acl acl2010 acl2010-86 knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Bonnie Webber ; Markus Egg ; Valia Kordoni
Abstract: unkown-abstract
Reference: text
sentIndex sentText sentNum sentScore
1 2 Content Overview This tutorial consists of four parts. [sent-9, score-0.185]
2 Part Istarts with a brief introduction to different bases for discourse structuring, properties of discourse structure that are relevant to LT, and accessible evidence for discourse structure. [sent-10, score-2.207]
3 For discourse structure to be useful for language technologies, one must be able to automatically recognize or generate with it. [sent-11, score-0.741]
4 Hence, Part II surveys computational approaches to recognizing and generating discourse structure, both manually- authored approaches and ones developed through Machine Learning. [sent-12, score-0.9]
5 Part III of the tutorial describes applications of discourse structure recognition and generation in LT, as well as discourse-related resources being made available in English, German, Turkish, Hindi, Czech, Arabic and Chinese. [sent-13, score-1.092]
6 Part IV concludes with a list of future possibilities. [sent-14, score-0.051]
7 PART I General Overview – (a) Bases for structure in monologic, dialogic and multiparty discourse (b) Aspects of discourse structure relevant to Language Technology (c) Evidence for discource structure 2. [sent-16, score-1.756]
8 PART II Computational Recognition and Generation of discourse structure (a) Discourse chunking and parsing (b) Recognizing arguments and sense of discourse connectives – (c) Recognizing and generating entity- based discourse structure (d) Dialogue parsing 3. [sent-17, score-2.154]
9 PART III – Applications and Resources (a) Applications to Language Technology (b) Discourse structure resources (mono- lingual and multilingual) 4. [sent-18, score-0.265]
10 The theory and practice of discourse p◦a Drsainnige la Mnda srcuum (m20ar0i0za). [sent-31, score-0.723]
11 Sequence Models and Ranking Meth◦od Bse fonr W W Deilslncoerur (s2e0 0 Pa8r)s. [sent-52, score-0.097]
wordName wordTfidf (topN-words)
[('discourse', 0.584), ('tutorial', 0.185), ('rashmi', 0.178), ('deniz', 0.167), ('lt', 0.157), ('iii', 0.153), ('prasad', 0.139), ('recognizing', 0.128), ('turkish', 0.123), ('law', 0.123), ('bases', 0.12), ('structure', 0.112), ('barzilay', 0.105), ('regina', 0.105), ('iv', 0.099), ('cem', 0.097), ('fonr', 0.097), ('ddi', 0.097), ('dialogic', 0.097), ('dinesh', 0.097), ('kordoni', 0.097), ('miltsakaki', 0.097), ('multiparty', 0.097), ('nikhil', 0.097), ('pere', 0.097), ('ruket', 0.097), ('authored', 0.089), ('attendees', 0.089), ('valia', 0.089), ('wellner', 0.084), ('resources', 0.081), ('connectives', 0.079), ('asscolcia', 0.079), ('cgeom', 0.079), ('jtuulytor', 0.079), ('revisited', 0.079), ('bse', 0.079), ('hindi', 0.075), ('catching', 0.072), ('din', 0.072), ('loc', 0.072), ('webber', 0.072), ('pra', 0.072), ('lingual', 0.072), ('markus', 0.07), ('developments', 0.07), ('ii', 0.068), ('accessible', 0.065), ('int', 0.065), ('amsterdam', 0.065), ('sweden', 0.065), ('od', 0.065), ('structuring', 0.063), ('uppsala', 0.063), ('part', 0.063), ('lee', 0.061), ('drift', 0.06), ('lda', 0.06), ('overview', 0.06), ('coordination', 0.059), ('manfred', 0.059), ('relevant', 0.058), ('bonnie', 0.057), ('af', 0.057), ('saarland', 0.057), ('practice', 0.055), ('outline', 0.054), ('lillian', 0.054), ('technology', 0.053), ('chunking', 0.052), ('sc', 0.052), ('surveys', 0.052), ('concludes', 0.051), ('alan', 0.05), ('brief', 0.05), ('evidence', 0.05), ('edinburgh', 0.05), ('ben', 0.048), ('arabic', 0.048), ('mirella', 0.047), ('generating', 0.047), ('recognition', 0.045), ('applications', 0.045), ('recognize', 0.045), ('theory', 0.044), ('annotating', 0.044), ('marcu', 0.043), ('dialogue', 0.041), ('lapata', 0.041), ('la', 0.04), ('generation', 0.04), ('versus', 0.04), ('aims', 0.036), ('fo', 0.035), ('notion', 0.034), ('le', 0.034), ('multilingual', 0.034), ('annotation', 0.033), ('al', 0.032), ('czech', 0.032)]
simIndex simValue paperId paperTitle
same-paper 1 1.0000004 86 acl-2010-Discourse Structure: Theory, Practice and Use
Author: Bonnie Webber ; Markus Egg ; Valia Kordoni
Abstract: unkown-abstract
2 0.29017648 155 acl-2010-Kernel Based Discourse Relation Recognition with Temporal Ordering Information
Author: WenTing Wang ; Jian Su ; Chew Lim Tan
Abstract: Syntactic knowledge is important for discourse relation recognition. Yet only heuristically selected flat paths and 2-level production rules have been used to incorporate such information so far. In this paper we propose using tree kernel based approach to automatically mine the syntactic information from the parse trees for discourse analysis, applying kernel function to the tree structures directly. These structural syntactic features, together with other normal flat features are incorporated into our composite kernel to capture diverse knowledge for simultaneous discourse identification and classification for both explicit and implicit relations. The experiment shows tree kernel approach is able to give statistical significant improvements over flat syntactic path feature. We also illustrate that tree kernel approach covers more structure information than the production rules, which allows tree kernel to further incorporate information from a higher dimension space for possible better discrimination. Besides, we further propose to leverage on temporal ordering information to constrain the interpretation of discourse relation, which also demonstrate statistical significant improvements for discourse relation recognition on PDTB 2.0 for both explicit and implicit as well. University of Singapore Singapore 117417 sg tacl @ comp .nus .edu . sg 1
