The Resolution of Anaphoric Links Using Mitkov s Algorithm

Similar documents
Anaphora Resolution. Nuno Nobre

08 Anaphora resolution

Identifying Anaphoric and Non- Anaphoric Noun Phrases to Improve Coreference Resolution

Towards a more consistent and comprehensive evaluation of anaphora resolution algorithms and systems

Reference Resolution. Regina Barzilay. February 23, 2004

Reference Resolution. Announcements. Last Time. 3/3 first part of the projects Example topics

ANAPHORA RESOLUTION IN HINDI LANGUAGE USING GAZETTEER METHOD

Year 7. Reading and Writing Booklet. This is a booklet to help you improve your English skills.

Automatic Evaluation for Anaphora Resolution in SUPAR system 1

Anaphora Resolution Exercise: An overview

Hybrid Approach to Pronominal Anaphora Resolution in English Newspaper Text

Coreference Resolution Lecture 15: October 30, Reference Resolution

Anaphora Resolution in Biomedical Literature: A

Anaphora Resolution in Hindi Language

How often do you go shopping? Target Language. Adverbs of Definite Frequency once three times four times

The Transmission of God s Word: Gender and Bible Choice

Dialogue structure as a preference in anaphora resolution systems

Totalitarianism Case Study: Stalinist Russia

Outline of today s lecture

Anaphoric Deflationism: Truth and Reference

Resolving Direct and Indirect Anaphora for Japanese Definite Noun Phrases

Introduction to the Special Issue on Computational Anaphora Resolution

Anaphora Resolution in Biomedical Literature: A Hybrid Approach

Models of Anaphora Processing and the Binding Constraints

TURCOLOGICA. Herausgegeben von Lars Johanson. Band 98. Harrassowitz Verlag Wiesbaden

CAS LX 522 Syntax I Fall 2000 November 6, 2000 Paul Hagstrom Week 9: Binding Theory. (8) John likes him.

Long-distance anaphora: comparing Mandarin Chinese with Iron Range English 1

Could have done otherwise, action sentences and anaphora

Statistical anaphora resolution in biomedical texts

Performance Analysis of two Anaphora Resolution System for Hindi Language

807 - TEXT ANALYTICS. Anaphora resolution: the problem

ANAPHORA RESOLUTION IN MACHINE TRANSLATION

For what does the scripture say? "Abraham believed God, and it was reckoned to him as righteousness." (NRS)

Wenstrom Bible Ministries Pastor-Teacher Bill Wenstrom Tuesday December 5, 2017

An Analysis of Reference in J.K. Rowling s Novel: Harry Potter and the Half-Blood Prince

Keywords Coreference resolution, anaphora resolution, cataphora, exaphora, annotation.

Palomar & Martnez-Barco the latter being the abbreviating form of the reference to an entity. This paper focuses exclusively on the resolution of anap

TEXT MINING TECHNIQUES RORY DUTHIE

1. Read, view, listen to, and evaluate written, visual, and oral communications. (CA 2-3, 5)

ADDIS ABABA UNIVERSITY SCHOOL OF GRADUATE STUDIES. Design of Amharic Anaphora Resolution Model. Temesgen Dawit

Pronoun-Antecedent Agreement

A Machine Learning Approach to Resolve Event Anaphora

Some observations on identity, sameness and comparison

The Spirit (Breath) of God By Tim Warner, Copyright 4Winds Fellowships

Year 9 P3 Jekyll and Hyde Assessment- Parent/Carer Information

An Introduction to Anaphora

Semantics and Pragmatics of NLP DRT: Constructing LFs and Presuppositions

SEVENTH GRADE RELIGION

Grace Bible Church Tree of Life A Weekly Review Week ending

INFORMATION EXTRACTION AND AD HOC ANAPHORA ANALYSIS

HS01: The Grammar of Anaphora: The Study of Anaphora and Ellipsis An Introduction. Winkler /Konietzko WS06/07

Article selection and anaphora in the German relative clause Julian Grove and Emily Hanink University of Chicago

FOUR CHAPTERS ON FREEDOM

ANAPHORIC REFERENCE IN JUSTIN BIEBER S ALBUM BELIEVE ACOUSTIC

What Is Saving Faith According to John s Gospel? John Hepp, Jr.

