TAILIEUCHUNG - Báo cáo khoa học: "WSD as a Distributed Constraint Optimization Problem"

This work models Word Sense Disambiguation (WSD) problem as a Distributed Constraint Optimization Problem (DCOP). To model WSD as a DCOP, we view information from various knowledge sources as constraints. DCOP algorithms have the remarkable property to jointly maximize over a wide range of utility functions associated with these constraints. We show how utility functions can be designed for various knowledge sources. | WSD as a Distributed Constraint Optimization Problem Siva Reddy IIIT Hyderabad India Abhilash Inumella IIIT Hyderabad India gvsreddy@ abhilashi@ Abstract This work models Word Sense Disambiguation WSD problem as a Distributed Constraint Optimization Problem DCOP . To model WSD as a DCOP we view information from various knowledge sources as constraints. DCOP algorithms have the remarkable property to jointly maximize over a wide range of utility functions associated with these constraints. We show how utility functions can be designed for various knowledge sources. For the purpose of evaluation we modelled all words WSD as a simple DCOP problem. The results are competitive with state-of-art knowledge based systems. 1 Introduction Words in a language may carry more than one sense. The correct sense of a word can be identified based on the context in which it occurs. In the sentence He took all his money from the bank bank refers to a financial institution sense instead of other possibilities like the edge of river sense. Given a word and its possible senses as defined by a dictionary the problem of Word Sense Disambiguation WSD can be defined as the task of assigning the most appropriate sense to the word within a given context. WSD is one of the oldest problems in computational linguistics which dates back to early 1950 s. A range of knowledge sources have been found to be useful for WSD. Agirre and Stevenson 2006 Agirre and Martinez 2001 McRoy 1992 Hirst 1987 highlight the importance of various knowledge sources like part of speech morphology collocations lexical knowledge base sense taxonomy gloss sub-categorization semantic word associations selectional preferences semantic roles domain topical word associations frequency of senses collocations domain knowledge. etc. Methods for WSD exploit information from one or more of these knowledge sources. Supervised approaches like Yarowsky and Florian 2002 Lee and Ng 2002 Martinez et

• Báo cáo khoa học
• WSD
• Distributed Constraint Optimization Problem
• Abhilash Inumella
• báo cáo khoa học
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Multilingual WSD
• Just a Few Lines of Code
• the BabelNet API
• All Words Domain Adapted WSD
• Finding a Middle Ground
• Supervision and Unsupervision
• Combining Orthogonal Monolingual
• Multilingual Sources of Evidence
• All Words WSD
• Bilingual Bootstrapping for WSD
• Long Papers
• Workshort
• Ensemble Methods
• Unsupervised WSD
• Samuel Brody Roberto Navigli Mirella Lapata
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Choosing Sense Distinctions for WSD
• Psycholinguistic Evidence
• Susan Windisch Brown
• A Hybrid Relational Approach
• WSD – First Results
• Lucia Specia Núcleo
• Supervised Domain
• Adaption for WSD
• Eneko Agirre and Oier Lopez
• scientific reports
• model language
• process natural language
• cách làm luận văn
• cách trình bày luận văn
• hướng dẫn làm luận văn
• luận văn ngành công nghệ sinh học
• kỹ thuật hóa mô miễn dịch