DOCSLIB.ORG

Resolving Direct and Indirect Anaphora for Japanese Definite

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Resolving Direct and Indirect Anaphora for Japanese Definite Resolving Direct and Indirect Anaphora for Japanese Definite Noun Phrases Naoya Inoue Ryu Iida Kentaro Inui Yuji Matsumoto NAIST, Japan Tokyo Institute of Technology, Japan NAIST, Japan NAIST, Japan [email protected] [email protected] [email protected] [email protected] Abstract An anaphoric relation can be either direct in parallel and classify the anaphora type. How- or indirect. In some cases, the antecedent ever, these issues have received little attention in being referred to lies outside the discourse the literature. to which its anaphor belongs. Therefore, In this paper, we regard the task of nominal an anaphora resolution model needs to con- anaphora resolution as a combination of two dis- sider the following two decisions in paral- tinct but arguably interdependent subtasks: lel: (i) antecedent selection–selecting the • Antecedent selection: the task of identifying the antecedent itself, and (ii) anaphora type antecedent of a given input definite NP, and classification–classifying exophora, direct • Anaphora type classification: the task of judg- anaphora, or indirect anaphora. However, ing whether the anaphor is direct anaphoric, in- the anaphora type classification has re- direct anaphoric or exophoric. ceived little attention in the literature. In Given this task decomposition, the following unex- this paper, we address this issue taking plored issues immediately arise: Japanese as our target language. Our find- • Whether the model for antecedent selection ings were: first, an antecedent selection should be designed and trained separately for model should be trained separately for each direct anaphora and indirect anaphora or if it anaphora type. Second, the best candidate can be trained as a single common model, antecedent selected by an antecedent selec- • How the two subtasks can be best combined tion model provides contextual information (e.g. which subtask should be carried out first), useful for anaphora type classification. In and consequence, antecedent selection should • Which context information is useful for be carried out before anaphora type clas- anaphora type classification. sification. In this paper, we explore these issues taking 1 Introduction Japanese as our target language. Anaphora resolution has been studied inten- Definite NPs in Japanese behave similarly to sively in recent years because of its significance those in English; that is, a definite NP may bear in many NLP applications such as information a direct anaphoric relation but may also bear an in- extraction and machine translation. In nominal direct anaphoric relation to its antecedent as shown anaphora resolution, an anaphor (typically a defi- in examples (4) and (5). nite noun phrase) and its antecedent hold either a (4) 新型車 が発売された。このミニバン は燃費が非常に direct anaphoric relation (e.g., coreference) or an よい。 A new car was released. The minivan has good gas indirect relation (e.g., bridging reference (Clark, mileage. 1977)). In example (1), the anaphor the CD refers (5) 家具屋で 机 を見た。そのデザイン は素晴らしかった。 to Her new album directly. I saw a desk in a furniture shop. The design was mar- (1) Her new album was released yesterday. velous. I want to get the CD as soon as possible. In contrast, the CD refers to her new song indi- “このミニバン (the minivan)” refers to “新型車 rectly in example (2). (a new car)” directly in (4), while “そのデザイン 机 (2) The artist announced her new song. (the design)” refers to “ (a desk)” indirectly in I want to get the CD as soon as possible. (5). In Japanese, however, the problem can be even In cases such as example (3), an antecedent re- more complex because a definite NP is not always ferred to is not in the same discourse. marked by a definiteness modifier. In an example (3) I want to get the CD as soon as possible. (6), a bare NP 大統領 (literally, President) refers to 韓国大統領 We call the reference in example (1) direct (Korean President). anaphora; in example (2) indirect anaphora; and (6) 今月 4 日、韓国大統領 が来日した。大統領 は翌日の 記者会見で新プランの詳細を語った。 in example (3) exophora. In anaphora resolution, Korean President visited Japan on the 4th this month. besides identifying the antecedent itself, it is there- (The) President talked about the details of his new plan fore necessary to consider these three possibilities at the news conference next day. Anaphora Type Classifier Antecedent Selection Model Anaphor Anaphor Anaphor Anaphor Anaphor Candidates Information Anaphor Direct Indirect Direct Indirect Anaphora Anaphora Anaphora Anaphora Single Direct Indirect Direct Indirect Anaphora Anaphora Anaphora Anaphora Direct Indirect Direct Indirect Direct Indirect Direct Indirect Anaphora Anaphora Anaphora Anaphora Anaphora Anaphora Direct Indirect Direct Indirect Anaphora Anaphora Anaphora Anaphora Anaphora Anaphora Indirect Direct Exophora Exophora Anaphora Anaphora Exophora Exophora Exophora Exophora a-Classify-then-Select c-Classify-then-Select s-Select-then-Classify d-Select-then-Classify i-Select-then-Classify