelligence, 3528:380–386. M. Sanderson. 2000. Retrieving with Good Sense. Information Retrieval, 2(1):49–69. M. Sanderson. 2008. Ambiguous Queries: Test Collections Need More Sense. In Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval, pages 499–506. ACM New York, NY, USA. C. Santamar ı´a, J. Gonzalo, and F. Verdejo. 2003. Automatic Association of Web Directories to Word Senses. Computational Linguistics, 29(3):485–502. Z. S. Syed, T. Finin, and Joshi. A. 2008. Wikipedia as an Ontology for Describing Documents. In Proc. ICWSM’08. 1366
5 0.091687508 113 acl-2010-Extraction and Approximation of Numerical Attributes from the Web
Author: Dmitry Davidov ; Ari Rappoport
Abstract: We present a novel framework for automated extraction and approximation of numerical object attributes such as height and weight from the Web. Given an object-attribute pair, we discover and analyze attribute information for a set of comparable objects in order to infer the desired value. This allows us to approximate the desired numerical values even when no exact values can be found in the text. Our framework makes use of relation defining patterns and WordNet similarity information. First, we obtain from the Web and WordNet a list of terms similar to the given object. Then we retrieve attribute values for each term in this list, and information that allows us to compare different objects in the list and to infer the attribute value range. Finally, we combine the retrieved data for all terms from the list to select or approximate the requested value. We evaluate our method using automated question answering, WordNet enrichment, and comparison with answers given in Wikipedia and by leading search engines. In all of these, our framework provides a significant improvement.
6 0.086948395 15 acl-2010-A Semi-Supervised Key Phrase Extraction Approach: Learning from Title Phrases through a Document Semantic Network
7 0.081955574 156 acl-2010-Knowledge-Rich Word Sense Disambiguation Rivaling Supervised Systems
8 0.079719827 44 acl-2010-BabelNet: Building a Very Large Multilingual Semantic Network
9 0.067686997 250 acl-2010-Untangling the Cross-Lingual Link Structure of Wikipedia
10 0.065241069 247 acl-2010-Unsupervised Event Coreference Resolution with Rich Linguistic Features
11 0.064935237 125 acl-2010-Generating Templates of Entity Summaries with an Entity-Aspect Model and Pattern Mining
12 0.059913419 124 acl-2010-Generating Image Descriptions Using Dependency Relational Patterns
13 0.05450137 218 acl-2010-Structural Semantic Relatedness: A Knowledge-Based Method to Named Entity Disambiguation
14 0.053925592 209 acl-2010-Sentiment Learning on Product Reviews via Sentiment Ontology Tree
15 0.051470112 85 acl-2010-Detecting Experiences from Weblogs
16 0.049703971 111 acl-2010-Extracting Sequences from the Web
17 0.048284382 23 acl-2010-Accurate Context-Free Parsing with Combinatory Categorial Grammar
18 0.044751469 245 acl-2010-Understanding the Semantic Structure of Noun Phrase Queries
19 0.043369651 6 acl-2010-A Game-Theoretic Model of Metaphorical Bargaining
20 0.04219811 160 acl-2010-Learning Arguments and Supertypes of Semantic Relations Using Recursive Patterns
topicId topicWeight
[(0, -0.132), (1, 0.067), (2, -0.051), (3, -0.002), (4, 0.071), (5, -0.011), (6, 0.083), (7, 0.011), (8, -0.0), (9, 0.034), (10, -0.034), (11, -0.07), (12, -0.115), (13, -0.071), (14, -0.004), (15, 0.075), (16, 0.014), (17, 0.23), (18, -0.007), (19, 0.012), (20, -0.057), (21, 0.011), (22, -0.108), (23, -0.037), (24, -0.109), (25, 0.043), (26, 0.176), (27, -0.186), (28, -0.03), (29, -0.028), (30, 0.022), (31, -0.039), (32, 0.03), (33, 0.053), (34, 0.099), (35, 0.195), (36, 0.016), (37, -0.154), (38, 0.117), (39, 0.08), (40, -0.059), (41, 0.052), (42, -0.053), (43, 0.145), (44, -0.002), (45, -0.096), (46, 0.084), (47, 0.1), (48, -0.016), (49, -0.186)]
