tailieunhanh - Báo cáo khoa học: "An Empirical Evaluation of Probabilistic Lexicalized Tree Insertion Grammars*"

We present an empirical study of the applicability of Probabilistic Lexicalized Tree Insertion Grammars (PLTIG), a lexicalized counterpart to Probabilistic Context-Free Grammars (PCFG), to problems in stochastic naturallanguage processing. Comparing the performance of PLTIGs with non-hierarchical N-gram models and PCFGs, we show that PLTIG combines the best aspects of both, with language modeling capability comparable to N-grams, and improved parsing performance over its nonlexicalized counterpart. Furthermore, training of PLTIGs displays faster convergence than PCFGs. . | An Empirical Evaluation of Probabilistic Lexicalized Tree Insertion Grammars Rebecca Hwa Harvard University Cambridge MA 02138 USA rebecca@ Abstract We present an empirical study of the applicability of Probabilistic Lexicalized Tree Insertion Grammars PLTIG a lexicalized counterpart to Probabilistic Context-Free Grammars PCFG to problems in stochastic naturallanguage processing. Comparing the performance of PLTIGs with non-hierarchical A-gram models and PCFGs we show that PLTIG combines the best aspects of both with language modeling capability comparable to A-grams and improved parsing performance over its non-lexicalized counterpart. Furthermore training of PLTIGs displays faster convergence than PCFGs. 1 Introduction There are many advantages to expressing a grammar in a lexicalized form where an observable word of the language is encoded in each grammar rule. First the lexical words help to clarify ambiguities that cannot be resolved by the sentence structures alone. For example to correctly attach a prepositional phrase it is often necessary to consider the lexical relationships between the head word of the prepositional phrase and those of the phrases it might modify. Second lexicalizing the grammar rules increases computational efficiency because those rules that do not contain any observed words can be pruned away immediately. The Lexicalized Tree Insertion Grammar formalism LTIG has been proposed as a way to lexicalize context-free grammars Schabes This material is based upon work supported by the National Science Foundation under Grant No. IRI9712068. We thank Yves Schabes and Stuart Shieber for their guidance Joshua Goodman for his PCFG code Lillian Lee and the three anonymous reviewers for their comments on the paper. and Waters 1994 . We now apply a probabilistic variant of this formalism Probabilistic Tree Insertion Grammars PLTIGs to natural language processing problems of stochastic parsing and language modeling. This paper presents

TỪ KHÓA LIÊN QUAN
crossorigin="anonymous">
Đã phát hiện trình chặn quảng cáo AdBlock
Trang web này phụ thuộc vào doanh thu từ số lần hiển thị quảng cáo để tồn tại. Vui lòng tắt trình chặn quảng cáo của bạn hoặc tạm dừng tính năng chặn quảng cáo cho trang web này.