p-Select-then-Classify (aC/S) (cC/S) (sS/C) (dS/C) (iS/C) (pS/C) Figure 1: Anaphora resolution models Furthermore, it is sometimes difficult even for hu- and the antecedent to resolve direct anaphora. In man annotators to determine the definiteness of a example (1), the resolution model has to know bare NP. Therefore, our study for now deals with that CD and album are synonymous. For indirect the resolution of noun phrases modified by a defi- anaphora, on the other hand, the model is required niteness modifier, i.e., この (this) + NP, その (the) to recognize such semantic relations as part-whole + NP and あの (that) + NP. This problem alone is and attribute-of as in example (2), where knowing large enough, because noun phrases modified by a that CD is an object related to song is crucial. This definiteness modifier account for a large proportion expectation is supported empirically by our exper- of occurrences of nominal anaphora in Japanese iments as reported in section 5. texts. 2.2 Anaphora type classification This paper is organized as follows. In the next For anaphora type classification, an interesting section, we give a detailed explanation of our in- question is whether this subtask should be carried vestigations. In section 3, we introduce related out before antecedent selection or after. Accord- work. In section 4, the experimental setup is de- ingly, we consider two kinds of configurations: scribed. In section 5, the results of our investiga- Classify-then-Select and Select-then-Classify as tions are shown and discussed. Finally, the conclu- summarized in Figure 1. sion is given and our future work is described. 2.2.1 Classify-then-Select (C/S) model 2 Anaphora Resolution Models Given an anaphor, this model first determines To explore how our two subtasks can be best whether the anaphor bears direct anaphora, indirect configured, we consider several possible models anaphora or exophora. If the anaphora type is clas- for each subtask. sified as direct, then the model calls for the direct 2.1 Antecedent selection antecedent selection model. If classified as indi- For antecedent selection, we can employ a va- rect, on the other hand, then the model calls for the riety of existing machine learning-based methods indirect antecedent selection model. No antecedent designed for coreference resolution ranging from selection model is called for if the anaphora type classification-based models (Soon et al., 2001, is classified as exophora. The model for anaphora etc.) and preference-based models (Ng and Cardie, type classification is trained in a supervised fash- 2001, etc.) to comparison-based models (Iida ion. et al., 2005; Yang et al., 2003, etc.). In this pa- According to the information used for the classi- per, we adopt Iida et al.’s tournament model, a fication, we can consider the following two config- state-of-the-art method for coreference resolution urations: in Japanese (Iida et al., 2005). • a-Classify-then-Select (aC/S) Model: Classify One issue to explore for this subtask is whether the anaphora type by using the anaphor and its a single common model should be trained for both properties before selecting the antecedent. direct and indirect anaphora or whether a separate • c-Classify-then-Select (cC/S) Model: Classify model should be trained for each. So we consider the anaphora type using the anaphor, its prop- the following two approaches: erties and the information from all potential an- • Single model: Train a single model with labeled tecedents before selecting the antecedent. examples of both direct and indirect anaphora. To verify the effects of using additional informa- • Separate model: Train two distinct models sep- tion (i.e., contextual information) we can choose arately for direct and indirect cases; i.e., a direct the aC/S model as a baseline. We give a detail of antecedent selection model is trained only with the feature set for these models in Section 4.2. labeled examples of direct anaphora and an in- 2.2.2 Select-then-Classify (S/C) model direct antecedent selection model only with la- Given an anaphor, this model first selects the beled examples of indirect anaphora. most likely antecedent and then calls for the The separate model approach is expected to be anaphora type classifier to determine the anaphora advantageous because the semantic relation be- type referring to both the anaphor and the selected tween an anaphor and its antecedent tends to be candidate antecedent(s). This way of configura- different in direct and indirect cases. It is crucial to tion has an advantage over the Classify-then-Select identify synonymous relations between an anaphor models in that it determines the anaphora type of a given anaphor taking into account the information The case of the dS/C configuration is slightly of its most likely candidate antecedent. The can- more complex. Analogous to the sS/C model, for didate antecedent selected in the first step can be (7), the classifier takes the CDi paired with its expected to provide contextual information useful direct antecedent albumi as an instance of direct for anaphora type classification: for example, if her anaphora.