simIndex simValue paperId paperTitle
same-paper 1 0.95585752 159 acl-2010-Learning 5000 Relational Extractors
Author: Raphael Hoffmann ; Congle Zhang ; Daniel S. Weld
Abstract: Many researchers are trying to use information extraction (IE) to create large-scale knowledge bases from natural language text on the Web. However, the primary approach (supervised learning of relation-specific extractors) requires manually-labeled training data for each relation and doesn’t scale to the thousands of relations encoded in Web text. This paper presents LUCHS, a self-supervised, relation-specific IE system which learns 5025 relations more than an order of magnitude greater than any previous approach with an average F1 score of 61%. Crucial to LUCHS’s performance is an automated system for dynamic lexicon learning, which allows it to learn accurately from heuristically-generated training data, which is often noisy and sparse. — —
2 0.76538777 185 acl-2010-Open Information Extraction Using Wikipedia
Author: Fei Wu ; Daniel S. Weld
Abstract: Information-extraction (IE) systems seek to distill semantic relations from naturallanguage text, but most systems use supervised learning of relation-specific examples and are thus limited by the availability of training data. Open IE systems such as TextRunner, on the other hand, aim to handle the unbounded number of relations found on the Web. But how well can these open systems perform? This paper presents WOE, an open IE system which improves dramatically on TextRunner’s precision and recall. The key to WOE’s performance is a novel form of self-supervised learning for open extractors using heuris— tic matches between Wikipedia infobox attribute values and corresponding sentences to construct training data. Like TextRunner, WOE’s extractor eschews lexicalized features and handles an unbounded set of semantic relations. WOE can operate in two modes: when restricted to POS tag features, it runs as quickly as TextRunner, but when set to use dependency-parse features its precision and recall rise even higher.
3 0.67609119 197 acl-2010-Practical Very Large Scale CRFs
Author: Thomas Lavergne ; Olivier Cappe ; Francois Yvon
Abstract: Conditional Random Fields (CRFs) are a widely-used approach for supervised sequence labelling, notably due to their ability to handle large description spaces and to integrate structural dependency between labels. Even for the simple linearchain model, taking structure into account implies a number of parameters and a computational effort that grows quadratically with the cardinality of the label set. In this paper, we address the issue of training very large CRFs, containing up to hun- dreds output labels and several billion features. Efficiency stems here from the sparsity induced by the use of a ‘1 penalty term. Based on our own implementation, we compare three recent proposals for implementing this regularization strategy. Our experiments demonstrate that very large CRFs can be trained efficiently and that very large models are able to improve the accuracy, while delivering compact parameter sets.
4 0.53502363 111 acl-2010-Extracting Sequences from the Web
Author: Anthony Fader ; Stephen Soderland ; Oren Etzioni
Abstract: Classical Information Extraction (IE) systems fill slots in domain-specific frames. This paper reports on SEQ, a novel open IE system that leverages a domainindependent frame to extract ordered sequences such as presidents of the United States or the most common causes of death in the U.S. SEQ leverages regularities about sequences to extract a coherent set of sequences from Web text. SEQ nearly doubles the area under the precision-recall curve compared to an extractor that does not exploit these regularities.
