acl acl2013 acl2013-303 knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Ondrej Dusek ; Filip Jurcicek
Abstract: We present a novel method of statistical morphological generation, i.e. the prediction of inflected word forms given lemma, part-of-speech and morphological features, aimed at robustness to unseen inputs. Our system uses a trainable classifier to predict “edit scripts” that are then used to transform lemmas into inflected word forms. Suffixes of lemmas are included as features to achieve robustness. We evaluate our system on 6 languages with a varying degree of morphological richness. The results show that the system is able to learn most morphological phenomena and generalize to unseen inputs, producing significantly better results than a dictionarybased baseline.
Reference: text
sentIndex sentText sentNum sentScore
1 c z Abstract We present a novel method of statistical morphological generation, i. [sent-4, score-0.405]
2 the prediction of inflected word forms given lemma, part-of-speech and morphological features, aimed at robustness to unseen inputs. [sent-6, score-0.823]
3 Our system uses a trainable classifier to predict “edit scripts” that are then used to transform lemmas into inflected word forms. [sent-7, score-0.305]
4 Suffixes of lemmas are included as features to achieve robustness. [sent-8, score-0.071]
5 We evaluate our system on 6 languages with a varying degree of morphological richness. [sent-9, score-0.524]
6 The results show that the system is able to learn most morphological phenomena and generalize to unseen inputs, producing significantly better results than a dictionarybased baseline. [sent-10, score-0.751]
7 1 Introduction Surface realization is an integral part of all natural language generation (NLG) systems, albeit often implemented in a very simple manner, such as filling words into ready hand-written templates. [sent-11, score-0.395]
8 More sophisticated methods use hand-written grammars (Gatt and Reiter, 2009), possibly in combination with a statistical reranker (Langkilde and Knight, 1998). [sent-12, score-0.056]
9 However, this approach poses a problem in languages with a complex morphology. [sent-14, score-0.132]
10 ensuring that a word lemma will keep its base form at all times, often leads to very unnatural results (see Figure 1). [sent-17, score-0.299]
11 Some generators use a hand-made morphological dictionary Tot sewoilnrfdílbeicnítisnegrte-uhd-ež-ton-ia- v-mva-oe-tid-e l-i Jan -ě Novákov-éá-. [sent-18, score-0.525]
12 This is liked by user dmaatsivceuline (name)nfeomminininaetive DTěhkanukje ymoeu, (Jna nm e N)no mviáynaoktiu v e,r vpaošle h balyasl sob oevevynát nvcíor eřaetneod. [sent-19, score-0.123]
13 (cnoar mecet l efo t rumn:i nvfolceact ievde) Figure 1: Unnatural language resulting from templates with no inflection. [sent-20, score-0.13]
14 The sentences are taken from the Czech translations of Facebook and Doodle, which use simple templates to generate personalized texts. [sent-21, score-0.128]
15 for inflection (Ptá cˇek and Žabokrtský, 2006) or a dictionary learned from automatically tagged data (Toutanova et al. [sent-23, score-0.392]
16 That gives good results, but reaching sufficient coverage with a hand-made dictionary is a very demanding task and even using extreme amounts of automatically annotated data will not generalize beyond the word forms already encountered in the corpus. [sent-25, score-0.279]
17 Hand-written rules can become overly complex and are not easily adaptable for a different language. [sent-26, score-0.169]
18 Therefore, the presented method relies on a statistical approach that learns to predict morphological inflection from annotated data. [sent-27, score-0.733]
19 capable of generalizing to unseen inputs, and easily portable to different languages. [sent-30, score-0.195]
20 An attempt to implement statistical morphological generation has already been made by Bohnet et al. [sent-31, score-0.549]
21 However, their morphology generation was only a component of a complex generation system. [sent-33, score-0.448]
22 Therefore, no deep analysis of the capabilities of the methods has been performed. [sent-34, score-0.043]
23 In addition, their method did not attempt to generalize beyond seen inputs. [sent-35, score-0.084]
24 In this paper, we propose 158 Sofia, BuPrlgoacreiead, iAngusgu osft 4h-e9 A 2C01L3 S. [sent-36, score-0.044]
25 c d2en0t1 3Re Ases aorc hiat Wio nrk fsohro Cp,om papguesta 1ti5o8n–a1l6 L4in,guistics several improvements and provide a detailed evaluation of a statistical morphological inflection sys- tem, including more languages into the evaluation and focusing on robustness to unseen inputs. [sent-38, score-1.242]
26 The paper is structured as follows: first, we explain the problem of morphological generation (Section 2), then give an account of our system (Section 3). [sent-39, score-0.604]
27 Section 4 provides a detailed evaluation of the performance of our system in different languages. [sent-40, score-0.055]
28 We then compare our system to related works in Section 5. [sent-41, score-0.055]
29 This does not include generating auxiliary words (such as be → will be), which are asisluimaryed w toor d bes already generated. [sent-45, score-0.062]
30 word + N NS words + N N Neut,Pl,Dat Wörtern be + VBZ is ser +V gmeono=d=c,niundmic=ast,ipveer,tseonnse==3p,resent es Wort Figure 2: The task of morphological generation (examples for English, German, and Spanish). [sent-46, score-0.602]
31 While this problem can be solved by a set of rules to a great extent for languages with little morphology such as English (Minnen et al. [sent-47, score-0.206]
32 , 2001), it becomes much more complicated in languages with a complex nominal case system or multiple synthetic verbal inflection patterns, such as German or Czech. [sent-48, score-0.561]
33 Figure 3 shows an example of ambiguity in these languages. [sent-49, score-0.051]
34 This research aims to create a system that is easy to train from morphologically annotated data, yet able to infer and apply more general rules and generate forms unseen in the training corpus. [sent-50, score-0.322]
35 (2010), our system is based on the prediction of edit scripts (diffs) between the lemma and the target word form (see Section 3. [sent-52, score-0.647]
36 1), which are then used to derive the target word form from the lemma. [sent-53, score-0.044]
37 The same inflection pattern is used to express multiple morphological properties (left) and multiple patterns may express the same property (right). [sent-55, score-0.733]
38 4 then gives an overview of the whole morphological inflection process. [sent-61, score-0.733]