Load more

Recommended publications
  • Exophoric and Endophoric Awareness
    Arab World English Journal (AWEJ) Volume.8 Number3 September 2017 Pp. 28-45 DOI: https://dx.doi.org/10.24093/awej/vol8no3.3 Exophoric and Endophoric Awareness Mohammad Awwad Faculty of Letters and Human Sciences Lebanese University, Deanship Dekweneh , Beirut, Lebanon Abstract This research aims to shed light on the impact of exophoric and endophoric instruction on the comprehension (decoding) skills, writing (encoding skills), and linguistic awareness of English as Foreign Language learners. In this line, a mixed qualitative quantitative approach was conducted over a period of fifteen weeks on sixty English major students enrolled in their first year at the Lebanese University, fifth branch. The sixty participants were divided into two groups (30 experimental) that benefited from instruction on exophoric and endophoric relations and (30 control) that did not have the opportunity to study referents in the designated period of the research. The participants sat for a reading and writing pretest at the beginning of the study; and they sat again for the same reading and writing assessment at the end of the study. The results of the pre and post tests for both groups were analyzed via SPSS program and findings were as follows: hypothesis one stating that students who are aware of endophoric and exophoric relations are likely to achieve better results in decoding a text than are their peers who receive no referential instruction, was accepted with significant findings. Hypothesis two stating that students who are aware of endophoric and exophoric relations are likely to perform better in writing than their peers who receive no referential instruction , was accepted with significant findings.
    [Show full text]
  • Japanese Zero Reference Resolution Considering Exophora and Author/Reader Mentions
    Japanese Zero Reference Resolution Considering Exophora and Author/Reader Mentions Masatsugu Hangyo Daisuke Kawahara Sadao Kurohashi Graduate School of Informatics, Kyoto University Yoshida-honmachi, Sakyo-ku Kyoto, 606-8501, Japan hangyo,dk,kuro @nlp.ist.i.kyoto-u.ac.jp { } Abstract For example, in example (1) , the accusative argu- ment of the predicate “食べます” (eat) is omitted .1 In Japanese, zero references often occur and The omitted argument is called a zero pronoun. In many of them are categorized into zero ex- this example, the zero pronoun refers to “パスタ” ophora, in which a referent is not mentioned in (pasta). the document. However, previous studies have focused on only zero endophora, in which Zero reference resolution is divided into two sub- a referent explicitly appears. We present a tasks: zero pronoun detection and referent identifi- zero reference resolution model considering cation. Zero pronoun detection is the task that de- zero exophora and author/reader of a docu- tects omitted zero pronouns from a document. In ment. To deal with zero exophora, our model example (1), this task detects that there are the zero adds pseudo entities corresponding to zero pronouns in the accusative and nominative cases of exophora to candidate referents of zero pro- “食べます” (eat) and there is no zero pronoun in nouns. In addition, we automatically detect the dative case of “食べます”. Referent identifica- mentions that refer to the author and reader of a document by using lexico-syntactic patterns. tion is the task that identifies the referent of a zero We represent their particular behavior in a dis- pronoun.
