tailieunhanh - Báo cáo khoa học: "A Simple, Similarity-based Model for Selectional Preferences"

We propose a new, simple model for the automatic induction of selectional preferences, using corpus-based semantic similarity metrics. Focusing on the task of semantic role labeling, we compute selectional preferences for semantic roles. In evaluations the similarity-based model shows lower error rates than both Resnik’s WordNet-based model and the EM-based clustering model, but has coverage problems. | A Simple Similarity-based Model for Selectional Preferences Katrin Erk University of Texas at Austin Abstract We propose a new simple model for the automatic induction of selectional preferences using corpus-based semantic similarity metrics. Focusing on the task of semantic role labeling we compute selectional preferences for semantic roles. In evaluations the similarity-based model shows lower error rates than both Resnik s WordNet-based model and the EM-based clustering model but has coverage problems. 1 Introduction Selectional preferences which characterize typical arguments of predicates are a very useful and versatile knowledge source. They have been used for example for syntactic disambiguation Hindle and Rooth 1993 word sense disambiguation WSD McCarthy and Carroll 2003 and semantic role labeling SRL Gildea and Jurafsky 2002 . The corpus-based induction of selectional preferences was first proposed by Resnik 1996 . All later approaches have followed the same two-step procedure first collecting argument headwords from a corpus then generalizing to other similar words. Some approaches have used WordNet for the generalization step Resnik 1996 Clark and Weir 2001 Abe and Li 1993 others EM-based clustering Rooth et al. 1999 . In this paper we propose a new simple model for selectional preference induction that uses corpus-based semantic similarity metrics such as Cosine or Lin s 1998 mutual informationbased metric for the generalization step. This model does not require any manually created 216 lexical resources. In addition the corpus for computing the similarity metrics can be freely chosen allowing greater variation in the domain of generalization than a fixed lexical resource. We focus on one application of selectional preferences semantic role labeling. The argument positions for which we compute selec-tional preferences will be semantic roles in the FrameNet Baker et al. 1998 paradigm and the predicates we consider will be .

• Báo cáo khoa học
• A Simple
• Similarity based Model
• Selectional Preferences
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Simple Des
• Basic fuctions of Simple De
• Crypanalysis of Simple Des
• Block cipher
• Structure of Simple Des
• Encryption algorithm on key
• Contrastive analysis
• EFL students
• Simple negative sentences
• Simple negative sentences in English
• Simple negative sentences in Vietnamese
• lập trình căn bản
• giáo trình lập trình
• ngôn ngữ lập trình
• lập trình Simple CSS Standard
• Simple CSS Standard Edition 2008
• CentOS Bible
• Windows Made Simple
• Excel 2010
• Excel 2010 Made Simple
• Abbott Katz
• English lesson
• Past simple and Past continuous
• Quá khứ đơn
• Quá khứ tiếp diễn
• Past simple
• Past continous
• The mathematics of money
• Core mathematical tools
• Simple interest
• Simple discount
• Compound interest
• Practical business
• Math procedures
• Practical business math procedures
• Maturity value
• Simple interest formula
• Development and validation of a simple spectrophotometric method
• A simple spectrophotometric method
• Quantification of chloride in polymeric materials
• The dissolution of the polymer
• Therapeutic assessment
• Dried rumen liquor preparations
• Simple indigestion in buffaloes
• Simple indigestion
• Treatment groups
• Bài giảng Lập trình nâng cao
• Kỹ thuật lập trình
• Simple calculator
• Phép toán
• Thứ tự ưu tiên
• Lệnh rẽ nhánh
• Chương trình Simple Calculator
• Mycophenolic acid
• Validation of a simple HPLC method
• Simple HPLC method
• Quantify mycophenolic acid concentrations
• Human plasma
• Abstract Summary Thesis of Language
• Semantic structure of simple sentences
• Vietnamese simple sentences
• Sentence structure
• Meaning of simple sentences
• Simple method of purification
• Purification of humic acid isolated
• Humic acid isolated
• Press mud
• Simple method
• 25 simple strategies
• boost your creativity
• luyện kỹ năng tư duy
• tư duy sáng tạo
• chiến lược phát triển sáng tạo
• giáo trình đại học
• giáo dục đào tạo
• kinh tế học
• kinh tế ứng dụng
• Simple Regression Model
• bài hát tiếng anh
• học tiếng anh qua bài hát
• lời bài hát tiếng anh
• lyric
• Simple Plan
• Happy together
• kĩ thuật lập trình
• công nghệ thông tin
• lập trình
• ngôn ngữ lập trình
• C Shark
• C#
• sybex c
• sharp database programming
• Creating a Simple ASP
• NET Web Application Using VS
• NET
• Creating a Simple Shopping Cart Application
• Developing a Simple Windows Application phần 1
• Developing a Simple Windows Application phần 2
• Simple Atmospheric Perspective
• hội họa
• kỹ thuật vẽ
• vẽ mỹ thuật
• nghệ thuật hội họa
• văn hóa hội họa
• Simple Symmetry
• Đối xứng
• Hatching Simple Mountains
• vẽ
• nghệ thuật vẽ
• văn hóa
• nghệ thuật