39 1 Lemma-Form Edit Scripts Our system uses lemma-form edit scripts based on the Levenshtein string distance metric (Levenshtein, 1966): the dynamic programming algorithm used to compute the distance can be adapted to produce diffs on characters, i. [sent-63, score-0.723]
40 a mapping from the source string (lemma) to the target string (word form) that indicates which characters were added, replaced or removed. [sent-65, score-0.211]
41 Adjacent changes in the string are joined together ntot produce a thoeta slt liongwe arr enu jominbeedr oof- more complex changes. [sent-69, score-0.451]
42 • • If the Levenshtein edit script indicates a reImfo thveal Loefv leentstehrtse nfr eomdi th scer beginning so fa t rheeword, we treat the target word form as irregular, i. [sent-70, score-0.386]
43 In our setup, the edit scripts need not be Itrnea oteudr as atomic, w edhiicth s aclrilopwtss nteoe tdrai nno separate classification models for word changes that are orthogonal (cf. [sent-73, score-0.601]
44 159 An example of the edit scripts generated by our system is shown in Figure 4. [sent-76, score-0.49]
wordName wordTfidf (topN-words)
[('morphological', 0.405), ('inflection', 0.328), ('scripts', 0.224), ('edit', 0.211), ('gen', 0.187), ('diffs', 0.152), ('ek', 0.152), ('unseen', 0.145), ('generation', 0.144), ('levenshtein', 0.137), ('inflected', 0.133), ('bohnet', 0.128), ('lemma', 0.113), ('realization', 0.112), ('nlg', 0.103), ('unnatural', 0.099), ('nn', 0.098), ('morphology', 0.092), ('german', 0.088), ('generalize', 0.084), ('string', 0.081), ('templates', 0.08), ('beginning', 0.072), ('forms', 0.072), ('lemmas', 0.071), ('robustness', 0.068), ('complex', 0.068), ('arr', 0.067), ('jur', 0.067), ('enu', 0.067), ('sob', 0.067), ('tot', 0.067), ('dictionary', 0.064), ('languages', 0.064), ('inputs', 0.063), ('minnen', 0.062), ('langkilde', 0.062), ('bes', 0.062), ('mof', 0.062), ('odu', 0.062), ('nno', 0.062), ('praha', 0.062), ('nov', 0.062), ('dictionarybased', 0.062), ('gatt', 0.062), ('jen', 0.062), ('changes', 0.061), ('nfr', 0.059), ('cek', 0.059), ('malostransk', 0.059), ('slt', 0.059), ('demanding', 0.059), ('liked', 0.056), ('filip', 0.056), ('reranker', 0.056), ('generators', 0.056), ('ufal', 0.056), ('enhancements', 0.056), ('system', 0.055), ('je', 0.053), ('ser', 0.053), ('integral', 0.053), ('adaptable', 0.051), ('abokrtsk', 0.051), ('irregular', 0.051), ('ambiguity', 0.051), ('rules', 0.05), ('portable', 0.05), ('symbolic', 0.05), ('efo', 0.05), ('tem', 0.05), ('characters', 0.049), ('personalized', 0.048), ('reiter', 0.048), ('joined', 0.048), ('vbz', 0.048), ('aorc', 0.047), ('ases', 0.047), ('nrk', 0.047), ('facebook', 0.047), ('corrections', 0.047), ('buprlgoacreiead', 0.046), ('fsohro', 0.046), ('hiat', 0.046), ('iangusgu', 0.046), ('papguesta', 0.046), ('synthetic', 0.046), ('trainable', 0.046), ('surface', 0.045), ('osft', 0.044), ('wio', 0.044), ('lemmatization', 0.044), ('form', 0.044), ('ready', 0.043), ('albeit', 0.043), ('orthogonal', 0.043), ('ej', 0.043), ('capabilities', 0.043), ('ensuring', 0.043), ('czech', 0.043)]
simIndex simValue paperId paperTitle
same-paper 1 1.0000001 303 acl-2013-Robust multilingual statistical morphological generation models
Author: Ondrej Dusek ; Filip Jurcicek
Abstract: We present a novel method of statistical morphological generation, i.e. the prediction of inflected word forms given lemma, part-of-speech and morphological features, aimed at robustness to unseen inputs. Our system uses a trainable classifier to predict “edit scripts” that are then used to transform lemmas into inflected word forms. Suffixes of lemmas are included as features to achieve robustness. We evaluate our system on 6 languages with a varying degree of morphological richness. The results show that the system is able to learn most morphological phenomena and generalize to unseen inputs, producing significantly better results than a dictionarybased baseline.
2 0.17723413 378 acl-2013-Using subcategorization knowledge to improve case prediction for translation to German
Author: Marion Weller ; Alexander Fraser ; Sabine Schulte im Walde
Abstract: This paper demonstrates the need and impact of subcategorization information for SMT. We combine (i) features on sourceside syntactic subcategorization and (ii) an external knowledge base with quantitative, dependency-based information about target-side subcategorization frames. A manual evaluation of an English-toGerman translation task shows that the subcategorization information has a positive impact on translation quality through better prediction of case.
3 0.17095038 78 acl-2013-Categorization of Turkish News Documents with Morphological Analysis
Author: Burak Kerim Akku� ; Ruket Cakici
Abstract: Morphologically rich languages such as Turkish may benefit from morphological analysis in natural language tasks. In this study, we examine the effects of morphological analysis on text categorization task in Turkish. We use stems and word categories that are extracted with morphological analysis as main features and compare them with fixed length stemmers in a bag of words approach with several learning algorithms. We aim to show the effects of using varying degrees of morphological information.
4 0.11418366 227 acl-2013-Learning to lemmatise Polish noun phrases
Author: Adam Radziszewski
Abstract: We present a novel approach to noun phrase lemmatisation where the main phase is cast as a tagging problem. The idea draws on the observation that the lemmatisation of almost all Polish noun phrases may be decomposed into transformation of singular words (tokens) that make up each phrase. We perform evaluation, which shows results similar to those obtained earlier by a rule-based system, while our approach allows to separate chunking from lemmatisation.
5 0.11235064 87 acl-2013-Compositional-ly Derived Representations of Morphologically Complex Words in Distributional Semantics
Author: Angeliki Lazaridou ; Marco Marelli ; Roberto Zamparelli ; Marco Baroni
Abstract: Speakers of a language can construct an unlimited number of new words through morphological derivation. This is a major cause of data sparseness for corpus-based approaches to lexical semantics, such as distributional semantic models of word meaning. We adapt compositional methods originally developed for phrases to the task of deriving the distributional meaning of morphologically complex words from their parts. Semantic representations constructed in this way beat a strong baseline and can be of higher quality than representations directly constructed from corpus data. Our results constitute a novel evaluation of the proposed composition methods, in which the full additive model achieves the best performance, and demonstrate the usefulness of a compositional morphology component in distributional semantics.