    [Show full text]
  • The English Referential System (A Tutorial) ! Natural Language Discourse Could Have Looked Like This: ! Andy Kehler Is Traveling to Stanford on Wednesday
    Discourse The English Referential System (a tutorial) ! Natural language discourse could have looked like this: ! Andy Kehler is traveling to Stanford on Wednesday. Andy Kehler will give a talk at Stanford. Andy Kehler’s talk at Stanford will be a tutorial on reference. Andy Kehler’s tutorial on reference will be at 4:30. Andy Kehler will give another talk on Thursday. Andy Kehler’s other talk on Thursday will be about pronoun Andrew Kehler interpretation. UCSD Linguistics Workshop On Context Dependence In Language And Communication, Stanford University, November 2, 2011. 1 2 Discourse Language gives us choices ! But instead it looks like this: ! Choices when expressing propositions ! ! Andy Kehler is traveling to Stanford on Wednesday. He will give a Active: Obama won the election tutorial on reference, which will be at 4:30. That talk will be ! Passive: The election was won by Obama followed by another on Thursday about pronoun interpretation. ! Clefts: It was Obama who won the election. ! Topicalization: The election, Obama won. ! Inversion: Winning the election was Obama. ! VP-Preposing: [Obama predicted he would win the election, and] - Win the election he did! 3 4 And more choices Outline ! Choices when referring to things ! Pinning down a few basics ! indefinite ‘a’: Congress passed a bill today. ! ! indefinite ‘this’: Congress passed this bill today. Taking inventory ! definite ‘the’: Congress passed the bill today. ! A few phenomena that I find interesting ! familiar ‘that’: Congress passed that bill today. ! Concluding thoughts ! demonstratives: Congress passed this/that? ! pronouns: Congress passed it! ! proper names: Congress passed House Bill 2356 today. 5 6 Outline Pinning down some terminology (Jespersen 1954) ! Pinning down a few basics If the baby does not thrive on raw milk, boil it.
    [Show full text]
  • Antar Solhy Abdellah Publication Date: 2007 Source: CDELT (Centre for Developing English Language Teaching) Occasional Papers, January (2007) [Egypt]
    Title: “English Majors’ errors in translating Arabic Endophora; Analysis and Remedy” Author: Antar Solhy Abdellah Publication date: 2007 Source: CDELT (Centre for Developing English Language Teaching) Occasional Papers, January (2007) [Egypt]. ENGLISH MAJORS' ERRORS IN TRANSLATING ARABIC ENDOPHORA: ANALYSIS AND REMEDY Antar Solhy Abdellah Lecturer in TEFL Qena Faculty of Education, South Valley University- Egypt Abstract Egyptian English majors in the faculty of Education, South Valley university tend to mistranslate the plural inanimate Arabic pronoun with the singular inanimate English pronoun. A diagnostic test was designed to analyze this error. Results showed that a large number of students (first year and fourth year students) make this error, that the error becomes more common if the pronoun is cataphori rather than anaphori, and that the further the pronoun is from its antecedent the more students are apt to make the error. On the basis of these results, sources of the error are identified and remedial procedures are suggested. Abstract in Arabic تقوم الدراسة الحالية بتحليل أخطاء طﻻب شعبة اللغة اﻹنجليزية )الفرقة اﻷولى والرابعة( في ترجمة ضمير جمع غير العاقل من العربية إلى اﻹنجليزية؛حيث يميل الطﻻب إلى استخدام ضمير غير العاقل المفرد في اﻹنجليزية بدﻻ من ضمير الجمع. تستخدم الدراسة اختبارا تشخيصيا يسعى للكشف عن نسبة شيوع الخطأ ومن ثم تحليله. أظهرت النتائج أن عددا كبيرا من طﻻب الفرقتين يرتكبون هذا الخطأ، وأن الخطأ يزداد إذا كان الضمير في موضع المتقدم أكثر مما إذا كان في موضع المتأخر، وأن الخطأ يزداد كلما بعد الضمير عن عائده. ثم تناولت الدراسة تحليﻻ لمصدر الخطأ وقدمت مقترحات لعﻻجه. INTRODUCTION 62 Students whose major is English in faculties of Education are faced with translation problems from the very start of their study.