Scriptural Promise The grass withers, the flower fades, but the word of our God stands forever, Isaiah 40:8

1984 GEORGE ORWELL PART ONE. Thoughtcrime. CHAPTER ONE Big Brother Is Watching You

Unit 2. Spelling Most Common Words Root Words. Student Page. Most Common Words

Recall. Validity: If the premises are true the conclusion must be true. Soundness. Valid; and. Premises are true

The Eden Proverb 2004 by Gerry L. Folbré III Research

Lesson 8 Taking Notes from a Speaker

The Murders in the Rue Morgue

Holy Spirit VI. The Comforter

LESSON 6. You will recognize the beginning form immediately. Right?

The miraculous gifts of the Holy Spirit are temporary.

THE SEVENTH-DAY ADVENTIST CHURCH AN ANALYSIS OF STRENGTHS, WEAKNESSES, OPPORTUNITIES, AND THREATS (SWOT) Roger L. Dudley

June Frank W. Nelte "GREAT TRIBULATION" AND "THE GREAT TRIBULATION"

AliQAn, Spanish QA System at multilingual

Resolution A-179 Clergy Compensation Submitted by Diocesan Council CASH SALARY & HOUSING ALLOWANCE TABLE FOR FULL-TIME PRIESTS.

Prentice Hall Literature: Timeless Voices, Timeless Themes, Bronze Level '2002 Correlated to: Oregon Language Arts Content Standards (Grade 7)

BY FAITH WE HAVE IN MIND... Hebrews 11:2, 3. Lordian Day September 16, 2018 a. m.

A Survey on Anaphora Resolution Toolkits

Polishing Our Hermeneutical Glasses Section 8 Useful Terms for The Study of Hermeneutics

What were we put in the world to do?

SCIENCE ASSESSMENT P4-G5 Colour key: Working Scientifically Animals, Including Humans Plants Materials Weather/Seasons/Earth and Space Living Things

Triune God. Week 5. September 29, 2013

THE LAWRENCE SCHOOL, SANAWAR ENGLISH

Resolution A-179 Clergy Compensation Submitted by Diocesan Council CASH SALARY & HOUSING ALLOWANCE TABLE FOR FULL-TIME PRIESTS.

Pronominal, temporal and descriptive anaphora

Climbing the Stairs Discussion Questions

the ARTICLE (for teachers)

Appendix K. Exegesis for the Translation of the Phrase the Holy Spirit as Antecedent in John 14, 15 and 16

Brainstorming exercise

On the Interpretation of Anaphoric Noun Phrases: Towards a Full Understanding of Partial Matches

CONGREGATIONAL VITALITY PROJECT

PAGE(S) WHERE TAUGHT (If submission is not text, cite appropriate resource(s))

By George Orwell. CHAPTER ONE Big Brother Is Watching You

Parish Needs Survey (part 2): the Needs of the Parishes

Table of Contents 1-30

UNIVERSITY FACULTY COUNCIL. Special Meeting July 2018, 2 pm Eastern / 1 pm Central Meeting and Videoconference MINUTES

The Reliability of Anaphoric Annotation, Reconsidered: Taking Ambiguity into Account

Natural Language Processing

, and Imperfect Verbs

CHAPTER IV FINDING AND DISCUSSION

Prentice Hall Literature: Timeless Voices, Timeless Themes, Silver Level '2002 Correlated to: Oregon Language Arts Content Standards (Grade 8)

Please turn with me to * Song of Solomon 5:10-16* and let s read it together I am my beloved s and my beloved is mine Song of Solomon 6:3a

Discourse Constraints on Anaphora Ling 614 / Phil 615 Sponsored by the Marshall M. Weinberg Fund for Graduate Seminars in Cognitive Science

Did Jesus Commit a Fallacy?

NUMBER, GENDER AND CASE IN GRAMMAR, AND AGREEMENT PHENOMENA

Pendragon Book One: The Merchant of Death by D.J. MacHale

Transcription:

The Resolution of Anaphoric Links Using Mitkov s Algorithm Taavet Kikas, Margus Treumuth May 4, 2007 1 The Task The task was to investigate anaphoric relations in two parallel texts (i.e. a source language text and its translation in another language) and to classify the anaphoric relations along the lines proposed by Mitkov [Mitkov 2000][Mitkov 2002]. 2 The Resolution of Anaphoric Links Using Mitkov s Algorithm We chose two parallel texts (Estonian-English aligned on level) from Multext-East Corpus containing the novel "1984" by George Orwell. We tried to resolve anaphoras in the Estonian s and in the corresponding English s using an algorithm proposed by Mitkov [Mitkov 2000]. This algorithm is known as knowledge-poor pronoun resolution approach. The key idea of the algorithm is to assign scores to noun phrase (NP) candidates based on different indicators and then choose the candidate with the highest score. The indicators used for calculating the score are given below. We used gender and number agreement as the primary filtering conditions. This filter eliminates noun phrases that do not have a matching gender or number. The filter is applied as the first step before the actual scoring begins. We did not use the boosting indicators "Indicating Verbs" and "Section Heading Preference" as we did not have a predefined set of verbs and we did not have section headings. We used the boosting indicators "First Noun Phrases" (score +1), "Lexical Re" (+1), "Collocation Pattern Preference" (+1), "Term preference" (+1). We also suggest a boosting indicator "Case Agreement" which could be used to improve Estonian anaphora resolution. The impeding indicators we used were "Indefiniteness" (-1) and "Prepositional Noun Phrases" (-1) as suggested by Mitkov [Mitkov 2000]. The prepositional NPs in Estonian are not as frequent. On the other hand, the use of postpositional phrases is rather common. It also common to use case endings instead of postpositions. In many occasions there are two parallel forms, one that uses separate postposition and the other one that uses case ending. We will refer to both of these as Postposition and regard them as impeding factor (-1).

We also used "Referential Distance" to impede or boost a candidate's chances of being selected as the antecedent of a pronoun depending on the NP's distance in s of clause and boundaries from the pronoun. The results are presented in the tables below where the s above the tables are the s that were used in the resolution. The bold and underlined words are anaphoras and their corresponding antecedents. The antecedents that were resolved with the best score are represented in a bold text in the first column of the table.

3 Experiments 3.1 The first set of s (Estonian-English) The first set of Estonian s used in anaphora resolution See oli osa vihkamise nädala eelsest kokkuhoiukampaaniast. Korter oli kaheksandal korrusel, ja Winston, kes oli kolmekümne üheksa aastane ja kel oli veenilaiendi haavand parema jala pahkluu kohal, astus aeglaselt, tőmmates minnes korduvalt hinge. Igal korrusel vaatas lifti vastasseinalt vastu plakat selle tohutu näoga. See oli niisugune pilt, mis on tehtud nii, et silmad saadavad sind igale poole. Phrase preference prepositional or postpositional indefiniteness distance (2, 1, 0, -1) score Igal korrusel 1 1 1-1 -1 1 0 lifti vastasseinalt 1 1-1 1 0 plakat selle tohutu näoga 1 1 1 1 Korter 1 1 1 0 1 kaheksandal korrusel 1 1 0 0 Winston 1 1 0 0 veenilaiendi haavand 1 1 0 0 parema jala pahkluu kohal 1 1 0 0 See 1 1 1-1 0 osa vihkamise nädala eelsest 1 1-1 -1-2 Kokkuhoiukampaaniast 1 1-1 -1 The task was to resolve the anaphora See (in English: it ). The analysis of the text in Estonian gave two results with equal scores and one of these is the correct antecedent for the anaphora. To improve the resolution of Estonian anaphoras it would be necessary to see if the phrases are in the same case (there are 14 cases in Estonian). We suggest that the boosting +1 should be applied if the anaphora and the antecedent are in the same case.

The first set of English s used in anaphora resolution It was part of the economy drive in preparation for Hate Week. The flat was seven flights up, and Winston, who was thirty-nine and had a varicose ulcer above his right ankle, went slowly, resting several times on the way. On each landing, opposite the lift-shaft, the poster with the enormous face gazed from the wall. It was one of those pictures which are so contrived that the eyes follow you about when you move. Phrase preference prepositional indefiniteness distance (2, 1, 0, -1) score On each landing 1 1 1-1 -1 1 0 opposite the lift-shaft 1 1-1 1 0 the poster with the enormous face 1 1 1 1 from the wall 1 1-1 1 0 The flat 1 1 1 0 1 Seven flights 1 0 0 Winston 1 1 0 0 a varicose ulcer 1 1-1 0 0 His right ankle 1 1 0 0 On the way 1 1-1 0-1 It 1 1-1 -1 part of the economy drive 1 1-1 -1-2 in preparation for Hate Week 1 1-1 -1-2 The analysis of the text in English gave two results with equal scores and one of these is the correct antecedent for the anaphora. The problem is that the first NP of the received boosting that was not justified in this case. As the algorithm gave better results in English, it supports the claim that the bilingual corpora can be used to improve pronoun resolution [Mitkov 2002]. We could have benefitted from the knowledge that opposite the lift shaft is a prepositional phrase and needs to be impeded by adding -1 to the score.