6 0.10895385 102 acl-2013-DErivBase: Inducing and Evaluating a Derivational Morphology Resource for German
7 0.097119279 86 acl-2013-Combining Referring Expression Generation and Surface Realization: A Corpus-Based Investigation of Architectures
8 0.096043654 330 acl-2013-Stem Translation with Affix-Based Rule Selection for Agglutinative Languages
10 0.092093587 110 acl-2013-Deepfix: Statistical Post-editing of Statistical Machine Translation Using Deep Syntactic Analysis
11 0.084680982 290 acl-2013-Question Analysis for Polish Question Answering
12 0.076932624 28 acl-2013-A Unified Morpho-Syntactic Scheme of Stanford Dependencies
13 0.073595509 21 acl-2013-A Statistical NLG Framework for Aggregated Planning and Realization
14 0.071781829 359 acl-2013-Translating Dialectal Arabic to English
15 0.068526901 343 acl-2013-The Effect of Higher-Order Dependency Features in Discriminative Phrase-Structure Parsing
16 0.067450047 90 acl-2013-Conditional Random Fields for Responsive Surface Realisation using Global Features
17 0.063988537 154 acl-2013-Extracting bilingual terminologies from comparable corpora
18 0.062976286 295 acl-2013-Real-World Semi-Supervised Learning of POS-Taggers for Low-Resource Languages
19 0.060516763 9 acl-2013-A Lightweight and High Performance Monolingual Word Aligner
20 0.054718357 80 acl-2013-Chinese Parsing Exploiting Characters
topicId topicWeight
[(0, 0.149), (1, -0.024), (2, -0.01), (3, -0.032), (4, -0.042), (5, -0.036), (6, -0.029), (7, -0.004), (8, 0.079), (9, 0.03), (10, -0.068), (11, 0.032), (12, 0.026), (13, 0.006), (14, -0.167), (15, -0.037), (16, -0.015), (17, -0.128), (18, -0.005), (19, -0.021), (20, -0.184), (21, 0.086), (22, 0.072), (23, 0.043), (24, -0.016), (25, -0.003), (26, -0.02), (27, -0.116), (28, 0.003), (29, -0.051), (30, 0.033), (31, -0.006), (32, -0.05), (33, 0.131), (34, -0.023), (35, -0.055), (36, -0.153), (37, 0.031), (38, -0.001), (39, -0.084), (40, -0.083), (41, 0.12), (42, 0.033), (43, 0.03), (44, -0.11), (45, -0.012), (46, 0.133), (47, 0.018), (48, -0.126), (49, 0.047)]
simIndex simValue paperId paperTitle
same-paper 1 0.9628914 303 acl-2013-Robust multilingual statistical morphological generation models
Author: Ondrej Dusek ; Filip Jurcicek
Abstract: We present a novel method of statistical morphological generation, i.e. the prediction of inflected word forms given lemma, part-of-speech and morphological features, aimed at robustness to unseen inputs. Our system uses a trainable classifier to predict “edit scripts” that are then used to transform lemmas into inflected word forms. Suffixes of lemmas are included as features to achieve robustness. We evaluate our system on 6 languages with a varying degree of morphological richness. The results show that the system is able to learn most morphological phenomena and generalize to unseen inputs, producing significantly better results than a dictionarybased baseline.
2 0.70914912 378 acl-2013-Using subcategorization knowledge to improve case prediction for translation to German
Author: Marion Weller ; Alexander Fraser ; Sabine Schulte im Walde
Abstract: This paper demonstrates the need and impact of subcategorization information for SMT. We combine (i) features on sourceside syntactic subcategorization and (ii) an external knowledge base with quantitative, dependency-based information about target-side subcategorization frames. A manual evaluation of an English-toGerman translation task shows that the subcategorization information has a positive impact on translation quality through better prediction of case.
3 0.69036937 78 acl-2013-Categorization of Turkish News Documents with Morphological Analysis
Author: Burak Kerim Akku� ; Ruket Cakici
Abstract: Morphologically rich languages such as Turkish may benefit from morphological analysis in natural language tasks. In this study, we examine the effects of morphological analysis on text categorization task in Turkish. We use stems and word categories that are extracted with morphological analysis as main features and compare them with fixed length stemmers in a bag of words approach with several learning algorithms. We aim to show the effects of using varying degrees of morphological information.
4 0.63884109 227 acl-2013-Learning to lemmatise Polish noun phrases
Author: Adam Radziszewski
Abstract: We present a novel approach to noun phrase lemmatisation where the main phase is cast as a tagging problem. The idea draws on the observation that the lemmatisation of almost all Polish noun phrases may be decomposed into transformation of singular words (tokens) that make up each phrase. We perform evaluation, which shows results similar to those obtained earlier by a rule-based system, while our approach allows to separate chunking from lemmatisation.
Author: Tirthankar Dasgupta
Abstract: In this work we present psycholinguistically motivated computational models for the organization and processing of Bangla morphologically complex words in the mental lexicon. Our goal is to identify whether morphologically complex words are stored as a whole or are they organized along the morphological line. For this, we have conducted a series of psycholinguistic experiments to build up hypothesis on the possible organizational structure of the mental lexicon. Next, we develop computational models based on the collected dataset. We observed that derivationally suffixed Bangla words are in general decomposed during processing and compositionality between the stem . and the suffix plays an important role in the decomposition process. We observed the same phenomena for Bangla verb sequences where experiments showed noncompositional verb sequences are in general stored as a whole in the ML and low traces of compositional verbs are found in the mental lexicon. 1 IInnttrroodduuccttiioonn Mental lexicon is the representation of the words in the human mind and their associations that help fast retrieval and comprehension (Aitchison, 1987). Words are known to be associated with each other in terms of, orthography, phonology, morphology and semantics. However, the precise nature of these relations is unknown. An important issue that has been a subject of study for a long time is to identify the fundamental units in terms of which the mental lexicon is i itkgp .ernet . in organized. That is, whether lexical representations in the mental lexicon are word based or are they organized along morphological lines. For example, whether a word such as “unimaginable” is stored in the mental lexicon as a whole word or do we break it up “un-” , “imagine” and “able”, understand the meaning of each of these constituent and then recombine the units to comprehend the whole word. Such questions are typically answered by designing appropriate priming experiments (Marslen-Wilson et al., 1994) or other lexical decision tasks. The reaction time of the subjects for recognizing various lexical items under appropriate conditions reveals important facts about their organization in the brain. (See Sec. 2 for models of morphological organization and access and related experiments). A clear understanding of the structure and the processing mechanism of the mental lexicon will further our knowledge of how the human brain processes language. Further, these linguistically important and interesting questions are also highly significant for computational linguistics (CL) and natural language processing (NLP) applications. Their computational significance arises from the issue of their storage in lexical resources like WordNet (Fellbaum, 1998) and raises the questions like, how to store morphologically complex words, in a lexical