Empirical Evaluation of Pronoun Resolution and Clausal Structure Joel Tetreault and James Allen University of Rochester Department of Computer Science.

Slides:



Advertisements
Similar presentations
Computational language: week 10 Lexical Knowledge Representation concluded Syntax-based computational language Sentence structure: syntax Context free.
Advertisements

Using Syntax to Disambiguate Explicit Discourse Connectives in Text Source: ACL-IJCNLP 2009 Author: Emily Pitler and Ani Nenkova Reporter: Yong-Xiang Chen.
Specialized models and ranking for coreference resolution Pascal Denis ALPAGE Project Team INRIA Rocquencourt F Le Chesnay, France Jason Baldridge.
Automatically Evaluating Text Coherence Using Discourse Relations Ziheng Lin, Hwee Tou Ng and Min-Yen Kan Department of Computer Science National University.
Prototype-Driven Grammar Induction Aria Haghighi and Dan Klein Computer Science Division University of California Berkeley.
1 Discourse, coherence and anaphora resolution Lecture 16.
Pragmatics II: Discourse structure Ling 571 Fei Xia Week 7: 11/10/05.
Discourse Martin Hassel KTH NADA Royal Institute of Technology Stockholm
Chapter 18: Discourse Tianjun Fu Ling538 Presentation Nov 30th, 2006.
INTERNATIONAL CONFERENCE ON NATURAL LANGUAGE PROCESSING NLP-AI IIIT-Hyderabad CIIL, Mysore ICON DECEMBER, 2003.
Semantic Role Labeling Abdul-Lateef Yussiff
April 26th, 2007 Workshop on Treebanking, HLT/NAACL, Rochester 1 Layering of Annotations in the Penn Discourse TreeBank (PDTB) Rashmi Prasad Institute.
Recognizing Implicit Discourse Relations in the Penn Discourse Treebank Ziheng Lin, Min-Yen Kan, and Hwee Tou Ng Department of Computer Science National.
S © Siemens Corporate Research, Inc. S I E M E N S C O R P O R A T E R E S E A R C H A Corpus-based Analysis for the Ordering of Clause Aggregation Operators.
Advanced Topics in Algorithms and Data Structures 1 Rooting a tree For doing any tree computation, we need to know the parent p ( v ) for each node v.
Introduction to RST Rhetorical Structure Theory Maite Taboada and Manfred Stede Simon Fraser University / Universität Potsdam Contact:
Partial Prebracketing to Improve Parser Performance John Judge NCLT Seminar Series 7 th December 2005.
14 April 2005 RST Discourse Corpus Lynn Carlson Daniel Marcu Mary Ellen Okurowski.
Evaluation of NLP Systems Martin Hassel KTH NADA Royal Institute of Technology Stockholm
CS 4705 Algorithms for Reference Resolution. Anaphora resolution Finding in a text all the referring expressions that have one and the same denotation.
CS 4705 Discourse Structure and Text Coherence. What makes a text/dialogue coherent? Incoherent? “Consider, for example, the difference between passages.
Generative Models of Discourse Eugene Charniak Brown Laboratory for Linguistic Information Processing BL IP L.
Discourse Structure Grosz and Sidner. Why bother? Leads to an account of discourse meaning Constrains how utterances are related Useful for explaining.
CS 4705 Lecture 21 Algorithms for Reference Resolution.
Natural Language Generation Martin Hassel KTH CSC Royal Institute of Technology Stockholm
June 7th, 2008TAG+91 Binding Theory in LTAG Lucas Champollion University of Pennsylvania
1 Introduction to Computational Linguistics Eleni Miltsakaki AUTH Spring 2006-Lecture 7.
Dialogue Structure and Pronoun Resolution Joel Tetreault and James Allen University of Rochester Department of Computer Science DAARC September 23, 2004.
1 Section 9.2 Tree Applications. 2 Binary Search Trees Goal is implementation of an efficient searching algorithm Binary Search Tree: –binary tree in.
Discourse Annotation for Improving Spoken Dialogue Systems Joel Tetreault, Mary Swift, Preethum Prithviraj, Myroslava Dzikovska, James Allen University.
Advanced Topics in Algorithms and Data Structures 1 An example.
Curs 10: Veins Theory Discourse structure and coherence Dan Cristea Selecţie de sliduri.