3.2 The second set of s (Estonian-English) The second set of Estonian s used in anaphora resolution Korter oli kaheksandal korrusel, ja Winston, kes oli kolmekümne üheksa aastane ja kel oli veenilaiendi haavand parema jala pahkluu kohal, astus aeglaselt, tőmmates minnes korduvalt hinge. Igal korrusel vaatas lifti vastasseinalt vastu plakat selle tohutu näoga. See oli niisugune pilt, mis on tehtud nii, et silmad saadavad sind igale poole. "Suur Vend valvab sind", oli pildi all kiri. There are no anaphoric pronouns in the Estonian ("Suur Vend valvab sind", oli pildi all kiri.). Yet there are anaphoric pronouns in the corresponding English (see the analysis on the next page).

The second set of English s used in anaphora resolution The flat was seven flights up, and Winston, who was thirty-nine and had a varicose ulcer above his right ankle, went slowly, resting several times on the way. On each landing, opposite the lift-shaft, the poster with the enormous face gazed from the wall. It was one of those pictures which are so contrived that the eyes follow you about when you move. "Big Brother is watching you", the caption beneath it ran. Phrase Collocation preference prepositional indefiniteness distance (2, 1, 0, -1) score Big Brother 1 1 1 2 3 you (1) 1 1 1 1 you (2) 1 1 1 1 the eyes 1 0 1 one of those pictures 1 1 1 0 1 2 On each landing 1 1 1-1 -1 0-1 opposite the lift-shaft 1 1-1 0-1 the poster with the enormous face 1 1 0 0 from the wall 1 1-1 0-1 The flat 1 1 1-1 0 seven flights 1 0-1 Winston 1 1-1 -1 a varicose ulcer 1 1-1 -1 his right ankle 1 1-1 -1 on the way 1 1-1 -1-2 The NP Big Brother was incorrectly identified as the antecedent of the anaphora it. The NP received boosting points because it was in the same with the anaphora it and was also the the. It is interesting to notice that the Estonian translation could have used the anaphoric pronoun, yet for unknown reasons it was replaced with explicit NP. This example also shows that again the use of parallel (bilingual) corpora would have been of great help in identifying the correct antecedent for the English translation.

3.3 The third set of s (Estonian-English) The third set of Estonian s used in anaphora resolution Korteris luges mahlakas hääl ette mingeid arvusid, mis käisid ilmselt malmitootmise kohta. Hääl tuli piklikust, tuhmi peegli moodi metallplaadist, mis moodustas osa parempoolesest seinast. Winston keeras nuppu ja hääl jäi veidi vaiksemaks, kuigi sőnad olid endiselt selged. Tal oli väga heledad juuksed ja loomu poolest jumekas nägu, mille naha oli kehv seep, nürid žiletid ja äsja lőppenud talve külmad karedaks muutnud. Phrase preference prepositional or postpositional indefiniteness distance (2, 1, 0, -1) score Sőnad 0 1 1 Hääl 0 1 1 1 Nuppu 0 1 1 Winston 1 1 1 1 2 osa parempoolesest seinast 0 1-1 0 piklikust, tuhmi peegli moodi metallplaadist 0 1-1 0 Hääl 0 1 1 1 0 Malmitootmise 0 1-1 mingeid arvusid 0 0-1 mahlakas hääl 0 1 1-1 Korteris 0 1 1-1 -1 This experiment worked well with no problems as the gender filter eliminated all other words but Winston, which was the correct choice. Although the gender between masculine and feminine cannot be distinguished in Estonian, the gender between neuter and masculine/feminine can be distinguished.

The third set of English s used in anaphora resolution Inside the flat a fruity voice was reading out a list of figures which had something to do with the production of pig-iron. The voice came from an oblong metal plaque like a dulled mirror which formed part of the surface of the right-hand wall. Winston turned a switch and the voice sank somewhat, though the words were still distinguishable. His hair was very fair, his face naturally sanguine, his skin roughened by coarse soap and blunt razor blades and the cold of the winter that had just ended. Phrase first NP in preference prepositional indefiniteness distance (2, 1, 0, -1) score the words 0 0 1 the voice 0 1 1 1 a switch 0 1-1 1 Winston 1 1 1 1 2 part of the surface of the right-hand wall 0 1-1 0 an oblong metal plaque like a dulled mirror 0 1-1 0 The voice 0 1 1 1 0 the production of pig-iron 0 1-1 a list of figures 0 0-1 a fruity voice 0 1 1-1 Inside the flat 0 1 1-1 -1 In the English translation the gender filter also eliminated all other words but Winston, which was the correct choice.