resource like WordNet keeping in mind the storage and access efficiency. There is a rich literature on organization and lexical access of morphologically complex words where experiments have been conducted mainly for derivational suffixed words of English, Hebrew, Italian, French, Dutch, and few other languages (Marslen-Wilson et al., 2008; Frost et al., 1997; Grainger, et al., 1991 ; Drews and Zwitserlood, 1995). However, we do not know of any such investigations for Indian languages, which 123 Sofia, BuPrlgoacreiead, iAngusgu osft 4h-e9 A 2C01L3 S.tu ?c d2en0t1 3Re Ases aorc hiat Wio nrk fsohro Cp,om papguesta 1ti2o3n–a1l2 L9in,guistics are morphologically richer than many of their Indo-European cousins. Moreover, Indian languages show some distinct phenomena like, compound and composite verbs for which no such investigations have been conducted yet. On the other hand, experiments indicate that mental representation and processing of morphologically complex words are not quite language independent (Taft, 2004). Therefore, the findings from experiments in one language cannot be generalized to all languages making it important to conduct similar experimentations in other languages. This work aims to design cognitively motivated computational models that can explain the organization and processing of Bangla morphologically complex words in the mental lexicon. Presently we will concentrate on the following two aspects: OOrrggaanniizzaattiioonn aanndd pprroocceessssiinngg ooff BBaannggllaa PPo o l yy-mmoorrpphheemmiicc wwoorrddss:: our objective here is to determine whether the mental lexicon decomposes morphologically complex words into its constituent morphemes or does it represent the unanalyzed surface form of a word. OOrrggaanniizzaattiioonn aanndd pprroocceessssiinngg ooff BBaannggllaa ccoomm-ppoouunndd vveerrbbss ((CCVV)) :: compound verbs are the subject of much debate in linguistic theory. No consensus has been reached yet with respect to the issue that whether to consider them as unitary lexical units or are they syntactically assembled combinations of two independent lexical units. As linguistic arguments have so far not led to a consensus, we here use cognitive experiments to probe the brain signatures of verb-verb combinations and propose cognitive as well as computational models regarding the possible organization and processing of Bangla CVs in the mental lexicon (ML). With respect to this, we apply the different priming and other lexical decision experiments, described in literature (Marslen-Wilson et al., 1994; Bentin, S. and Feldman, 1990) specifically for derivationally suffixed polymorphemic words and compound verbs of Bangla. Our cross-modal and masked priming experiment on Bangla derivationally suffixed words shows that morphological relatedness between lexical items triggers a significant priming effect, even when the forms are phonologically/orthographically unrelated. These observations are similar to those reported for English and indicate that derivationally suffixed words in Bangla are in general accessed through decomposition of the word into its constituent morphemes. Further, based on the experimental data we have developed a series of computational models that can be used to predict the decomposition of Bangla polymorphemic words. Our evaluation result shows that decom- position of a polymorphemic word depends on several factors like, frequency, productivity of the suffix and the compositionality between the stem and the suffix. The organization of the paper is as follows: Sec. 2 presents related works; Sec. 3 describes experiment design and procedure; Sec. 4 presents the processing of CVs; and finally, Sec. 5 concludes the paper by presenting the future direction of the work. 2 RReellaatteedd WWoorrkkss 2. . 11 RReepprreesseennttaattiioonn ooff ppoollyymmoorrpphheemmiicc wwoorrddss Over the last few decades many studies have attempted to understand the representation and processing of morphologically complex words in the brain for various languages. Most of the studies are designed to support one of the two mutually exclusive paradigms: the full-listing and the morphemic model. The full-listing model claims that polymorphic words are represented as a whole in the human mental lexicon (Bradley, 1980; Butterworth, 1983). On the other hand, morphemic model argues that morphologically complex words are decomposed and represented in terms of the smaller morphemic units. The affixes are stripped away from the root form, which in turn are used to access the mental lexicon (Taft and Forster, 1975; Taft, 1981 ; MacKay, 1978). Intermediate to these two paradigms is the partial decomposition model that argues that different types of morphological forms are processed separately. For instance, the derived morphological forms are believed to be represented as a whole, whereas the representation of the inflected forms follows the morphemic model (Caramazza et al., 1988). Traditionally, priming experiments have been used to study the effects of morphology in language processing. Priming is a process that results in increase in speed or accuracy of response to a stimulus, called the target, based on the occurrence of a prior exposure of another stimulus, called the prime (Tulving et al., 1982). Here, subjects are exposed to a prime word for a short duration, and are subsequently shown a target word. The prime and target words may be morphologically, phonologically or semantically re124 lated. An analysis of the effect of the reaction time of subjects reveals the actual organization and representation of the lexicon at the relevant level. See Pulvermüller (2002) for a detailed account of such phenomena. It has been argued that frequency of a word influences the speed of lexical processing and thus, can serve as a diagnostic tool to observe the nature and organization of lexical representations. (Taft, 1975) with his experiment on English inflected words, argued that lexical decision responses of polymorphemic words depends upon the base word frequency. Similar observation for surface word frequency was also observed by (Bertram et al., 2000;Bradley, 1980;Burani et al., 1987;Burani et al., 1984;Schreuder et al., 1997; Taft 1975;Taft, 2004) where it has been claimed that words having low surface frequency tends to decompose. Later, Baayen(2000) proposed the dual processing race model that proposes that a specific morphologically complex form is accessed via its parts if the frequency of that word is above a certain threshold of frequency, then the direct route will win, and the word will be accessed as a whole. If it is below that same threshold of frequency, the parsing route will win, and the word will be accessed via its parts. 2. . 22 RReepprreesseennttaattiioonn ooff CCoommppoouunndd A compound verb (CV) consists of two verbs (V1 and V2) acting as and expresses a single expression For example, in the sentence VVeerrbbss a sequence of a single verb of meaning. রুটিগুল ো খেল খেল ো (/ruTigulo kheYe phela/) ―bread-plural-the eat and drop-pres. Imp‖ ―Eat the breads‖ the verb sequence “খেল খেল ো (eat drop)” is an example of CV. Compound verbs are a special phenomena that are abundantly found in IndoEuropean languages like Indian languages. A plethora of works has been done to provide linguistic explanations on the formation of such word, yet none so far has led to any consensus. Hook (1981) considers the second verb V2 as an aspectual complex comparable to the auxiliaries. Butt (1993) argues CV formations in Hindi and Urdu are either morphological or syntactical and their formation take place at the argument struc- ture. Bashir (1993) tried to construct a semantic analysis based on “prepared” and “unprepared mind”. Similar findings have been proposed by Pandharipande (1993) that points out V1 and V2 are paired on the basis of their semantic compatibility, which is subject to syntactic constraints. Paul (2004) tried to represent Bangla CVs in terms of HPSG formalism. She proposes that the selection of a V2 by a V1 is determined at the semantic level because the two verbs will unify if and only if they are semantically compatible. Since none of the linguistic formalism could satisfactorily explain the unique phenomena of CV formation, we here for the first time drew our attention towards psycholinguistic and neurolinguistic studies to model the processing of verb-verb combinations in the ML and compare these responses with that of the existing models. 