tailieunhanh - Báo cáo khoa học: "Syntactic Features and Word Similarity for Supervised Metonymy Resolution"

We present a supervised machine learning algorithm for metonymy resolution, which exploits the similarity between examples of conventional metonymy. We show that syntactic head-modifier relations are a high precision feature for metonymy recognition but suffer from data sparseness. We partially overcome this problem by integrating a thesaurus and introducing simpler grammatical features, thereby preserving precision and increasing recall. Our algorithm generalises over two levels of contextual similarity. . | Syntactic Features and Word Similarity for Supervised Metonymy Resolution Malvina Nissim ICCS School of Informatics University of Edinburgh mnissim@ Katja Markert ICCS School of Informatics University of Edinburgh and School of Computing University of Leeds markert@ Abstract We present a supervised machine learning algorithm for metonymy resolution which exploits the similarity between examples of conventional metonymy. We show that syntactic head-modifier relations are a high precision feature for metonymy recognition but suffer from data sparseness. We partially overcome this problem by integrating a thesaurus and introducing simpler grammatical features thereby preserving precision and increasing recall. Our algorithm generalises over two levels of contextual similarity. Resulting inferences exceed the complexity of inferences undertaken in word sense disambiguation. We also compare automatic and manual methods for syntactic feature extraction. 1 Introduction Metonymy is a figure of speech in which one expression is used to refer to the standard referent of a related one Lakoff and Johnson 1980 . In 1 1 seat 19 refers to the person occupying seat 19. 1 Ask seat 19 whether he wants to swap The importance of resolving metonymies has been shown for a variety of NLP tasks . machine translation Kamei and Wakao 1992 question answering Stallard 1993 and anaphora resolution Harabagiu 1998 Markert and Hahn 2002 . 1 1 was actually uttered by a flight attendant on a plane. In order to recognise and interpret the metonymy in 1 a large amount of knowledge and contextual inference is necessary . seats cannot be questioned people occupy seats people can be questioned . Metonymic readings are also potentially open-ended Nunberg 1978 so that developing a machine learning algorithm based on previous examples does not seem feasible. However it has long been recognised that many metonymic readings are actually quite regular Lakoff and Johnson 1980 .

• Báo cáo khoa học
• Syntactic Features
• Word Similarity
• Supervised Metonymy Resolution
• Malvina Nissim
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Syntactic features of rejection in English
• Face threatening speech act
• Rejection in declarative structures
• Interrogative structures
• Cross cultural communication
• Syntactic representation
• Dictionary for learners of English
• Exploring Syntactic Structural Features
• Sub Tree Alignment
• Bilingual Tree Kernels
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Improving Chinese Semantic Role Labeling
• Rich Syntactic Features
• Weiwei Sun
• Computing
• Evaluating Syntactic Complexity Features for Automated Scoring
• Spontaneous Non Native Speech
• Combining Lexical
• Syntactic
• Semantic Features
• Maximum Entropy Models
• Extracting Relations
• Lexicon Features
• Japanese Syntactic Analysis
• Mu Project JE
• scientific reports
• model language
• process natural language
• The syntactic features
• Vietnamese negative sentences
• English negative sentences
• Literary works
• Negative sentences
• Graduation course of English language sector
• The English translational versions
• Trinh Cong Son’s songs in terms
• Semantic and syntactic features
• English and Vietnamese
• Educational mottos
• Tertiary institutions
• English speaking countries
• Overseas educational sector
• Research article
• Comparative perspective
• Vietnamese researchers
• English for Specific Purposes
• Syntactic realizations
• Functional grammar
• Syntactic aspect
• Theoretical framework
• Hyperbolic expressions
• CEO news
• Chief Executive Officials
• Pragmatic features
• English and Vietnamese language teaching
• Teacher student conversations
• Halliday’s Functional Grammar
• Linguistic features
• Syntactic aspects