3.4 The fourth set of s (Estonian-English) The fourth set of Estonian s used in anaphora resolution Oli külm selge aprillipäev, kellad lőid parajasti kolmteist. Winston Smith, lőug vastu rinda surutud, et kaitsta end läbilőikava tuule vastu, lipsas kiiresti Vőidu Maja klaasuksest sisse, aga mitte küllalt kiiresti, et takistada liivasegust tolmukeerist endaga kaasa tulemast. Trepikoda haises keedetud kapsa ja vanade kaltsumattide järgi. Selle ühes otsas oli seinale kinnitatud värviline plakat, mis oli siseruumi kohta liiga suur. prepositional or distance (2, phrase preference postpositional indefiniteness 1, 0, -1) score külm selge argipäev 1 1 1-1 0 kellad 1 0-1 kolmteist 1 1-1 -1 Winston Smith 0 1 1 lõug 1 1 0 rind 1 1-1 -1 läbilõikav tuul 1 1-1 -1 Võidu Maja klaasuks 1 1-1 -1 liivasegune tolmukeeris 1 1 0 trepikoda 1 1 1 1 2 keedetud kapsas 1 1 1 1 vanad kaltsumatid 1 0 1 1

The fourth set of English s used in anaphora resolution It was a bright cold day in April, and the clocks were striking thirteen. Winston Smith, his chin nuzzled into his breast in an effort to escape the vile wind, slipped quickly through the glass doors of Victory Mansions, though not quickly enough to prevent a swirl of gritty dust from entering along with him. The hallway smelt of boiled cabbage and old rag mats. At one end of it a coloured poster, too large for indoor display, had been tacked to the wall. phrase preference prepositional or postpositional indefiniteness distance (2, 1, 0, -1) score a bright cold day in April 1 1 1-1 -1-1 the clocks 1 0-1 thirteen 1 1-1 -1 Winston Smith 0 1 1 his chin 1 1 0 his breast 1 1-1 -1 an effort 1 1-1 -1 the vile wind the glass doors of Victory Mansions 1 0-1 a swirl of gritty dust 1 1-1 -1 the hallway 1 1 1 1 2 boiled cabbage 1 1 1 1 old rag mats 1 0 1 The noun phrase was identified correctly in both cases. There are some significant differences between English and Estonian. For example the glass doors of Victory Mansions is translated as Võidu Maja klaasuks, which actually means the glass door of Victory Mansion, so there is a difference in number. The average score for English noun phrases is little lowern than in Estonian, this is due to the fact that Esonian nouns do not have indefiniteness, which contributes to negative socre in English.

3.5 The fifth set of s (Estonian-English) The fifth set of Estonian s used in anaphora resolution Winston Smith, lőug vastu rinda surutud, et kaitsta end läbilőikava tuule vastu, lipsas kiiresti Vőidu Maja klaasuksest sisse, aga mitte küllalt kiiresti, et takistada liivasegust tolmukeerist endaga kaasa tulemast. Trepikoda haises keedetud kapsa ja vanade kaltsumattide järgi. Selle ühes otsas oli seinale kinnitatud värviline plakat, mis oli siseruumi kohta liiga suur. See kujutas vaid üht tohutut, enam kui meetrilaiust nägu: umbes neljakümne viie aastase mehe nägu tihedate mustade vuntside ja karmide meeldivate näojoontega. phrase preference prepositional or postpositional indefiniteness distance (2, 1, 0, -1) score Winston Smith 1 1 1 1 lõug 1 1-1 -1 rind 1 1-1 -1-2 läbilõikav tuul 1 1-1 -1-2 Võidu Maja klaasuks 1 1-1 -1-2 liivasegune tolmukeeris 1 1-1 -1 trepikoda 1 1 1 1 keedetud kapsas 1 1 0 vanad kaltsumatid 1 0 värviline plakat 1 1 1 1 2 sein 1 1-1 1 0