3 TThhee PPrrooppoosseedd AApppprrooaacchheess 3. . 11 TThhee ppssyycchhoolliinngguuiissttiicc eexxppeerriimmeennttss We apply two different priming experiments namely, the cross modal priming and masked priming experiment discussed in (Forster and Davis, 1984; Rastle et al., 2000;Marslen-Wilson et al., 1994; Marslen-Wilson et al., 2008) for Bangla morphologically complex words. Here, the prime is morphologically derived form of the target presented auditorily (for cross modal priming) or visually (for masked priming). The subjects were asked to make a lexical decision whether the given target is a valid word in that language. The same target word is again probed but with a different audio or visual probe called the control word. The control shows no relationship with the target. For example, baYaska (aged) and baYasa (age) is a prime-target pair, for which the corresponding control-target pair could be naYana (eye) and baYasa (age). Similar to (Marslen-Wilson et al., 2008) the masked priming has been conducted for three different SOA (Stimulus Onset Asynchrony), 48ms, 72ms and 120ms. The SOA is measured as the amount of time between the start the first stimulus till the start of the next stimulus. TCM abl-’+ Sse-+ O1 +:-DatjdgnmAshielbatArDu)f(osiAMrawnteihmsgcdaoe)lEx-npgmAchebamr)iD-gnatmprhdiYlbeaA(n ftrTsli,ae(+gnrmdisc)phroielctn)osrelated, and - implies unrelated. There were 500 prime-target and controltarget pairs classified into five classes. Depending on the class, the prime is related to the target 125 either in terms of morphology, semantics, orthography and/or Phonology (See Table 1). The experiments were conducted on 24 highly educated native Bangla speakers. Nineteen of them have a graduate degree and five hold a post graduate degree. The age of the subjects varies between 22 to 35 years. RReessuullttss:: The RTs with extreme values and incorrect decisions were excluded from the data. The data has been analyzed using two ways ANOVA with three factors: priming (prime and control), conditions (five classes) and prime durations (three different SOA). We observe strong priming effects (p<0.05) when the target word is morphologically derived and has a recognizable suffix, semantically and orthographically related with respect to the prime; no priming effects are observed when the prime and target words are orthographically related but share no morphological or semantic relationship; although not statistically significant (p>0.07), but weak priming is observed for prime target pairs that are only semantically related. We see no significant difference between the prime and control RTs for other classes. We also looked at the RTs for each of the 500 target words. We observe that maximum priming occurs for words in [M+S+O+](69%), some priming is evident in [M+S+O-](51%) and [M'+S-O+](48%), but for most of the words in [M-S+O-](86%) and [M-S-O+](92%) no priming effect was observed. 3. . 22 FFrreeqquueennccyy DDiissttrriibbuuttiioonn MMooddeellss ooff MMoo rrpphhoo-llooggiiccaall PPrroocceessssiinngg From the above results we saw that not all polymorphemic words tend to decompose during processing, thus we need to further investigate the processing phenomena of Bangla derived words. One notable means is to identify whether the stem or suffix frequency is involved in the processing stage of that word. For this, we apply different frequency based models to the Bangla polymorphemic words and try to evaluate their performance by comparing their predicted results with the result obtained through the priming experiment. MMooddeell --11:: BBaassee aanndd SSuurrffaaccee wwoorrdd ffrreeqquueennccyy ee ff-ffeecctt -- It states that the probability of decomposition of a Bangla polymorphemic word depends upon the frequency of its base word. Thus, if the stem frequency of a polymorphemic word crosses a given threshold value, then the word will decomposed into its constituent morpheme. Similar claim has been made for surface word frequency model where decomposition depends upon the frequency of the surface word itself. We have evaluated both the models with the 500 words used in the priming experiments discussed above. We have achieved an accuracy of 62% and 49% respectively for base and surface word frequency models. MMooddeell --22:: CCoommbbiinniinngg tthhee bbaassee aanndd ssuurrffaaccee wwoorrdd ffrreeq quueennccyy -- In a pursuit towards an extended model, we combine model 1 and 2 together. We took the log frequencies of both the base and the derived words and plotted the best-fit regression curve over the given dataset. The evaluation of this model over the same set of 500 target words returns an accuracy of 68% which is better than the base and surface word frequency models. However, the proposed model still fails to predict processing of around 32% of words. This led us to further enhance the model. For this, we analyze the role of suffixes in morphological processing. MMooddeell -- 33:: DDeeggrreeee ooff AAffffiixxaattiioonn aanndd SSuuffffiixx PPrroodd-uuccttiivviittyy:: we examine whether the regression analysis between base and derived frequency of Bangla words varies between suffixes and how these variations affect morphological decomposition. With respect to this, we try to compute the degree of affixation between the suffix and the base word. For this, we perform regression analysis on sixteen different Bangla suffixes with varying degree of type and token frequencies. For each suffix, we choose 100 different derived words. We observe that those suffixes having high value of intercept are forming derived words whose base frequencies are substantially high as compared to their derived forms. Moreover we also observe that high intercept value for a given suffix indicates higher inclination towards decomposition. Next, we try to analyze the role of suffix type/token ratio and compare them with the base/derived frequency ratio model. This has been done by regression analysis between the suffix type-token ratios with the base-surface frequency ratio. We further tried to observe the role of suffix productivity in morphological processing. For this, we computed the three components of productivity P, P* and V as discussed in (Hay and Plag, 2004). P is the “conditioned degree of productivity” and is the probability that we are encountering a word with an affix and it is representing a new type. P* is the “hapaxedconditioned degree of productivity”. It expresses the probability that when an entirely new word is 126 encountered it will contain the suffix. V is the “type frequency”. Finally, we computed the productivity of a suffix through its P, P* and V values. We found that decomposition of Bangla polymorphemic word is directly proportional to the productivity of the