1 Anaphora, Discourse and Information Structure Oana Postolache EGK Colloquium April 29, 2004.

Slides:



Advertisements
Similar presentations
School of something FACULTY OF OTHER School of Computing FACULTY OF ENGINEERING Chunking: Shallow Parsing Eric Atwell, Language Research Group.
Advertisements

Referring Expressions: Definition Referring expressions are words or phrases, the semantic interpretation of which is a discourse entity (also called referent)
CILC2011 A framework for structured knowledge extraction and representation from natural language via deep sentence analysis Stefania Costantini Niva Florio.
Specialized models and ranking for coreference resolution Pascal Denis ALPAGE Project Team INRIA Rocquencourt F Le Chesnay, France Jason Baldridge.
A Machine Learning Approach to Coreference Resolution of Noun Phrases By W.M.Soon, H.T.Ng, D.C.Y.Lim Presented by Iman Sen.
Progress update Lin Ziheng. System overview 2 Components – Connective classifier Features from Pitler and Nenkova (2009): – Connective: because – Self.
NYU ANLP-00 1 Automatic Discovery of Scenario-Level Patterns for Information Extraction Roman Yangarber Ralph Grishman Pasi Tapanainen Silja Huttunen.
Processing of large document collections Part 6 (Text summarization: discourse- based approaches) Helena Ahonen-Myka Spring 2006.
1 Discourse, coherence and anaphora resolution Lecture 16.
Chapter 18: Discourse Tianjun Fu Ling538 Presentation Nov 30th, 2006.
LEDIR : An Unsupervised Algorithm for Learning Directionality of Inference Rules Advisor: Hsin-His Chen Reporter: Chi-Hsin Yu Date: From EMNLP.
CS 4705 Algorithms for Reference Resolution. Anaphora resolution Finding in a text all the referring expressions that have one and the same denotation.
Basi di dati distribuite Prof. M.T. PAZIENZA a.a
CS 4705 Lecture 21 Algorithms for Reference Resolution.
Empirical Methods in Information Extraction - Claire Cardie 자연어처리연구실 한 경 수
1 Information Retrieval and Extraction 資訊檢索與擷取 Chia-Hui Chang, Assistant Professor Dept. of Computer Science & Information Engineering National Central.
Information Retrieval and Extraction 資訊檢索與擷取 Chia-Hui Chang National Central University
تمرين شماره 1 درس NLP سيلابس درس NLP در دانشگاه هاي ديگر ___________________________ راحله مکي استاد درس: دکتر عبدالله زاده پاييز 85.
Improving Machine Learning Approaches to Coreference Resolution Vincent Ng and Claire Cardie Cornell Univ. ACL 2002 slides prepared by Ralph Grishman.
Artificial Intelligence Research Centre Program Systems Institute Russian Academy of Science Pereslavl-Zalessky Russia.
A Light-weight Approach to Coreference Resolution for Named Entities in Text Marin Dimitrov Ontotext Lab, Sirma AI Kalina Bontcheva, Hamish Cunningham,
Andreea Bodnari, 1 Peter Szolovits, 1 Ozlem Uzuner 2 1 MIT, CSAIL, Cambridge, MA, USA 2 Department of Information Studies, University at Albany SUNY, Albany,
Empirical Methods in Information Extraction Claire Cardie Appeared in AI Magazine, 18:4, Summarized by Seong-Bae Park.
“How much context do you need?” An experiment about context size in Interactive Cross-language Question Answering B. Navarro, L. Moreno-Monteagudo, E.
Tree-adjoining grammar (TAG) is a grammar formalism defined by Aravind Joshi and introduced in Tree-adjoining grammars are somewhat similar to context-free.
Illinois-Coref: The UI System in the CoNLL-2012 Shared Task Kai-Wei Chang, Rajhans Samdani, Alla Rozovskaya, Mark Sammons, and Dan Roth Supported by ARL,
A multiple knowledge source algorithm for anaphora resolution Allaoua Refoufi Computer Science Department University of Setif, Setif 19000, Algeria .