UAM CorpusTool: An Overview Debopam Das Discourse Research Group Department of Linguistics Simon Fraser University Feb 5, 2014.
ICS 220 – Data Structures and Algorithms Week 7 Dr. Ken Cosh.
Tree Kernels for Parsing: (Collins & Duffy, 2001) Advanced Statistical Methods in NLP Ling 572 February 28, 2012.
Database Management 9. course. Execution of queries.
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,
TEXT PROCESSING 1 Anaphora resolution Introduction to Anaphora Resolution.
Methods for the Automatic Construction of Topic Maps Eric Freese, Senior Consultant ISOGEN International.
1 Exploiting Syntactic Patterns as Clues in Zero- Anaphora Resolution Ryu Iida, Kentaro Inui and Yuji Matsumoto Nara Institute of Science and Technology.
August Discourse Structure and Anaphoric Accessibility Massimo Poesio and Barbara Di Eugenio with help from Gerard Keohane.
Computer Sciences Department1. Sorting algorithm 3 Chapter 6 3Computer Sciences Department Sorting algorithm 1  insertion sort Sorting algorithm 2.
A Study of Balanced Search Trees: Brainstorming a New Balanced Search Tree Anthony Kim, 2005 Computer Systems Research.
REFERENTIAL CHOICE AS A PROBABILISTIC MULTI-FACTORIAL PROCESS Andrej A. Kibrik, Grigorij B. Dobrov, Natalia V. Loukachevitch, Dmitrij A. Zalmanov
Reference Resolution. Sue bought a cup of coffee and a donut from Jane. She met John as she left. He looked at her enviously as she drank the coffee.
A Systematic Exploration of the Feature Space for Relation Extraction Jing Jiang & ChengXiang Zhai Department of Computer Science University of Illinois,
Conversion of Penn Treebank Data to Text. Penn TreeBank Project “A Bank of Linguistic Trees” (as of 11/1992) University of Pennsylvania, LINC Laboratory.
Coherence and Coreference Introduction to Discourse and Dialogue CS 359 October 2, 2001.
What’s in a translation rule? Paper by Galley, Hopkins, Knight & Marcu Presentation By: Behrang Mohit.
A.F.K. by SoTel. An Introduction to SoTel SoTel created A.F.K., an Android application used to auto generate text message responses to other users. A.F.K.
CSCI 4310 Lecture 6: Adversarial Tree Search. Book Winston Chapter 6.
NLP. Introduction to NLP Background –From the early ‘90s –Developed at the University of Pennsylvania –(Marcus, Santorini, and Marcinkiewicz 1993) Size.
Automatic recognition of discourse relations Lecture 3.
Evaluation issues in anaphora resolution and beyond Ruslan Mitkov University of Wolverhampton Faro, 27 June 2002.
INTRO TO HEAP & Adding and Removing a NODE Presented to: Sir AHSAN RAZA Presented by: SHAH RUKH Roll #07-22 Semester BIT 3 rd Session 2007—2011 Department.
Natural Language Processing Lecture 15—10/15/2015 Jim Martin.
CPSC 422, Lecture 27Slide 1 Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 27 Nov, 16, 2015.
Probabilistic Text Structuring: Experiments with Sentence Ordering Mirella Lapata Department of Computer Science University of Sheffield, UK (ACL 2003)
NLP. Parsing ( (S (NP-SBJ (NP (NNP Pierre) (NNP Vinken) ) (,,) (ADJP (NP (CD 61) (NNS years) ) (JJ old) ) (,,) ) (VP (MD will) (VP (VB join) (NP (DT.
1 An Efficient Optimal Leaf Ordering for Hierarchical Clustering in Microarray Gene Expression Data Analysis Jianting Zhang Le Gruenwald School of Computer.
LING/C SC 581: Advanced Computational Linguistics Lecture Notes Feb 3 rd.
Statistical Natural Language Parsing Parsing: The rise of data and statistics.
Matching sets of parse trees for answering multi-sentence questions
CSC 594 Topics in AI – Natural Language Processing
Curs 8 Teoria nervurilor.
Red Black Trees
LING/C SC/PSYC 438/538 Lecture 21 Sandiway Fong.
Algorithms for Reference Resolution
A Machine Learning Approach to Coreference Resolution of Noun Phrases
A Machine Learning Approach to Coreference Resolution of Noun Phrases
Presentation transcript:

Empirical Evaluation of Pronoun Resolution and Clausal Structure Joel Tetreault and James Allen University of Rochester Department of Computer Science

RST and pronoun resolution Previous work suggests that breaking apart utterances into clauses (Kameyama 1998), or assigning a hierarchical structure (Grosz and Sidner, 1986; Webber 1988) can aid in the resolution of pronouns: 1. Make search more efficient (less entities to consider) 2. Make search more successful (block competing antecedents) Empirical work has focused on using segmentation to limit accessibility space of antecedents Test claim by performing an automated study on a corpus (1241 sentence subsection of PennTreebank; rd person pronouns)

Rhetorical Structure Theory A way of organizing and describing natural text (Mann and Thompson, 1988) It identifies a hierarchical structure Describes binary relations between text parts

Experiment Create coref corpus that includes PT syntactic trees and RST information Run pronoun algorithms over this merged data set to determine baseline score LRC (Tetreault, 1999) S-list (Strube, 1998) BFP (Brennan et al., 1987) Develop algorithms that use clausal information to compare with baseline

Corpus 52 Wall Street Journal Articles from 1995 Penn Treebank 1273 sentences, 7594 words, 454 third person pronouns Pronoun Corpus annotated in same manner as Ge and Charniak (1998) RST corpus from RST Discourse Treebank (Marcu et al., 2002)

Pronoun Corpus ( (S (S (NP\-SBJ\-\1#-290~1 (DT The) (NN package) ) (VP (VBD was) (VP (VBN termed) (S (NP\-SBJ (\-NONE\- \*\-\1) ) (ADJP\-PRD (JJ excessive) )) (PP (IN by) (NP\-LGS (DT the) (NNP Bush) (NN administration) ))))) (\, \,) (CC but) (S (NP\-SBJ (PRP#OBJREF-290~2 it) ) (ADVP (RB also) ) (VP (VBD provoked) (NP…..

RST Corpus (SATELLITE (SPAN |4| |19|) (REL2PAR ELABORATION- ADDITIONAL) (SATELLITE (SPAN |4| |7|) (REL2PAR CIRCUMSTANCE) (NUCLEUS (LEAF |4|) (REL2PAR CONTRAST) (TEXT _!THE PACKAGE WAS TERMED EXCESSIVE BY THE BUSH |ADMINISTRATION,_!|)) (NUCLEUS (SPAN |5| |7|) (REL2PAR CONTRAST) (NUCLEUS (LEAF |5|) (REL2PAR SPAN) (TEXT _!BUT IT ALSO PROVOKED A STRUGGLE WITH INFLUENTIAL CALIFORNIA LAWMAKERS_!))

Baseline Results Algorithm% Right (S)% Right (C) LRC80.8%76.4% S-list73.4%70.0% BFP59.5%48.7% Naïve50.7%56.0%

LRC Algorithm While processing utterance’s entities (left to right) do: Push entity onto Cf-list-new, if pronoun, attempt to resolve first: Search through Cf-list-new (l-to-r) taking the first candidate that meets gender, agreement constraints, etc. If none found, search past utterance’s Cf-lists starting from previous utterance to beginning of discourse

LRC Error Analysis (89 errors) (24) Minimal S “the committee said the company reneged on its obligations” (21) Localized Errors “…to get a customer’s 1100 parcel-a-week load to its doorstep” (15) Preposed Phrase “Although he was really tired, John managed to drive 10 hours without sleep”

LRC Errors (2) (12) Parallelism “It more than doubled the Federal’s long term debt to 1.9 billion dollars, thrust the company into unknown territory – heavy cargo – and suddenly exanded its landing rights to 21 countries from 4. (11) Competing Antecedents “The weight of Lebanon’s history was also against him, and it is a history…” (4) Plurals referring to companies “The Ministory of Construction spreads concrete…. But they seldom think of the poor commuters.”