suffix. Therefore, words that are composed of productive suffixes (P value ranges between 0.6 and 0.9) like “-oYAlA”, “-giri”, “-tba” and “-panA” are highly decomposable than low productive suffixes like “-Ani”, “-lA”, “-k”, and “-tama”. The evaluation of the proposed model returns an accuracy of 76% which comes to be 8% better than the preceding models. CCoommbbiinniinngg MMooddeell --22 aanndd MMooddeell -- 33:: One important observation that can be made from the above results is that, model-3 performs best in determining the true negative values. It also possesses a high recall value of (85%) but having a low precision of (50%). In other words, the model can predict those words for which decomposition will not take place. On the other hand, results of Model-2 posses a high precision of 70%. Thus, we argue that combining the above two models can better predict the decomposition of Bangla polymorphemic words. Hence, we combine the two models together and finally achieved an overall accuracy of 80% with a precision of 87% and a recall of 78%. This surpasses the performance of the other models discussed earlier. However, around 22% of the test words were wrongly classified which the model fails to justify. Thus, a more rigorous set of experiments and data analysis are required to predict access mechanisms of such Bangla polymorphemic words. 3. . 33 SStteemm- -SSuuffffiixx CCoommppoossiittiioonnaalliittyy Compositionality refers to the fact that meaning of a complex expression is inferred from the meaning of its constituents. Therefore, the cost of retrieving a word from the secondary memory is directly proportional to the cost of retrieving the individual parts (i.e the stem and the suffix). Thus, following the work of (Milin et al., 2009) we define the compositionality of a morphologically complex word (We) as: C(We)=α 1H(We)+α α2H(e)+α α3H(W|e)+ α4H(e|W) Where, H(x) is entropy of an expression x, H(W|e) is the conditional entropy between the stem W and suffix e and is the proportionality factor whose value is computed through regression analysis. Next, we tried to compute the compositionality of the stem and suffixes in terms of relative entropy D(W||e) and Point wise mutual information (PMI). The relative entropy is the measure of the distance between the probability distribution of the stem W and the suffix e. The PMI measures the amount of information that one random variable (the stem) contains about the other (the suffix). We have compared the above three techniques with the actual reaction time data collected through the priming and lexical decision experiment. We observed that all the three information theoretic models perform much better than the frequency based models discussed in the earlier section, for predicting the decomposability of Bangla polymorphemic words. However, we think it is still premature to claim anything concrete at this stage of our work. We believe much more rigorous experiments are needed to be per- formed in order to validate our proposed models. Further, the present paper does not consider factors related to age of acquisition, and word familiarity effects that plays important role in the processing of morphologically complex words. Moreover, it is also very interesting to see how stacking of multiple suffixes in a word are processed by the human brain. 44 OOrrggaanniizzaattiioonn aanndd PPrroocceessssiinngg ooff CCoomm-ppoouunndd VVeerrbbss iinn tthhee MMeennttaall LLeexxiiccoonn Compound verbs, as discussed above, are special type of verb sequences consisting of two or more verbs acting as a single verb and express a single expression of meaning. The verb V1 is known as pole and V2 is called as vector. For example, “ওঠে পড়া ” (getting up) is a compound verb where individual words do not entirely reflects the meaning of the whole expression. However, not all V1+V2 combinations are CVs. For example, expressions like, “নিঠে য়াও ”(take and then go) and “ নিঠে আঠ ়া” (return back) are the examples of verb sequences where meaning of the whole expression can be derived from the mean- ing of the individual component and thus, these verb sequences are not considered as CV. The key question linguists are trying to identify for a long time and debating a lot is whether to consider CVs as a single lexical units or consider them as two separate units. Since linguistic rules fails to explain the process, we for the first time tried to perform cognitive experiments to understand the organization and processing of such verb sequences in the human mind. A clear understanding about these phenomena may help us to classify or extract actual CVs from other verb 127 sequences. In order to do so, presently we have applied three different techniques to collect user data. In the first technique, we annotated 4500 V1+V2 sequences, along with their example sentences, using a group of three linguists (the expert subjects). We asked the experts to classify the verb sequences into three classes namely, CV, not a CV and not sure. Each linguist has received 2000 verb pairs along with their respective example sentences. Out of this, 1500 verb sequences are unique to each of them and rest 500 are overlapping. We measure the inter annotator agreement using the Fleiss Kappa (Fleiss et al., 1981) measure (κ) where the agreement lies around 0.79. Next, out of the 500 common verb sequences that were annotated by all the three linguists, we randomly choose 300 V1+V2 pairs and presented them to 36 native Bangla speakers. We ask each subjects to give a compositionality score of each verb sequences under 1-10 point scale, 10 being highly compositional and 1 for noncompositional. We found an agreement of κ=0.69 among the subjects. We also observe a continuum of compositionality score among the verb sequences. This reflects that it is difficult to classify Bangla verb sequences discretely into the classes of CV and not a CV. We then, compare the compositionality score with that of the expert user’s annotation. We found a significant correlation between the expert annotation and the compositionality score. We observe verb sequences that are annotated as CVs (like, খেঠে খিল )কঠে খি ,ওঠে পড ,have got low compositionality score (average score ranges between 1-4) on the other hand high compositional values are in general tagged as not a cv (নিঠে য়া (come and get), নিঠে আে (return back), তুঠল খেঠেনি (kept), গনিঠে পিল (roll on floor)). This reflects that verb sequences which are not CV shows high degree of compositionality. In other words non CV verbs can directly interpret from their constituent verbs. This leads us to the possibility that compositional verb sequences requires individual verbs to be recognized separately and thus the time to recognize such expressions must be greater than the non-compositional verbs which maps to a single expression of meaning. In order to validate such claim we perform a lexical decision experiment using 32 native Bangla speakers with 92 different verb sequences. We followed the same experimental procedure as discussed in (Taft, 2004) for English polymorphemic words. However, rather than derived words, the subjects were shown a verb sequence and asked whether they recognize them as a valid combination. The reaction time (RT) of each subject is recorded. Our preliminarily observation from the RT analysis shows that as per our claim, RT of verb sequences having high compositionality value is significantly higher than the RTs for low or noncompositional verbs. This proves our hypothesis that Bangla compound verbs that show less compositionality are stored as a hole in the mental lexicon and thus follows the full-listing model whereas compositional verb phrases are individually parsed. However, we do believe that our experiment is composed of a very small set of data and it is premature to conclude anything concrete based only on the current experimental results. 