The fifth set of English s used in anaphora resolution Winston Smith, his chin nuzzled into his breast in an effort to escape the vile wind, slipped quickly through the glass doors of Victory Mansions, though not quickly enough to prevent a swirl of gritty dust from entering along with him. The hallway smelt of boiled cabbage and old rag mats. At one end of it a coloured poster, too large for indoor display, had been tacked to the wall. It depicted simply an enormous face, more than a metre wide: the face of a man of about forty-five, with a heavy black moustache and ruggedly handsome features. phrase preference prepositional or postpositional indefiniteness distance (2, 1, 0, -1) score Winston Smith 0 1 1-1 his chin 1 1-1 -1 his breast 1 1-1 -1-2 an effort 1 1-1 -1-2 the vile wind 1 1-1 the glass doors of Victory Mansions 1 0-1 -1 a swirl of gritty dust 1 1-1 -1-2 the hallway 1 1 1 1 boiled cabbage 1 1 0 old rag mats 1 0 a coloured poster 1 1 1-1 1 1 the wall 1 1-1 1 0 In this case the right pronoun is selected only in Estonian. In English the knowledge-poor approach does a pretty good job as well but is unable to select the best noun phrase simply by comparing the scores as both the hallway and colured poster gain the same rating. This is a case of tough anaphor [Mitkov 2001], for which some sort of heuristics has to be applied. Another possibility is to use the approach proposed by Mitkov [Mitkov Bilingual]. His basic idea is to use the help of parallel corpora to resolve the ambiguity. In the current case there is no ambiguity in the Estonian translation so we can simply choose the nounphrase that corresponds to the Estonian phrase that got the highest score. This approach will give a right answer at least in the current case.

3.6 The sixth set of s (Estonian-English) The sixth set of Estonian s used in anaphora resolution See kujutas vaid üht tohutut, enam kui meetrilaiust nägu: umbes neljakümne viie aastase mehe nägu tihedate mustade vuntside ja karmide meeldivate näojoontega. Winston hakkas treppist üles minema. Lifti ei tasunud proovidagi. See töötas parematel aegadel harva, ja praegu oli vool päeva ajaks välja lülitatud. phrase preference prepositional or postpositional indefiniteness distance (2, 1, 0, -1) score enam kui meetri laiust nägu 1 1 1-1 0 umbes neljakümne viie aastase mehe nägu 1 1-1 -1 tihedate mustade vuntside 1 0-1 karmide meeldivate näojoontega 1 0-1 -1 Winston 0 1 1 trepist (üles minema) 1 1-1 -1 Lifti 1 1 1 1 2

The sixth set of English s used in anaphora resolution It depicted simply an enormous face, more than a metre wide: the face of a man of about forty-five, with a heavy black moustache and ruggedly handsome features. Winston made for the stairs. It was no use trying the lift. Even at the best of times it was seldom working, and at present the electric current was cut off during daylight hours. phrase preference prepositional or postpositional indefiniteness distance (2, 1, 0, -1) score an enormouse face 1 1 1-1 -1-1 the face of a man 1 1-1 -1 heavy black moustache 1 1-1 -1 ruggedly handsome features 1 0-1 Winston 0 1 1 the stairs 1 1 0 the lift 1 1 1 1 2 The knowledge-poor approach identifies the right noun phrase for the English text and as well for the Estonian translation, but again there are some differences in translation. This alters the individual scores. The Winston made for the stairs is translated as Winston hakkas treppist üles minema, which in direct translation means Winston started to move up the stairs. So the stairs appears in a prepositional phrase in Estonian but not in a prepositional phrase in English. There is also a difference between word moustache and word vuntsid. They both mean the same thing, but the Estonian noun is in plural. This eliminates it from the noun phrase candidates. So we might benefit form number dissimilarities in different languages when resolving anaphors.

4 Conclusion The experiments show that the method proposed by Mitkov works well and can be improved even more by using bilingual corpora. The knowledge poor approach performed equally well on the English test set and on the Estonian counterpart, even though the method was not designed for Estonian, which is a somewhat different language. Some of these differences were illustrated in our examples. We also came up with an idea that the boosting indicator Case Agreement might be of some help in Estonian anaphora resolution. It would be interesting to try to implement the algorithm and evaluate it on a larger group of s in Estonian language. For those experiments that resulted in more than one antecedent, the heuristics to be applied to distinguish the correct antecedent were really hard to come up with. We noticed that the positional features (like first noun phrase in ) were less important than gender and number agreement. References [Mitkov 2000] Mitkov, R. 2000. "Towards a more consistent and comprehensive evaluation of anaphora resolution algorithms and systems." Proceedings of the Discourse Anaphora and Anaphora Resolution Colloquium (DAARC-2000), 96-107, Lancaster, UK [Mitkov 2002] Mitkov, R. and Barbu, C. 2002. "Using bilingual corpora to improve pronoun resolution." Languages in context, 4(1).