5 0.53339463 113 acl-2010-Extraction and Approximation of Numerical Attributes from the Web
Author: Dmitry Davidov ; Ari Rappoport
Abstract: We present a novel framework for automated extraction and approximation of numerical object attributes such as height and weight from the Web. Given an object-attribute pair, we discover and analyze attribute information for a set of comparable objects in order to infer the desired value. This allows us to approximate the desired numerical values even when no exact values can be found in the text. Our framework makes use of relation defining patterns and WordNet similarity information. First, we obtain from the Web and WordNet a list of terms similar to the given object. Then we retrieve attribute values for each term in this list, and information that allows us to compare different objects in the list and to infer the attribute value range. Finally, we combine the retrieved data for all terms from the list to select or approximate the requested value. We evaluate our method using automated question answering, WordNet enrichment, and comparison with answers given in Wikipedia and by leading search engines. In all of these, our framework provides a significant improvement.
6 0.38179985 261 acl-2010-Wikipedia as Sense Inventory to Improve Diversity in Web Search Results
7 0.36295289 250 acl-2010-Untangling the Cross-Lingual Link Structure of Wikipedia
8 0.33427852 68 acl-2010-Conditional Random Fields for Word Hyphenation
9 0.304052 245 acl-2010-Understanding the Semantic Structure of Noun Phrase Queries
10 0.29875597 248 acl-2010-Unsupervised Ontology Induction from Text
11 0.29863286 125 acl-2010-Generating Templates of Entity Summaries with an Entity-Aspect Model and Pattern Mining
12 0.296848 222 acl-2010-SystemT: An Algebraic Approach to Declarative Information Extraction
13 0.28068075 124 acl-2010-Generating Image Descriptions Using Dependency Relational Patterns
14 0.27684489 15 acl-2010-A Semi-Supervised Key Phrase Extraction Approach: Learning from Title Phrases through a Document Semantic Network
15 0.27242607 166 acl-2010-Learning Word-Class Lattices for Definition and Hypernym Extraction
16 0.26450318 44 acl-2010-BabelNet: Building a Very Large Multilingual Semantic Network
17 0.24846467 109 acl-2010-Experiments in Graph-Based Semi-Supervised Learning Methods for Class-Instance Acquisition
18 0.24099956 194 acl-2010-Phrase-Based Statistical Language Generation Using Graphical Models and Active Learning
19 0.2379988 181 acl-2010-On Learning Subtypes of the Part-Whole Relation: Do Not Mix Your Seeds
20 0.23182423 134 acl-2010-Hierarchical Sequential Learning for Extracting Opinions and Their Attributes
topicId topicWeight
[(14, 0.018), (25, 0.069), (33, 0.022), (42, 0.023), (59, 0.093), (72, 0.408), (73, 0.033), (76, 0.013), (78, 0.025), (83, 0.075), (84, 0.025), (98, 0.107)]
simIndex simValue paperId paperTitle
same-paper 1 0.82237715 159 acl-2010-Learning 5000 Relational Extractors
Author: Raphael Hoffmann ; Congle Zhang ; Daniel S. Weld
Abstract: Many researchers are trying to use information extraction (IE) to create large-scale knowledge bases from natural language text on the Web. However, the primary approach (supervised learning of relation-specific extractors) requires manually-labeled training data for each relation and doesn’t scale to the thousands of relations encoded in Web text. This paper presents LUCHS, a self-supervised, relation-specific IE system which learns 5025 relations more than an order of magnitude greater than any previous approach with an average F1 score of 61%. Crucial to LUCHS’s performance is an automated system for dynamic lexicon learning, which allows it to learn accurately from heuristically-generated training data, which is often noisy and sparse. — —
2 0.77438056 171 acl-2010-Metadata-Aware Measures for Answer Summarization in Community Question Answering
Author: Mattia Tomasoni ; Minlie Huang
Abstract: This paper presents a framework for automatically processing information coming from community Question Answering (cQA) portals with the purpose of generating a trustful, complete, relevant and succinct summary in response to a question. We exploit the metadata intrinsically present in User Generated Content (UGC) to bias automatic multi-document summarization techniques toward high quality information. We adopt a representation of concepts alternative to n-grams and propose two concept-scoring functions based on semantic overlap. Experimental re- sults on data drawn from Yahoo! Answers demonstrate the effectiveness of our method in terms of ROUGE scores. We show that the information contained in the best answers voted by users of cQA portals can be successfully complemented by our method.