    [Show full text]
  • Deixis Used in the Writing Text by the Fourth Semester Students of STKIP PGRI Tulungagung
    BRIGHT: Journal of English Language Teaching, Linguistics and Literature Vol.1 No.1, July 2017, pp 54-70 Deixis Used in the Writing Text by the Fourth Semester Students of STKIP PGRI Tulungagung Umdatul Khoirot [email protected] STKIP PGRI Tulungagung ABSTRACT Deixis is clearly a form of referring that is tied to the speaker´s context which leads us to the concept of deictic centre. The deictic centre can be divided into certain ‘sub-centres’: (1) person deixis; (2) time deixis; (3) place deixis; (4) discourse deixis; and (5) social deixis. This research provides descriptive knowledge of the way in using deixis of fourth semester students of STKIP PGRI Tulungagung.This research is a descriptive qualitative for it describes deixis found on the written texts made by C class of fourth semester in English department both group A and B. Furthermore, this research is called qualitative because this research has soft data, it is in the form of words, and it provides rich description and analysis of the data.Person deixis can be found as: subject, object, possessive adjective, reflexive or emphatic pronoun, name of person, definite and indefinite noun. Furthermore, place deixis in students’ writing can be found only in word where as adverb of place. In addition, time deixis can be seen in the form of adverb of frequency, noun phrase, adjective of time, adverb of time, numeral adjective, and temporal conjunction. Key Words: deixis, deictic center, reference INTRODUCTION Pragmatics is another broad approach to discourse which deals with three concepts namely meaning, context, and communication (Schiffrin, 1994: 190).
    [Show full text]
  • A Coding System for Analysing a Spoken Text Database. PUB DATE 94 NOTE 16P.; for Serial Publication in Which This Paper Appears, See FL 022 351
    DOCUMENT RESUME ED 373 552 FL 022 352 AUTHOR Cutting, Joan TITLE A Coding System for Analysing a Spoken Text Database. PUB DATE 94 NOTE 16p.; For serial publication in which this paper appears, see FL 022 351. PUB TYPE Reports Research/Technical (143) Journal Articles (080) JOURNAL CIT Edinburgh Working Papers in Applied Linguistics; n5 p1-14 1994 EDRS PRICE MFO1 /PCO1 Plus Postage. DESCRIPTORS Applied Linguistics; *Coding; Databases; *Discourse Analysis; Foreign Countries; *Graduate Students; Grammar; *Group Discussion; Group Dynamics; Higher Education; *Language Patterns; Language Research; *Language Styles; Peer Relationship; Speech Acts IDENTIFIERS University of Edinburgh (Scotland) ABSTRACT This paper describe'a coding system devised to analyze conversations of graduate students in applied linguistics at Edinburgh University. The system was devised to test the hypothesis that as shared knowledge among conversation participants grows, the textual density of in-group members has more cues than that of strangers. The informal conversations of 6 students who shared classes in linguistics were recorded over the course of the 1991-92 academic year. The paper provides details of the lexical and grammatical tags applied to the texts of the conversations and outlines the code for the analysis of each discourse unit's assumed knowledge area, macro-function, speech act, and move. The problems encountered in the implementation of this system are discussed and explained. (Contains 15 references.)(MDM) ***********************************************************************
    [Show full text]
  • Donkey Sentences 763 Creating Its Institutions of Laws, Religion, and Learning
    Donkey Sentences 763 creating its institutions of laws, religion, and learning. many uneducated speakers to restructure their plural, It was the establishment of viceroyalties, convents so that instead of the expected cotas ‘coasts’, with -s and a cathedral, two universities – the most notable denoting plurality, they have created a new plural being Santo Toma´s de Aquino – and the flourishing of with -se,asinco´ tase. arts and literature during the 16th and early 17th Dominican syntax tends to prepose pronouns in century that earned Hispaniola the title of ‘Athena interrogative questions. As an alternative to the stan- of the New World.’ The Spanish language permeated dard que´ quieres tu´ ? ‘what do you want?’, carrying an those institutions from which it spread, making obligatory, postverbal tu´ ‘you’, speakers say que´ tu´ Hispaniola the cradle of the Spanish spoken in the quieres?. The latter sentence further shows retention Americas. of pronouns, which most dialects may omit. Fre- Unlike the Spanish of Peru and Mexico, which quently found in Dominican is the repetition of dou- co-existed with native Amerindian languages, ble negatives for emphatic purposes, arguably of Dominican Spanish received little influence from the Haitian creole descent. In responding to ‘who did decimated Tainos, whose Arawak-based language that?’, many speakers will reply with a yo no se´ no disappeared, leaving a few recognizable words, such ‘I don’t know, no’. as maı´z ‘maize’ and barbacoa ‘barbecue’. The 17th Notwithstanding the numerous changes to its century saw the French challenge Spain’s hegemony grammatical system, and the continuous contact by occupying the western side of the island, which with the English of a large immigrant population they called Saint Domingue and later became the residing in the United States, Dominican Spanish has Republic of Haiti.