3 0.23281087 33 acl-2010-Assessing the Role of Discourse References in Entailment Inference
Author: Shachar Mirkin ; Ido Dagan ; Sebastian Pado
Abstract: Discourse references, notably coreference and bridging, play an important role in many text understanding applications, but their impact on textual entailment is yet to be systematically understood. On the basis of an in-depth analysis of entailment instances, we argue that discourse references have the potential of substantially improving textual entailment recognition, and identify a number of research directions towards this goal.
4 0.15120238 206 acl-2010-Semantic Parsing: The Task, the State of the Art and the Future
Author: Rohit J. Kate ; Yuk Wah Wong
Abstract: unkown-abstract
5 0.12159716 229 acl-2010-The Influence of Discourse on Syntax: A Psycholinguistic Model of Sentence Processing
Author: Amit Dubey
Abstract: Probabilistic models of sentence comprehension are increasingly relevant to questions concerning human language processing. However, such models are often limited to syntactic factors. This paper introduces a novel sentence processing model that consists of a parser augmented with a probabilistic logic-based model of coreference resolution, which allows us to simulate how context interacts with syntax in a reading task. Our simulations show that a Weakly Interactive cognitive architecture can explain data which had been provided as evidence for the Strongly Interactive hypothesis.
6 0.11603179 31 acl-2010-Annotation
7 0.10954595 246 acl-2010-Unsupervised Discourse Segmentation of Documents with Inherently Parallel Structure
8 0.10657294 59 acl-2010-Cognitively Plausible Models of Human Language Processing
9 0.092681609 260 acl-2010-Wide-Coverage NLP with Linguistically Expressive Grammars
10 0.08334782 243 acl-2010-Tree-Based and Forest-Based Translation
11 0.080445558 221 acl-2010-Syntax-to-Morphology Mapping in Factored Phrase-Based Statistical Machine Translation from English to Turkish
12 0.077257425 190 acl-2010-P10-5005 k2opt.pdf
13 0.077067345 38 acl-2010-Automatic Evaluation of Linguistic Quality in Multi-Document Summarization
14 0.066209517 47 acl-2010-Beetle II: A System for Tutoring and Computational Linguistics Experimentation
15 0.059537202 208 acl-2010-Sentence and Expression Level Annotation of Opinions in User-Generated Discourse
16 0.057525836 227 acl-2010-The Impact of Interpretation Problems on Tutorial Dialogue
17 0.056555714 101 acl-2010-Entity-Based Local Coherence Modelling Using Topological Fields
18 0.054352965 49 acl-2010-Beyond NomBank: A Study of Implicit Arguments for Nominal Predicates
19 0.048131291 81 acl-2010-Decision Detection Using Hierarchical Graphical Models
20 0.045833036 237 acl-2010-Topic Models for Word Sense Disambiguation and Token-Based Idiom Detection
topicId topicWeight
[(0, -0.122), (1, 0.066), (2, 0.006), (3, -0.132), (4, -0.081), (5, 0.043), (6, -0.01), (7, 0.01), (8, -0.096), (9, -0.072), (10, 0.021), (11, 0.017), (12, 0.079), (13, 0.227), (14, -0.11), (15, 0.129), (16, -0.029), (17, 0.008), (18, 0.247), (19, -0.173), (20, 0.043), (21, -0.064), (22, -0.204), (23, 0.0), (24, -0.047), (25, -0.015), (26, 0.043), (27, 0.13), (28, -0.027), (29, 0.124), (30, 0.103), (31, 0.071), (32, -0.158), (33, -0.129), (34, -0.036), (35, -0.01), (36, 0.088), (37, -0.039), (38, -0.114), (39, 0.097), (40, -0.174), (41, -0.089), (42, -0.137), (43, 0.095), (44, -0.04), (45, -0.155), (46, -0.082), (47, -0.146), (48, -0.088), (49, 0.062)]
simIndex simValue paperId paperTitle
same-paper 1 0.99378449 86 acl-2010-Discourse Structure: Theory, Practice and Use
Author: Bonnie Webber ; Markus Egg ; Valia Kordoni
Abstract: unkown-abstract
2 0.60267675 155 acl-2010-Kernel Based Discourse Relation Recognition with Temporal Ordering Information
Author: WenTing Wang ; Jian Su ; Chew Lim Tan
