tailieunhanh - Báo cáo khoa học: "AUTOMATIC ACQUISITION OF SUBCATEGORIZATION FRAMES FROM UNTAGGED TEXT"

This paper describes an implemented program that takes a raw, untagged text corpus as its only input (no open-class dictionary) and generates a partial list of verbs occurring in the text and the subcategorization frames (SFs) in which they occur. Verbs are detected by a novel technique based on the Case Filter of Rouvret and Vergnaud (1980). The completeness of the output list increases monotonically with the total number of occurrences of each verb in the corpus. False positive rates are one to three percent of observations. Five SFs are currently detected and more are planned. . | AUTOMATIC ACQUISITION OF SUBCATEGORIZATION FRAMES FROM UNTAGGED TEXT Michael R. Brent MIT Al Lab 545 Technology Square Cambridge Massachusetts 02139 michael@ ABSTRACT This paper describes an implemented program that takes a raw untagged text corpus as its only input no open-class dictionary and generates a partial list of verbs occurring in the text and the sub categorization frames SFs in which they occur. Verbs are detected by a novel technique based on the Case Filter of Rouvret and Vergnaud 1980 . The completeness of the output list increases monotonically with the total number of occurrences of each verb in the corpus. False positive rates are one to three percent of observations. Five SFs are currently detected and more are planned. Ultimately I expect to provide a large SF dictionary to the NLP community and to train dictionaries for specific corpora. 1 INTRODUCTION This paper describes an implemented program that takes an untagged text corpus and generates a partial list of verbs occurring in it and the subcategorization frames SFs in which they occur. So far it detects the five SFs shown in Table 1. SF Description Good Example Bad Example direct object direct object clause direct object infinitive clause infinitive greet them tell him he s a fool want him to attend know I ll attend hope to attend arrive them hope him he s a fool hope him to attend want I ll attend greet to attend Table 1 The five subcategorization frames SFs detected so far The SF acquisition program has been tested on a corpus of million words of the Wall Street Journal kindly provided by the Penn Tree Bank project . On this corpus it makes 5101 observations about 2258 orthographically distinct verbs. False positive rates vary from one to three percent of observations depending on the SF. WHY IT MATTERS Accurate parsing requires knowing the subcategorization frames of verbs as shown by 1 . 1 a. I expected up the man who smoked Np to eat ice-cream b. I doubted Np the man

• Báo cáo khoa học
• AUTOMATIC ACQUISITION
• SUBCATEGORIZATION FRAMES
• UNTAGGED TEXT
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Automatic Selectional Preference Acquisition
• Latin verbs
• Barbara McGillivray
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Ranked Qualia Structures from the Web
• Philipp Cimiano Johanna Wenderoth
• Adjectival Subcategorization from Corpora
• Jeremy Yallop
• English Topic Signatures
• a Second Language
• An Improved Extraction
• Pattern Representation Model
• Automatic IE Pattern Acquisition
• Automatic Acquisition of Named
• Entity Tagged Corpus
• World Wide Web
• Language Model
• Head Dependent Relation between Words
• A LARGE SUBCATEGORIZATION DICTIONARY FROM CORPORA
• Christopher D
• Manning
• THE LEXICAL SEMANTICS OF VERBS
• SENTENCE FRAMES
• scientific reports
• model language
• process natural language
• Knowledge Acquisition from Texts
• Using an Automatic Clustering Method
• Noun Modifier Relationship
• Script Knowledge
• Text Collection
• NATURALLANGUAGEPROCESSINGAND THE AUTOMATIC
• ACQUISITION OF KOLDENWEG
• Long Papers