Introduction  Information Extraction (IE)  A limited form of “complete text comprehension”  Document 로부터 entity, relationship 을 추출 
Automatic Detection of Tags for Political Blogs Khairun-nisa Hassanali Vasileios Hatzivassiloglou The University.
August Discourse Structure and Anaphoric Accessibility Massimo Poesio and Barbara Di Eugenio with help from Gerard Keohane.
Terminology and documentation*  Object of the study of terminology:  analysis and description of the units representing specialized knowledge in specialized.
1 Learning Sub-structures of Document Semantic Graphs for Document Summarization 1 Jure Leskovec, 1 Marko Grobelnik, 2 Natasa Milic-Frayling 1 Jozef Stefan.
A Cross-Lingual ILP Solution to Zero Anaphora Resolution Ryu Iida & Massimo Poesio (ACL-HLT 2011)
Opinion Holders in Opinion Text from Online Newspapers Youngho Kim, Yuchul Jung and Sung-Hyon Myaeng Reporter: Chia-Ying Lee Advisor: Prof. Hsin-Hsi Chen.
Processing of large document collections Part 6 (Text summarization: discourse- based approaches) Helena Ahonen-Myka Spring 2005.
Coherence and Coreference Introduction to Discourse and Dialogue CS 359 October 2, 2001.
What you have learned and how you can use it : Grammars and Lexicons Parts I-III.
Using Semantic Relations to Improve Passage Retrieval for Question Answering Tom Morton.
For Monday Read chapter 24, sections 1-3 Homework: –Chapter 23, exercise 8.
For Monday Read chapter 26 Last Homework –Chapter 23, exercise 7.
Multilingual Opinion Holder Identification Using Author and Authority Viewpoints Yohei Seki, Noriko Kando,Masaki Aono Toyohashi University of Technology.
MedKAT Medical Knowledge Analysis Tool December 2009.
For Friday Finish chapter 23 Homework –Chapter 23, exercise 15.
Supertagging CMSC Natural Language Processing January 31, 2006.
Syntactic Annotation of Slovene Corpora (SDT, JOS) Nina Ledinek ISJ ZRC SAZU
UWMS Data Mining Workshop Content Analysis: Automated Summarizing Prof. Marti Hearst SIMS 202, Lecture 16.
Evaluation issues in anaphora resolution and beyond Ruslan Mitkov University of Wolverhampton Faro, 27 June 2002.
Answer Mining by Combining Extraction Techniques with Abductive Reasoning Sanda Harabagiu, Dan Moldovan, Christine Clark, Mitchell Bowden, Jown Williams.
Acquisition of Categorized Named Entities for Web Search Marius Pasca Google Inc. from Conference on Information and Knowledge Management (CIKM) ’04.
FILTERED RANKING FOR BOOTSTRAPPING IN EVENT EXTRACTION Shasha Liao Ralph York University.
An evolutionary approach for improving the quality of automatic summaries Constantin Orasan Research Group in Computational Linguistics School of Humanities,
For Monday Read chapter 26 Homework: –Chapter 23, exercises 8 and 9.
Using Semantic Relations to Improve Information Retrieval
Text Summarization using Lexical Chains. Summarization using Lexical Chains Summarization? What is Summarization? Advantages… Challenges…
Simone Paolo Ponzetto University of Heidelberg Massimo Poesio
Statistical NLP: Lecture 3
Web News Sentence Searching Using Linguistic Graph Similarity
INAGO Project Automatic Knowledge Base Generation from Text for Interactive Question Answering.
Kenneth Baclawski et. al. PSB /11/7 Sa-Im Shin
Curs 8 Teoria nervurilor.
NYU Coreference CSCI-GA.2591 Ralph Grishman.
Improving a Pipeline Architecture for Shallow Discourse Parsing
Referring Expressions: Definition
Social Knowledge Mining
Clustering Algorithms for Noun Phrase Coreference Resolution
Algorithms for Reference Resolution
BBI 3212 ENGLISH SYNTAX AND MORPHOLOGY
Automatic Detection of Causal Relations for Question Answering
Curs 4 Rezoluţia anaforei - continuare
Artificial Intelligence 2004 Speech & Natural Language Processing
Presentation transcript:

1 Anaphora, Discourse and Information Structure Oana Postolache EGK Colloquium April 29, 2004

2 Overview  Anaphora Resolution  Discourse (parsing)  Balkanet  Information Structure Joint work with Prof. Dan Cristea & Prof. Dan Tufis; Univ. of Iasi

3 Anaphora Resolution “If an incendiary bomb drops next to you, don’t loose your head. Put it in a bucket and cover it with sand”. Ruslan Mitkov (p.c.)

4 Anaphora Resolution “Anaphora represents the relation between a term (named anaphor) and another (named antecedent), when the interpretation of the anaphor is somehow determined by the interpretation of the antecedent”. Barbara Lust, Introduction to Studies of Anaphora Acquisition, D. Reidel, 1986

5 Anaphora Resolution Types Coreference resolution The anaphor and the antecedent refer to the same entity in the real world. Three blind mice, three blind mice. See how they run! Functional anaphora resolution The anaphor and the antecedent refer to two distinct entities that are in a certain relation. When the car stopped, the driver got scared. Haliday & Hassan 1976

6 Types of Coreference Pronominal coreference The butterflies were dancing in the air. They offered an amazing couloured show. Common nouns with different lemmas Amenophis the IV th 's wife was looking through the window. The beautiful queen was sad. Common nouns with different lemmas and number A patrol was marching in the street. The soldiers were very well trained. Proper names The President of U.S. gave a very touching speech. Bush talked about the antiterorist war. Appositions Mrs. Parson, the wife of a neighbour on the same floor, was looking for help. Nominal predicates Maria is the best student of the whole class. Function-value coreference The visitors agreed on the ticket price. They concluded that 100$ was not that much.

7 RARE – Robust Anaphora Resolution Engine RARE text AR-model 3 AR-model 2 AR-model 1 Coreference chains

8 RARE: Two main principles 1.Coreferential relations are semantic, not textual. Coreferential anaphoric relation text layer……………………………………………….. semantic layer…………………………………………… a a proposes center a center a b evokes center a b

9 RARE: Two main principles 2. Processing is incremental text layer ………………………………………… projection layer ……………………………………………………….. semantic layer …………………………………. RE b projects PS b PS b center a PS a proposes center a RE a projects PS a PS a ……………………… b a PS b evokes center a

10 Terminology text layer ……………………….………………………………………… semantic layer ……………………………………… DE m REa projection layer ……………………………………………… DE j PS x REbREcREdREx reference expressions DE 1 projected structures discourse entities

11 What is an AR-model? text layer ……………………….………………………………………… semantic layer ……………………………………… DE m REa projection layer ……………………………………………… DE j PS x REbREcREdREx DE 1 knowledge sources primary attributes heuristics/rules domain of referential accessibility

12 Primary attributes 1.Morphological (number, lexical gender, person) 2.Syntactic (REs as constituents of a syntactic tree, quality of being adjunct, embedded or complement of a preposition, inclusion or not in an existential construction, syntactic patterns in which the RE is involved) 3.Semantic and lexical (RE’s head position in a conceptual hierarchy, animacy, sex/natural gender, concreteness, inclusion in a synonymy class, semantic roles) 4.Positional (RE’s offset in the text, inclusion in a discourse unit) 5.Surface realisation (zero/clitic/full/reflexive/possessive/ demonstrative/reciprocal pronoun, expletive “it”, bare noun, indefinite NP, definite NP, proper noun) 6.Other (domain concept, frequency of the term in the text, occurrence of the term in a heading)

13 Knowledge sources A knowledge source: a (virtual) processor able to fetch values to attributes on the projections layer Minimum set: POS-tagger + shallow parser

14 Matching Rules Certifying Rules (applied first): certify without ambiguity a possible candidate. Demolishing Rules (applied afterwards): rule out a possible candidate. Scored Rules: increase/decrease a resolution score associated with a pair.