Abstract: Syntactic knowledge is important for discourse relation recognition. Yet only heuristically selected flat paths and 2-level production rules have been used to incorporate such information so far. In this paper we propose using tree kernel based approach to automatically mine the syntactic information from the parse trees for discourse analysis, applying kernel function to the tree structures directly. These structural syntactic features, together with other normal flat features are incorporated into our composite kernel to capture diverse knowledge for simultaneous discourse identification and classification for both explicit and implicit relations. The experiment shows tree kernel approach is able to give statistical significant improvements over flat syntactic path feature. We also illustrate that tree kernel approach covers more structure information than the production rules, which allows tree kernel to further incorporate information from a higher dimension space for possible better discrimination. Besides, we further propose to leverage on temporal ordering information to constrain the interpretation of discourse relation, which also demonstrate statistical significant improvements for discourse relation recognition on PDTB 2.0 for both explicit and implicit as well. University of Singapore Singapore 117417 sg tacl @ comp .nus .edu . sg 1
3 0.56209075 33 acl-2010-Assessing the Role of Discourse References in Entailment Inference
Author: Shachar Mirkin ; Ido Dagan ; Sebastian Pado
Abstract: Discourse references, notably coreference and bridging, play an important role in many text understanding applications, but their impact on textual entailment is yet to be systematically understood. On the basis of an in-depth analysis of entailment instances, we argue that discourse references have the potential of substantially improving textual entailment recognition, and identify a number of research directions towards this goal.
4 0.43441626 246 acl-2010-Unsupervised Discourse Segmentation of Documents with Inherently Parallel Structure
Author: Minwoo Jeong ; Ivan Titov
Abstract: Documents often have inherently parallel structure: they may consist of a text and commentaries, or an abstract and a body, or parts presenting alternative views on the same problem. Revealing relations between the parts by jointly segmenting and predicting links between the segments, would help to visualize such documents and construct friendlier user interfaces. To address this problem, we propose an unsupervised Bayesian model for joint discourse segmentation and alignment. We apply our method to the “English as a second language” podcast dataset where each episode is composed of two parallel parts: a story and an explanatory lecture. The predicted topical links uncover hidden re- lations between the stories and the lectures. In this domain, our method achieves competitive results, rivaling those of a previously proposed supervised technique.
5 0.42876536 190 acl-2010-P10-5005 k2opt.pdf
Author: empty-author
Abstract: unkown-abstract
6 0.4126327 206 acl-2010-Semantic Parsing: The Task, the State of the Art and the Future
7 0.37470517 229 acl-2010-The Influence of Discourse on Syntax: A Psycholinguistic Model of Sentence Processing
8 0.32028776 59 acl-2010-Cognitively Plausible Models of Human Language Processing
9 0.28975564 256 acl-2010-Vocabulary Choice as an Indicator of Perspective
10 0.27787089 81 acl-2010-Decision Detection Using Hierarchical Graphical Models
11 0.27488607 260 acl-2010-Wide-Coverage NLP with Linguistically Expressive Grammars
12 0.26584655 101 acl-2010-Entity-Based Local Coherence Modelling Using Topological Fields
13 0.24617521 31 acl-2010-Annotation
14 0.24265057 157 acl-2010-Last but Definitely Not Least: On the Role of the Last Sentence in Automatic Polarity-Classification
15 0.2388878 55 acl-2010-Bootstrapping Semantic Analyzers from Non-Contradictory Texts
16 0.23795693 221 acl-2010-Syntax-to-Morphology Mapping in Factored Phrase-Based Statistical Machine Translation from English to Turkish
17 0.1971439 82 acl-2010-Demonstration of a Prototype for a Conversational Companion for Reminiscing about Images
18 0.19323269 49 acl-2010-Beyond NomBank: A Study of Implicit Arguments for Nominal Predicates
19 0.18855505 218 acl-2010-Structural Semantic Relatedness: A Knowledge-Based Method to Named Entity Disambiguation
20 0.18634105 12 acl-2010-A Probabilistic Generative Model for an Intermediate Constituency-Dependency Representation
topicId topicWeight
[(25, 0.07), (28, 0.413), (42, 0.03), (44, 0.099), (59, 0.053), (73, 0.026), (78, 0.029), (83, 0.069), (84, 0.022), (98, 0.09)]
simIndex simValue paperId paperTitle
same-paper 1 0.78795886 86 acl-2010-Discourse Structure: Theory, Practice and Use
Author: Bonnie Webber ; Markus Egg ; Valia Kordoni
Abstract: unkown-abstract
2 0.59239721 49 acl-2010-Beyond NomBank: A Study of Implicit Arguments for Nominal Predicates
Author: Matthew Gerber ; Joyce Chai
Abstract: Despite its substantial coverage, NomBank does not account for all withinsentence arguments and ignores extrasentential arguments altogether. These arguments, which we call implicit, are important to semantic processing, and their recovery could potentially benefit many NLP applications. We present a study of implicit arguments for a select group of frequent nominal predicates. We show that implicit arguments are pervasive for these predicates, adding 65% to the coverage of NomBank. We demonstrate the feasibility of recovering implicit arguments with a supervised classification model. Our results and analyses provide a baseline for future work on this emerging task.