3 0.70372492 209 acl-2010-Sentiment Learning on Product Reviews via Sentiment Ontology Tree
Author: Wei Wei ; Jon Atle Gulla
Abstract: Existing works on sentiment analysis on product reviews suffer from the following limitations: (1) The knowledge of hierarchical relationships of products attributes is not fully utilized. (2) Reviews or sentences mentioning several attributes associated with complicated sentiments are not dealt with very well. In this paper, we propose a novel HL-SOT approach to labeling a product’s attributes and their associated sentiments in product reviews by a Hierarchical Learning (HL) process with a defined Sentiment Ontology Tree (SOT). The empirical analysis against a humanlabeled data set demonstrates promising and reasonable performance of the proposed HL-SOT approach. While this paper is mainly on sentiment analysis on reviews of one product, our proposed HLSOT approach is easily generalized to labeling a mix of reviews of more than one products.
4 0.66645032 127 acl-2010-Global Learning of Focused Entailment Graphs
Author: Jonathan Berant ; Ido Dagan ; Jacob Goldberger
Abstract: We propose a global algorithm for learning entailment relations between predicates. We define a graph structure over predicates that represents entailment relations as directed edges, and use a global transitivity constraint on the graph to learn the optimal set of edges, by formulating the optimization problem as an Integer Linear Program. We motivate this graph with an application that provides a hierarchical summary for a set of propositions that focus on a target concept, and show that our global algorithm improves performance by more than 10% over baseline algorithms.
5 0.53573883 174 acl-2010-Modeling Semantic Relevance for Question-Answer Pairs in Web Social Communities
Author: Baoxun Wang ; Xiaolong Wang ; Chengjie Sun ; Bingquan Liu ; Lin Sun
Abstract: Quantifying the semantic relevance between questions and their candidate answers is essential to answer detection in social media corpora. In this paper, a deep belief network is proposed to model the semantic relevance for question-answer pairs. Observing the textual similarity between the community-driven questionanswering (cQA) dataset and the forum dataset, we present a novel learning strategy to promote the performance of our method on the social community datasets without hand-annotating work. The experimental results show that our method outperforms the traditional approaches on both the cQA and the forum corpora.
6 0.51885402 113 acl-2010-Extraction and Approximation of Numerical Attributes from the Web
7 0.50721914 215 acl-2010-Speech-Driven Access to the Deep Web on Mobile Devices
8 0.475362 122 acl-2010-Generating Fine-Grained Reviews of Songs from Album Reviews
9 0.47294843 185 acl-2010-Open Information Extraction Using Wikipedia
10 0.45636046 218 acl-2010-Structural Semantic Relatedness: A Knowledge-Based Method to Named Entity Disambiguation
11 0.45352262 208 acl-2010-Sentence and Expression Level Annotation of Opinions in User-Generated Discourse
12 0.45114434 109 acl-2010-Experiments in Graph-Based Semi-Supervised Learning Methods for Class-Instance Acquisition
13 0.45026612 189 acl-2010-Optimizing Question Answering Accuracy by Maximizing Log-Likelihood
14 0.44474846 248 acl-2010-Unsupervised Ontology Induction from Text
15 0.44429827 160 acl-2010-Learning Arguments and Supertypes of Semantic Relations Using Recursive Patterns
16 0.44338435 251 acl-2010-Using Anaphora Resolution to Improve Opinion Target Identification in Movie Reviews
17 0.4399116 245 acl-2010-Understanding the Semantic Structure of Noun Phrase Queries
18 0.43526298 121 acl-2010-Generating Entailment Rules from FrameNet
19 0.4327639 134 acl-2010-Hierarchical Sequential Learning for Extracting Opinions and Their Attributes
20 0.43091029 63 acl-2010-Comparable Entity Mining from Comparative Questions