TAILIEUCHUNG - Báo cáo khoa học: "Coreference Resolution Using Competition Learning Approach"

In this paper we propose a competition learning approach to coreference resolution. Traditionally, supervised machine learning approaches adopt the singlecandidate model. Nevertheless the preference relationship between the antecedent candidates cannot be determined accurately in this model. By contrast, our approach adopts a twin-candidate learning model. Such a model can present the competition criterion for antecedent candidates reliably, and ensure that the most preferred candidate is selected. Furthermore, our approach applies a candidate filter to reduce the computational cost and data noises during training and resolution. . | Coreference Resolution Using Competition Learning Approach Xiaofeng Yang Guodong Zh ou Institute for Infocomm Research 21 Heng Mui Keng Terrace Singapore 119613 xiaofengy zhougd sujian @ Abstract In this paper we propose a competition learning approach to coreference resolution. Traditionally supervised machine learning approaches adopt the singlecandidate model. Nevertheless the preference relationship between the antecedent candidates cannot be determined accurately in this model. By contrast our approach adopts a twin-candidate learning model. Such a model can present the competition criterion for antecedent candidates reliably and ensure that the most preferred candidate is selected. Furthermore our approach applies a candidate filter to reduce the computational cost and data noises during training and resolution. The experimental results on MUC-6 and MUC-7 data set show that our approach can outperform those based on the singlecandidate model. 1 Introduction Coreference resolution is the process of linking together multiple expressions of a given entity. The key to solve this problem is to determine the antecedent for each referring expression in a document. In coreference resolution it is common that two or more candidates compete to be the antecedent of an anaphor Mitkov 1999 . Whether a candidate is coreferential to an anaphor is often determined by the competition among all the candidates. So far various algorithms have been proposed to determine the preference relationship between two candidates. Mitkov s knowledge-poor pronoun resolution method Mitkov 1998 for example uses the scores from a set of antecedent indicators Jian Su Chew Lim Tan Department of Computer Science National University of Singapore Singapore 117543 yangxiao tancl @ to rank the candidates. And centering algorithms Brennan et al. 1987 Strube 1998 Tetreault 2001 sort the antecedent candidates based on the ranking of the forward-looking or backwardlooking

• Báo cáo khoa học
• Coreference Resolution
• Competition Learning Approach
• Xiaofeng Yang
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• VNU Journal of Science
• Coreference resolution in Vietnamese electronic medical records
• Vietnamese electronic medical records
• Adjective mentions possible
• Coreference resolution in Vietnamese EMRs
• Unsupervised Event Coreference Resolution
• Rich Linguistic Features
• Long Papers
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Coreference Resolution across Corpora
• Coding Schemes
• and Preprocessing Information
• Coreference Resolution with Reconcile
• Veselin Stoyanov
• Conundrums in Noun Phrase Coreference Resolution
• Making Sense
• State of the Art
• Bootstrapping Coreference Resolution
• Word Associations
• Hamidreza Kobdani
• World Knowledge
• Altaf Rahman and Vincent Ng
• State of the art NLP
• Approaches to Coreference Resolution
• Theory and Practical Recipes
• An Entity Mention Model
• Inductive Logic Programming
• Enforcing Transitivity
• Jenny Rose Finkel and Christopher D
• Manning
• Conditional Modality Fusion
• Jacob Eisenstein and Randall Davis
• Semantic Relatedness Information
• Automatically Discovered Patterns
• Semantic Class Induction
• Vincent Ng
• A Modular Toolkit
• Unsupervised Coreference Resolution
• Nonparametric Bayesian Model
• Aria Haghighi and Dan Klein
• Machine Learning for Coreference Resolution
• From Local Classification to Global Ranking
• A Mention Synchronous Coreference Resolution Algorithm
• the Bell Tree
• Xiaoqiang Luo and Abe Ittycheriah Hongyan Jing and Nanda Kambhatla and Salim Roukos
• Learning Noun Phrase Anaphoricity to Improve Coreference Resolution
• Issues in Representation and Optimization
• Reference Resolution
• beyond Coreference
• Conceptual Frame and its Application
• Improving Machine Learning
• Vincent Ng and Claire Cardie
• Semantic Role Labeling
• Simone Paolo Ponzetto and Michael Strube
• scientific reports
• model language
• process natural language
• Optimization in Coreference Resolution Is Not Needed
• A Nearly Optimal Algorithm
• Intensional Constraints
• BMC Bioinformatics
• Coreference annotation
• Colorado Richly Annotated Full Text
• Syntactic annotation
• Domain specific ontologies