    [Show full text]
  • Microstructural (Cohesion and Coherence) Text Generation Problems of Syrian Refugee Students Learning Turkish
    Universal Journal of Educational Research 5(4): 581-590, 2017 http://www.hrpub.org DOI: 10.13189/ujer.2017.050407 Microstructural (Cohesion and Coherence) Text Generation Problems of Syrian Refugee Students Learning Turkish Sercan Demirgüneş Department of Turkish Education, Omer Halisdemir University, Turkey Copyright©2017 by authors, all rights reserved. Authors agree that this article remains permanently open access under the terms of the Creative Commons Attribution License 4.0 International License Abstract In language education, teaching a language as a were obtained that Turkish was learnt with non-systematic foreign language is an emerging field compared to teaching it methods by foreigners, but there is no specific information as a mother tongue. However, the experiences obtained in about a systematic teaching of Turkish [2]. mother tongue education are adapted to teaching a language Today’s modern foreign language education policies are as a foreign language with various amendments and systematically implemented by the determination of therefore progress in this field has been achieved. Council of common criteria by Council of Europe. Common European Europe presented some common criteria for teaching a Framework of Reference for Languages (CEFR) provides a language as a foreign language and these criteria are put into common framework for foreign language education practice in many countries, including Turkey, therefore programs, textbooks etc. in all Europe. In addition to this, Common European Framework of Reference for Languages being able to use a foreign language with a means other than is also applied in teaching Turkish as a foreign language. communication describes thoroughly which knowledge and Using a microstructural analysis, this study tries to describe skill is required to be improved.
    [Show full text]
  • Global Coherence and the Teaching of Composition
    University of Louisville ThinkIR: The University of Louisville's Institutional Repository Electronic Theses and Dissertations 8-1995 Global coherence and the teaching of composition. Frank A. Davis 1953- University of Louisville Follow this and additional works at: https://ir.library.louisville.edu/etd Recommended Citation Davis, Frank A. 1953-, "Global coherence and the teaching of composition." (1995). Electronic Theses and Dissertations. Paper 318. https://doi.org/10.18297/etd/318 This Doctoral Dissertation is brought to you for free and open access by ThinkIR: The University of Louisville's Institutional Repository. It has been accepted for inclusion in Electronic Theses and Dissertations by an authorized administrator of ThinkIR: The University of Louisville's Institutional Repository. This title appears here courtesy of the author, who has retained all other copyrights. For more information, please contact [email protected]. GLOBAL COHERENCE AND THE TEACHING OF COMPOSITION By Frank A. Davis B.A., Western Kentucky University, 1976 M.A., University of Arizona, 1982 A Dissertation Submitted to the Faculty of the Graduate School of the University of Louisville in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy Department of English University of Louisville Louisville, Kentucky August 1995 Global Coherence and the Teaching of Composition By Frank A. Davis B.A., Western Kentucky University, 1976 M.A., University of Arizona, 1982 A Dissertation Approved 4 November 1994 By the Following Reading Committee Dennis Hall, Director Thomas Van R.H. Miller John Robinson H. Edward Richardson ii ABSTRACT within the discipline of rhetoric and composition, the notion of coherence possesses the status of sine qua non, yet this notion has been treated unevenly or been taken for granted, much as the process of composing itself was taken for granted for the better part of this century.