15 Domain of referential accesibility Filter and order the candidate discourse entities: a. Linearly Dorepaal, Mitkov,... b. Hierarchically Grosz & Sidner; Cristea, Ide & Romary...

16 The engine for_each RE in RESequence: projection(RE) proposing/evoking(PS) completion(DE,PS) re-evaluation

17 The engine: Projection for_each RE in RESequence: projection(RE) proposing/evoking(PS) completion(DE,PS) re-evaluation text layer ……………………….………………………………………… semantic layer ……………………………………… DE m RE a projection layer ……………………………………………… RE b RE c RE d DE n PS d RE x ps x primary attributes knowledge sources PS x

18 The engine: Proposing for_each RE in RESequence: projection(RE) proposing/evoking(PS) completion(DE,PS) re-evaluation text layer ……………………….………………………………………… semantic layer ……………………………………… DE m RE a projection layer ……………………………………………… PS x RE b RE c RE d RE x domain of referential accessibility DE n PS d heuristics/rules DE n

19 The engine: Proposing (2) for_each RE in RESequence: projection(RE) proposing/evoking(PS) apply certifying rules apply demolishing rules apply scored rules sort candidates in desc. order of scores use thresholds to: –propose a new DE –link the current PS to an existing DE –postpone decision completion(DE,PS) re-evaluation

20 The engine: Completion for_each RE in RESequence: projection(RE) proposing/evoking(PS) completion(DE,PS) re-evaluation text layer ……………………….………………………………………… semantic layer ……………………………………… DE m RE a projection layer ……………………………………………… PS x RE b RE c RE d RE x DE n PS d DE n

21 The engine: Completion (2) for_each RE in RESequence: projection(RE) proposing/evoking(PS) completion(DE,PS) re-evaluation text layer ……………………….………………………………………… semantic layer ……………………………………… DE m RE a projection layer ……………………………………………… RE b RE c RE d RE x PS d DE n

22 The engine: Re-evaluation for_each RE in RESequence: projection(RE) proposing/evoking(PS) completion(DE,PS) re-evaluation text layer ……………………….………………………………………… semantic layer ……………………………………… DE m RE a projection layer ……………………………………………… RE b RE c RE d RE x PS d DE n PS d DE n

23 The engine: Re-eval (2) for_each RE in RESequence: projection(RE) proposing/evoking(PS) completion(DE,PS) re-evaluation text layer ……………………….………………………………………… semantic layer ……………………………………… DE m RE a projection layer ……………………………………………… RE b RE c RE d RE x DE n

24 The Coref Corpus 4 chapters from George Orwell’s novel “1984” summing up aprox. 19,500 words. Preprocessed using a POS-tagger & a FDG-parser. The NPs automatically extracted from FDG structure (some manual corrections were necessary, also adding other types of referential expressions). Manual annotation of the coreferential links (each text was assigned to two annotators). Interannotator agreement – as low as 60%. Our annotation is conformant with MUC & ACE

25 The Coref Corpus Text 1Text 2Text 3Text 4Total No. of sentences No. of words No. of REs Average no. of REs per sentence Pronouns No. of DEs

26 Evaluation Success Rate = #correctly solved anaphors / all anaphors For the four texts we obtained values between 60% and 70%. (Mitkov 2000)

27 Road Map  Anaphora Resolution  Discourse (parsing)  Balkanet  Information Structure

28 Discourse Parsing Input: plain text Goal: - Automatically obtain a discourse structure of the text (resembling RST trees). - Apply the Veins Theory to produce focussed summaries. Cristea, Ide & Romary 1998

29 Veins Theory: Quick Intro Cristea, Ide & Romary H=1 3 5 H=1 3 H=1 H=3 H=1 H=2 H=3 H=4 H=5 V=1 3 5 V= V=1 3 5 V= Head expression: the sequence of the most important units within the corresponding span of text Vein expression: the sequence of units that are required to understand the span of text covered by the node, in the context of the whole discourse

30 Focused Summaries We call focused summary on an entity X, a coherent excerpt presenting how X is involved in the story that constitutes the content of the text. - It is given by the vein expression of the unit to which X belongs.