3 0.58368772 246 acl-2010-Unsupervised Discourse Segmentation of Documents with Inherently Parallel Structure
Author: Minwoo Jeong ; Ivan Titov
Abstract: Documents often have inherently parallel structure: they may consist of a text and commentaries, or an abstract and a body, or parts presenting alternative views on the same problem. Revealing relations between the parts by jointly segmenting and predicting links between the segments, would help to visualize such documents and construct friendlier user interfaces. To address this problem, we propose an unsupervised Bayesian model for joint discourse segmentation and alignment. We apply our method to the “English as a second language” podcast dataset where each episode is composed of two parallel parts: a story and an explanatory lecture. The predicted topical links uncover hidden re- lations between the stories and the lectures. In this domain, our method achieves competitive results, rivaling those of a previously proposed supervised technique.
4 0.44237912 163 acl-2010-Learning Lexicalized Reordering Models from Reordering Graphs
Author: Jinsong Su ; Yang Liu ; Yajuan Lv ; Haitao Mi ; Qun Liu
Abstract: Lexicalized reordering models play a crucial role in phrase-based translation systems. They are usually learned from the word-aligned bilingual corpus by examining the reordering relations of adjacent phrases. Instead of just checking whether there is one phrase adjacent to a given phrase, we argue that it is important to take the number of adjacent phrases into account for better estimations of reordering models. We propose to use a structure named reordering graph, which represents all phrase segmentations of a sentence pair, to learn lexicalized reordering models efficiently. Experimental results on the NIST Chinese-English test sets show that our approach significantly outperforms the baseline method. 1
5 0.38915369 165 acl-2010-Learning Script Knowledge with Web Experiments
Author: Michaela Regneri ; Alexander Koller ; Manfred Pinkal
Abstract: We describe a novel approach to unsupervised learning of the events that make up a script, along with constraints on their temporal ordering. We collect naturallanguage descriptions of script-specific event sequences from volunteers over the Internet. Then we compute a graph representation of the script’s temporal structure using a multiple sequence alignment algorithm. The evaluation of our system shows that we outperform two informed baselines.
6 0.38040388 243 acl-2010-Tree-Based and Forest-Based Translation
7 0.37033808 210 acl-2010-Sentiment Translation through Lexicon Induction
8 0.33914468 71 acl-2010-Convolution Kernel over Packed Parse Forest
9 0.32964209 247 acl-2010-Unsupervised Event Coreference Resolution with Rich Linguistic Features
10 0.32768798 109 acl-2010-Experiments in Graph-Based Semi-Supervised Learning Methods for Class-Instance Acquisition
11 0.32674181 120 acl-2010-Fully Unsupervised Core-Adjunct Argument Classification
12 0.32629019 128 acl-2010-Grammar Prototyping and Testing with the LinGO Grammar Matrix Customization System
13 0.32620195 218 acl-2010-Structural Semantic Relatedness: A Knowledge-Based Method to Named Entity Disambiguation
14 0.32378662 248 acl-2010-Unsupervised Ontology Induction from Text
15 0.32367337 153 acl-2010-Joint Syntactic and Semantic Parsing of Chinese
16 0.32354069 169 acl-2010-Learning to Translate with Source and Target Syntax
17 0.32311291 198 acl-2010-Predicate Argument Structure Analysis Using Transformation Based Learning
18 0.32306188 101 acl-2010-Entity-Based Local Coherence Modelling Using Topological Fields
19 0.32287103 158 acl-2010-Latent Variable Models of Selectional Preference
20 0.32245708 12 acl-2010-A Probabilistic Generative Model for an Intermediate Constituency-Dependency Representation