tailieunhanh - Báo cáo khoa học: "A Connectionist Approach to Prepositional Phrase Attachment for Real World Texts"

Ill this paper we describe a neural network-based approach to prepositional phrase attachment disambiguation for real world texts. Although the use of semantic classes in this task seems intuitively to be adequate, methods employed to date have not used them very effectively. Causes of their poor results are discussed. Our model, which uses only classes, scores appreciably better than the other class-based methods which have been tested on the Wall Street Journal corpus. To date, the best result obtained using only classes was a score of ; we obtained an accuracy score of . . | A Connectionist Approach to Prepositional Phrase Attachment for Real World Texts Josep M. Sopena and Agusti LLoberas and Joan L. Moliner Laboratory of Neurocomputing University of Barcelona Pg. Vail d Hebron 171 08035 Barcelona Spain e-mail pep agusti j oan axon . Abstract In this paper we describe a neural network-based approach to prepositional phrase attachment disambiguation for real world texts. Although the use of semantic classes in this task seems intuitively to be adequate methods employed to date have not used them very effectively. Causes of their poor results are discussed. Our model which uses only classes scores appreciably better than the other class-based methods which have been tested on the Wall Street Journal corpus. To date the best result obtained using only classes was a score of we obtained an accuracy score of . This score is among the best reported in the literature using this corpus. 1 Introduction Structural ambiguity is one of the most serious problems faced by Natural Language Processing NLP systems. It occurs when the syntactic information does not suffice to make an assignment decision. Prepositional phrase PP attachment is perhaps the canonical case of structural ambiguity. What kind of information should we use in order to solve this ambiguity In most cases the information needed comes from a local context and the attachment decision is based essentially on the relationships existing between predicates and arguments what Katz y Fodor 1963 called selectional restrictions. For example in the expression V accommodate NP Johnson s election PP as a director the pp is attached to the NP. However in the expression V taking NP that news pp as a sign to be cautious the pp is attached to the verb. In both expressions the attachment site is decided on the basis of verb and noun selectional restrictions. In other cases the information determining the pp attachment comes from a global context. In this paper we will focus on .

• Báo cáo khoa học
• A Connectionist
• Prepositional Phrase Attachment
• Real World Texts
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• A Connectionist Architecture
• Learning to Parse
• Long Papers
• Optimality Theory
• Universal Grammar
• Learning and Parsing Algorithms
• Connectionist Foundations
• Acquiring Receptive Morphology
• A Connectionist Model
• Michael Gasser
• DUAL CODING THEORY
• CONNECTIONIST LEXICAL SELECTION
• Ye Yi Wang
• An Incremental Connectionist
• Phrase Structure Parser
• James Henderson
• A CONNECTIONIST PARSER FOR STRUCTURE
• UNIFICATION GRAMMAR
• James B
• Henderson
• ASPECTS OF ANAPHOR RESOLUTION
• Ronan G
• Reilly
• scientific reports
• model language
• process natural language
• Connectionist Models
• Natural Language Processing
• David L
• Waltz
• REPRESENTATION OF FEATURE SYSTEMS
• NON CONNECTIONIST MOLECULAR MACHINE