31 The method Plain text FDG parser segments detector NP Detector sentence tree extractor AR-engine tagged corefs s-trees Discouse Parser Discourse structure Veins Theory focused summary

32 The method Plain text FDG parser segments detector NP Detector sentence tree extractor AR-engine tagged corefs s-trees Discouse Parser Discourse structure Veins Theory focused summary Conexor FDG parser

33 The method Plain text FDG parser segments detector NP Detector sentence tree extractor AR-engine tagged corefs s-trees Discouse Parser Discourse structure Veins Theory focused summary Extracts NPs from the FDG structure

34 The method Plain text FDG parser segments detector NP Detector sentence tree extractor AR-engine tagged corefs s-trees Discouse Parser Discourse structure Veins Theory focused summary RARE...

35 The method Plain text FDG parser segments detector NP Detector sentence tree extractor AR-engine tagged corefs s-trees Discouse Parser Discourse structure Veins Theory focused summary Detects the boundaries of clauses, based on learning methods. Georgiana Puscasu (2004): A Multilingual Method for Clause Splitting.

36 The method Plain text FDG parser segments detector NP Detector sentence tree extractor AR-engine tagged corefs s-trees Discouse Parser Discourse structure Veins Theory focused summary — Proposes one or more tree structure(s) at the sentence level. — The leaves are the clauses previously detected. — Uses the FDG structure and the cue-phrases.

37 The method Plain text FDG parser segments detector NP Detector sentence tree extractor AR-engine tagged corefs s-trees Discouse Parser Discourse structure Veins Theory focused summary

38 The Discourse Parser – We have trees for each sentence; – The goal is to incrementally integrate these trees into a single structure corresponding to the entire text The current tree is inserted at each node on the right frontier; each resulting structure is scored considering: – The coreference links – Centering Theory – Veins Theory foot node * Cristea, Postolache, Pistol (2004): Summarization through Discourse structure (submitted to Coling)

39 The Discourse Parser – At the end of the process - set of trees corresponding to the input text, each with a score T* = argmax score(T i ) – Veins(T*) – Extract the summary TiTi

40 Discusion & Evaluation - We do obtain automatically coherent summaries! - How to evauate? - We have 90 summaries made by humans... 1)Construct a golden summary out of the 90 summaries and compare it with the system output? 2)Compare the sytem output with all 90 summaries and take the best result?

41 Road Map  Anaphora Resolution  Discourse (parsing)  Balkanet  Information Structure

42 Information Structure  Many approaches for IS:  Prague School Approach;  Formal account of English intonation;  Integrating different means of IS realization within one grammar framework;  Formal semantics of focus;  Formal semantics of topic;  Integrating IS within a theory of discourse interpretation;  IS-sensitive discourse context updating; Sgall et al; Steedman; Kruijff; Krifka, Rooth; Hendriks; Vallduvi, Kruijff-Korbayova

43 Information Structure  Goals:  Improve/Create/Enlarge a corpus annotated at IS (and not only); Investigate means of continuing the annotation (at least partially) automatically Investigate how the (major) NLP tasks can benefit from IS. Find correlation between different features. System that detects IS

44 Summary  Anaphora Resolution: RARE  Discourse Parsing: Veins theory  Balkanet: Multilingual WordNet  Information Structure

45 References Postolache, Oana ‘‘A Coreference Resolution Model on Excerpts from a novel’’. ESSLLI’04, to appear. Postolache, Oana ‘‘RARE: Robust Anaphora Resolution Engine’’. M.Sci. thesis. Univ. of Iasi.