5 FFuuttuurree DDiirreeccttiioonnss In the next phase of our work we will focus on the following aspects of Bangla morphologically complex words: TThhee WWoorrdd FFaammiilliiaarriittyy EEffffeecctt:: Here, our aim is to study the role of familiarity of a word during its processing. We define the familiarity of a word in terms of corpus frequency, Age of acquisition, the level of language exposure of a person, and RT of the word etc. RRoollee ooff ssuuffffiixx ttyyppeess iinn mmoorrpphhoollooggiiccaall ddeeccoo mm ppoo-ssiittiioonn:: For native Bangla speakers which morphological suffixes are internalized and which are just learnt in school, but never internalized. We can compare the representation of Native, Sanskrit derived and foreign suffixes in Bangla words. CCoommppuuttaattiioonnaall mmooddeellss ooff oorrggaanniizzaattiioonn aanndd pprroocceessssiinngg ooff BBaannggllaa ccoommppoouunndd vveerrbbss :: presently we have performed some small set of experiments to study processing of compound verbs in the mental lexicon. In the next phase of our work we will extend the existing experiments and also apply some more techniques like, crowd sourcing and language games to collect more relevant RT and compositionality data. Finally, based on the collected data we will develop computational models that can explain the possible organizational structure and processing mechanism of morphologically complex Bangla words in the mental lexicon. Reference Aitchison, J. (1987). ―Words in the mind: An introduction to the mental lexicon‖. Wiley-Blackwell, 128 Baayen R. H. (2000). ―On frequency, transparency and productivity‖. G. Booij and J. van Marle (eds), Yearbook of Morphology, pages 181-208, Baayen R.H. (2003). ―Probabilistic approaches to morphology‖. Probabilistic linguistics, pages 229287. Baayen R.H., T. Dijkstra, and R. Schreuder. (1997). ―Singulars and plurals in dutch: Evidence for a parallel dual-route model‖. Journal of Memory and Language, 37(1):94-1 17. Bashir, E. (1993), ―Causal Chains and Compound Verbs.‖ In M. K. Verma ed. (1993). Bentin, S. & Feldman, L.B. (1990). The contribution of morphological and semantic relatedness to repetition priming at short and long lags: Evidence from Hebrew. Quarterly Journal of Experimental Psychology, 42, pp. 693–71 1. Bradley, D. (1980). Lexical representation of derivational relation, Juncture, Saratoga, CA: Anma Libri, pp. 37-55. Butt, M. (1993), ―Conscious choice and some light verbs in Urdu.‖ In M. K. Verma ed. (1993). Butterworth, B. (1983). Lexical Representation, Language Production, Vol. 2, pp. 257-294, San Diego, CA: Academic Press. Caramazza, A., Laudanna, A. and Romani, C. (1988). Lexical access and inflectional morphology. Cognition, 28, pp. 297-332. Drews, E., and Zwitserlood, P. (1995).Morphological and orthographic similarity in visual word recognition. Journal of Experimental Psychology:HumanPerception andPerformance, 21, 1098– 1116. Fellbaum, C. (ed.). (1998). WordNet: An Electronic Lexical Database, MIT Press. Forster, K.I., and Davis, C. (1984). Repetition priming and frequency attenuation in lexical access. Journal of Experimental Psychology: Learning, Memory, and Cognition, 10, 680–698. Frost, R., Forster, K.I., & Deutsch, A. (1997). What can we learn from the morphology of Hebrew? A masked-priming investigation of morphological representation. Journal of Experimental Psychology: Learning, Memory, and Cognition, 23, 829–856. Grainger, J., Cole, P., & Segui, J. (1991). Masked morphological priming in visual word recognition. Journal of Memory and Language, 30, 370–384. Hook, P. E. (1981). ―Hindi Structures: Intermediate Level.‖ Michigan Papers on South and Southeast Asia, The University of Michigan Center for South and Southeast Studies, Ann Arbor, Michigan. Joseph L Fleiss, Bruce Levin, and Myunghee Cho Paik. 1981. The measurement of interrater agreement. Statistical methods for rates and proportions,2:212–236. MacKay,D.G.(1978), Derivational rules and the internal lexicon. Journal of Verbal Learning and Verbal Behavior, 17, pp.61-71. Marslen-Wilson, W.D., & Tyler, L.K. (1997). Dissociating types of mental computation. Nature, 387, pp. 592–594. Marslen-Wilson, W.D., & Tyler, L.K. (1998). Rules, representations, and the English past tense. Trends in Cognitive Sciences, 2, pp. 428–435. Marslen-Wilson, W.D., Tyler, L.K., Waksler, R., & Older, L. (1994). Morphology and meaning in the English mental lexicon. Psychological Review, 101, pp. 3–33. Marslen-Wilson,W.D. and Zhou,X.( 1999). Abstractness, allomorphy, and lexical architecture. Language and Cognitive Processes, 14, 321–352. Milin, P., Kuperman, V., Kosti´, A. and Harald R., H. (2009). Paradigms bit by bit: an information- theoretic approach to the processing of paradigmatic structure in inflection and derivation, Analogy in grammar: Form and acquisition, pp: 214— 252. Pandharipande, R. (1993). ―Serial verb construction in Marathi.‖ In M. K. Verma ed. (1993). Paul, S. (2004). An HPSG Account of Bangla Compound Verbs with LKB Implementation, Ph.D. Dissertation. CALT, University of Hyderabad. Pulvermüller, F. (2002). The Neuroscience guage. Cambridge University Press. of Lan- Stolz, J.A., and Feldman, L.B. (1995). The role of orthographic and semantic transparency of the base morpheme in morphological processing. In L.B. Feldman (Ed.) Morphological aspects of language processing. Hillsdale, NJ: Lawrence Erlbaum Associates Inc. Taft, M., and Forster, K.I.(1975). Lexical storage and retrieval of prefix words. Journal of Verbal Learning and Verbal Behavior, Vol.14, pp. 638-647. Taft, M.(1988). A morphological decomposition model of lexical access. Linguistics, 26, pp. 657667. Taft, M. (2004). Morphological decomposition and the reverse base frequency effect. Quarterly Journal of Experimental Psychology, 57A, pp. 745-765 Tulving, E., Schacter D. L., and Heather A.(1982). Priming Effects in Word Fragment Completion are independent of Recognition Memory. Journal of Experimental Psychology: Learning, Memory and Cognition, vol.8 (4). 129
7 0.55622184 102 acl-2013-DErivBase: Inducing and Evaluating a Derivational Morphology Resource for German
8 0.53148687 330 acl-2013-Stem Translation with Affix-Based Rule Selection for Agglutinative Languages
9 0.51802689 337 acl-2013-Tag2Blog: Narrative Generation from Satellite Tag Data
10 0.50960696 327 acl-2013-Sorani Kurdish versus Kurmanji Kurdish: An Empirical Comparison
11 0.50273442 21 acl-2013-A Statistical NLG Framework for Aggregated Planning and Realization
12 0.49176952 360 acl-2013-Translating Italian connectives into Italian Sign Language
13 0.46688223 28 acl-2013-A Unified Morpho-Syntactic Scheme of Stanford Dependencies
14 0.45618576 110 acl-2013-Deepfix: Statistical Post-editing of Statistical Machine Translation Using Deep Syntactic Analysis
15 0.45377535 90 acl-2013-Conditional Random Fields for Responsive Surface Realisation using Global Features
16 0.44770434 321 acl-2013-Sign Language Lexical Recognition With Propositional Dynamic Logic
17 0.43862873 87 acl-2013-Compositional-ly Derived Representations of Morphologically Complex Words in Distributional Semantics
18 0.42690119 1 acl-2013-"Let Everything Turn Well in Your Wife": Generation of Adult Humor Using Lexical Constraints
19 0.40565354 203 acl-2013-Is word-to-phone mapping better than phone-phone mapping for handling English words?