LRC Errors (3) (2) Genitive Errors “Mr. Richardson wouldn;t offer specifics regarding Atco’s proposed British project, but he said it would compete for customers…”

Advanced Approaches Grosz and Sidner (1986)– discourse structure is dependent on intentional structure. Attentional state is modeled as a stack that pushes and pops current state with changes in intentional structure Veins Theory (Ide and Cristea, 2000) – position of nuclei and satellites in a RST tree determine DRA (domain of referential accessibility) for each clause

G&S Accessibility e3 e4 e5 e6, p1 e1, e2 Search Order: e6, e5, e4, e1, e2

Veins Theory Each RST discourse unit (leaf) has an associated vein (Cristea et al., 1998; Ide and Cristea, 2000) Vein provides a “summary of the discourse fragment that contains that unit” Contains salient parts of the RST tree – the preceding nuclei and surrounding satellites Veins determined by whether node is a nucleus or satellite and what its left and right children are

Veins Algorithm Use same data set augmented with head and veins information (automatically computed) Exception: RST data set has some multi-child nodes, assume all extra children are right children Bonus: areas to the left of the root are potentially accessible – makes global topics introduced in the beginning accessible Implementation – search each unit in the entity’s DRA starting with most-recent and left-to-right within clause. If no antecedent is found, use LRC to search.

Transforms Goal of transforms – flatten corpus a bit to create larger segments, so more entities can be considered SAT – merge satellite leaf into its sibling if sibling is a subtree with all leaves SENT – merge clauses together in RST tree back into sentence ATT – merge clauses that are in attribution relation

Transform Examples Nucleus Leaf C1 Satellite Leaf C2 Subtree Root Nucleus *Sat-leaf C3 (1) ORIG Subtree Root C1 C3 (2) SAT C2 Subtree Root(3) SENT C1 + C2 + C3 (4) ATTSubtree Root C1 + C2C3 * C1 and C2 are in an Attribution relation

SAT example S.A. Brewing would make a takeover offer for all of Bell Resources if it exercises the option according to the commission. Nucleus Sat-Leaf (attribution) Nuc-LeafSat-Leaf (condition) Nucleus S.A. Brewing would make a takeover offer for all of Bell Resources if it exercises the option according to the commission Sat-Leaf Nuc-LeafSat-Leaf Nucleus ORIGINAL TRANSFORM

SENT example Under the plan, Costa Rica will buy back roughly 60% of its bank debt at a deeply discounted price according to officials Nuc-Leaf Satellite (attribution) Nuc-Leaf Sat-Leaf (elaboration) Nucleus ORIGINAL TRANSFORM involved in the agreement. Under the plan, Costa Rica will buy back roughly 60% of its bank debt at a deeply discounted price, according to officials involved in the agreement Nuc-leaf

ATT example said Douglas Myers, Chief Executive Of Lion Nathan. Nuc-LeafSat-Leaf (attribution) Satellite (summary) ORIGINAL TRANSFORM Lion Nathan has a concluded contract with Bond and Bell Resources, Sat-leaf (summary) Lion Nathan has a concluded contract with Bond and Bell Resources, said Douglas Myers, Chief Executive of Lion Nathan

Results TransformVeins (S)Veins (C)GS (S*)GS (S)GS (C) Original ATT SAT SENTN/A N/A SENT-SATN/A N/A

Long Distance Resolution 10 cases in corpus of pronouns with antecedents more than 2 utterances away, most in ATT relations LRC gets them all correct, since no competing antecedents (“him”, “their”) Veins (w/o ATT) gets 6 out of 10 With the transforms, all algorithms get 100%

Conclusions Two ways to determine success of decomposition strategy: intrasentential and intersentential resolution Intra: no improvement, better to use grammatical function Inter: LDR’s…. Hard to draw concrete conclusions Need more data to determine if transforms give a good approximation of segmentation Using G&S accessibility of clauses doesn’t seem to work either At the minimum, even if a method performs the same, it has the advantage of a smaller search space

Future Work Error analysis shows determining coherence relations could account for several intrasentential cases Use rhetorical relations themselves to constrain accessibility of entities Annotating human-human dialogues in TRIPS 911 domain for reference, already been annotated for argumentation acts (Stent, 2001)