    [Show full text]
  • Resolving Direct and Indirect Anaphora for Japanese Definite
    Resolving Direct and Indirect Anaphora for Japanese Definite Noun Phrases Naoya Inouey, Ryu Iidayy, Kentaro Inuiy and Yuji Matsumotoy An anaphoric relation can be either direct or indirect. In some cases, the antecedent being referred to lies outside of the discourse its anaphor belongs to. Therefore, an anaphora resolution model needs to consider the following two decisions in parallel: antecedent selection{selecting the antecedent itself, and anaphora type classification{ classifying an anaphor into direct anaphora, indirect anaphora or exophora. However, there are non-trivial issues for taking these decisions into account in anaphora resolu- tion models since the anaphora type classification has received little attention in the literature. In this paper, we address three non-trivial issues: (i) how the antecedent se- lection model should be designed, (ii) what information helps with anaphora type clas- sification, (iii) how the antecedent selection and anaphora type classification should be carried out, taking Japanese as our target language. Our findings are: first, an antecedent selection model should be trained separately for each anaphora type using the information useful for identifying its antecedent. Second, the best candidate an- tecedent selected by an antecedent selection model provides contextual information useful for anaphora type classification. Finally, the antecedent selection should be carried out before anaphora type classification. Key Words: Anaphora resolution, antecedent selection, anaphora type classification, direct anaphora, indirect anaphora, exophora 1 Introduction Anaphora resolution has been studied intensively in recent years because of its significance in many natural language processing (NLP) applications such as information extraction and ma- chine translation. In nominal anaphora, an anaphor (typically a definite noun phrase) and its antecedent in the preceding discourse holds either a direct anaphoric relation (e.g.
    [Show full text]
  • Anaphora: Text-Based Or Discourse-Dependent? Functionalist Vs
    Anaphora: Text-based or discourse-dependent? Functionalist vs. formalist accounts Francis Cornish To cite this version: Francis Cornish. Anaphora: Text-based or discourse-dependent? Functionalist vs. formalist accounts. Functions of Language, John Benjamins Publishing, 2010, 17 (2), pp.207-241. 10.1075/fol.17.2.03cor. hal-00966398 HAL Id: hal-00966398 https://hal-univ-tlse2.archives-ouvertes.fr/hal-00966398 Submitted on 26 Mar 2014 HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. 1 ANAPHORA: TEXT-BASED OR DISCOURSE-DEPENDENT? FUNCTIONALIST VS. FORMALIST ACCOUNTS* (Published in Functions of Language 17(2), 2010, pp. 207-241. DOI: 10.1075/fol.17.2.03cor) Francis Cornish, CLLE-ERSS, CNRS UMR 5263 and Université de Toulouse-Le-Mirail, Département Etudes du Monde Anglophone, 5, Allées Antonio Machado, 31058 Toulouse Cedex 09, France Email address: [email protected] 2 Abstract The traditional definition of anaphora in purely co-textual terms as a relation between two co-occurring expressions is in wide currency in theoretical and descriptive studies of the phenomenon. Indeed, it is currently adopted in on-line psycholinguistic experiments on the interpretation of anaphors, and is the basis for all computational approaches to automatic anaphor resolution (see Mitkov, 2002).
    [Show full text]
  • Semantics and Pragmatics
    Semantics and Pragmatics Lecture No.20 Study Material Language in Context: Reference Introduction What is Reference? In pragmatics, an act in which a speaker uses linguistic forms to enable the hearer to identify something is known as reference. Reference is a broader term which covers Exophora, Endophora, Anaphora, Cataphora and Grammatical Cohesion. The speaker uses linguistic forms, known as referring expressions, to enable the hearer to identify the entity being referred to, which is known as referent. Words themselves do not refer to anything, people refer. Example: „Mr. Aftershave is late today‟. By means of reference, a speaker indicates which things in the world (including persons) are being talked about. The term 'reference‟ has to do with the relationship which holds between an expression and what that expression stands for on particular occasions of its utterance. „My son (person) is in the beech tree‟ (thing) Among referring expressions, we can distinguish between: 1. those that refer to individuals (singular – He, she, it) and those that refer to classes of individuals (general expressions – They, those). 2. Definite (The City) and indefinite (a place, a man) expressions The choice of referring expression seems to be based, to a large extent, on what the speaker assumes the listener already knows. Referential and Attributive Uses: „He wants to marry a woman with lots of money‟. an attributive use, meaning 'whoever/ whatever fits the description'. Collaboration: In reference there is a basic collaboration at work: „intention-to-identify‟ and 'recognition-of-intention‟. (End) Referring to the context outside: Exophora Exophora refers to the context which does not exist inside the text.
    [Show full text]