20 0.40394258 295 acl-2013-Real-World Semi-Supervised Learning of POS-Taggers for Low-Resource Languages
topicId topicWeight
[(0, 0.076), (6, 0.027), (11, 0.071), (14, 0.038), (24, 0.036), (26, 0.051), (35, 0.082), (39, 0.193), (42, 0.097), (48, 0.04), (70, 0.021), (88, 0.049), (90, 0.023), (95, 0.129)]
simIndex simValue paperId paperTitle
same-paper 1 0.86647022 303 acl-2013-Robust multilingual statistical morphological generation models
Author: Ondrej Dusek ; Filip Jurcicek
Abstract: We present a novel method of statistical morphological generation, i.e. the prediction of inflected word forms given lemma, part-of-speech and morphological features, aimed at robustness to unseen inputs. Our system uses a trainable classifier to predict “edit scripts” that are then used to transform lemmas into inflected word forms. Suffixes of lemmas are included as features to achieve robustness. We evaluate our system on 6 languages with a varying degree of morphological richness. The results show that the system is able to learn most morphological phenomena and generalize to unseen inputs, producing significantly better results than a dictionarybased baseline.
2 0.82640463 279 acl-2013-PhonMatrix: Visualizing co-occurrence constraints of sounds
Author: Thomas Mayer ; Christian Rohrdantz
Abstract: This paper describes the online tool PhonMatrix, which analyzes a word list with respect to the co-occurrence of sounds in a specified context within a word. The cooccurrence counts from the user-specified context are statistically analyzed according to a number of association measures that can be selected by the user. The statistical values then serve as the input for a matrix visualization where rows and columns represent the relevant sounds under investigation and the matrix cells indicate whether the respective ordered pair of sounds occurs more or less frequently than expected. The usefulness of the tool is demonstrated with three case studies that deal with vowel harmony and similar place avoidance patterns.
3 0.74231648 137 acl-2013-Enlisting the Ghost: Modeling Empty Categories for Machine Translation
Author: Bing Xiang ; Xiaoqiang Luo ; Bowen Zhou
Abstract: Empty categories (EC) are artificial elements in Penn Treebanks motivated by the government-binding (GB) theory to explain certain language phenomena such as pro-drop. ECs are ubiquitous in languages like Chinese, but they are tacitly ignored in most machine translation (MT) work because of their elusive nature. In this paper we present a comprehensive treatment of ECs by first recovering them with a structured MaxEnt model with a rich set of syntactic and lexical features, and then incorporating the predicted ECs into a Chinese-to-English machine translation task through multiple approaches, including the extraction of EC-specific sparse features. We show that the recovered empty categories not only improve the word alignment quality, but also lead to significant improvements in a large-scale state-of-the-art syntactic MT system.
4 0.74206799 223 acl-2013-Learning a Phrase-based Translation Model from Monolingual Data with Application to Domain Adaptation
Author: Jiajun Zhang ; Chengqing Zong
Abstract: Currently, almost all of the statistical machine translation (SMT) models are trained with the parallel corpora in some specific domains. However, when it comes to a language pair or a different domain without any bilingual resources, the traditional SMT loses its power. Recently, some research works study the unsupervised SMT for inducing a simple word-based translation model from the monolingual corpora. It successfully bypasses the constraint of bitext for SMT and obtains a relatively promising result. In this paper, we take a step forward and propose a simple but effective method to induce a phrase-based model from the monolingual corpora given an automatically-induced translation lexicon or a manually-edited translation dictionary. We apply our method for the domain adaptation task and the extensive experiments show that our proposed method can substantially improve the translation quality. 1
5 0.74072641 174 acl-2013-Graph Propagation for Paraphrasing Out-of-Vocabulary Words in Statistical Machine Translation
Author: Majid Razmara ; Maryam Siahbani ; Reza Haffari ; Anoop Sarkar
Abstract: Out-of-vocabulary (oov) words or phrases still remain a challenge in statistical machine translation especially when a limited amount of parallel text is available for training or when there is a domain shift from training data to test data. In this paper, we propose a novel approach to finding translations for oov words. We induce a lexicon by constructing a graph on source language monolingual text and employ a graph propagation technique in order to find translations for all the source language phrases. Our method differs from previous approaches by adopting a graph propagation approach that takes into account not only one-step (from oov directly to a source language phrase that has a translation) but multi-step paraphrases from oov source language words to other source language phrases and eventually to target language translations. Experimental results show that our graph propagation method significantly improves performance over two strong baselines under intrinsic and extrinsic evaluation metrics.
6 0.73486584 127 acl-2013-Docent: A Document-Level Decoder for Phrase-Based Statistical Machine Translation
7 0.73470283 97 acl-2013-Cross-lingual Projections between Languages from Different Families
8 0.73398709 98 acl-2013-Cross-lingual Transfer of Semantic Role Labeling Models
9 0.73285317 383 acl-2013-Vector Space Model for Adaptation in Statistical Machine Translation
10 0.73142636 181 acl-2013-Hierarchical Phrase Table Combination for Machine Translation
11 0.73141968 207 acl-2013-Joint Inference for Fine-grained Opinion Extraction
12 0.73054981 267 acl-2013-PARMA: A Predicate Argument Aligner
13 0.72945678 314 acl-2013-Semantic Roles for String to Tree Machine Translation
14 0.72797608 18 acl-2013-A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization
15 0.72796428 70 acl-2013-Bilingually-Guided Monolingual Dependency Grammar Induction
16 0.72635412 226 acl-2013-Learning to Prune: Context-Sensitive Pruning for Syntactic MT
17 0.72619194 9 acl-2013-A Lightweight and High Performance Monolingual Word Aligner
18 0.72590262 13 acl-2013-A New Syntactic Metric for Evaluation of Machine Translation
19 0.72569615 164 acl-2013-FudanNLP: A Toolkit for Chinese Natural Language Processing
20 0.72407162 264 acl-2013-Online Relative Margin Maximization for Statistical Machine Translation