Lexicalization of Probabilistic Grammars
نویسنده
چکیده
Two general methods for the lexicalization of probabilistic grammars are presented which are modular, powerful and require only a small number of parameters. The rst method multiplies the unlexicalized parse tree probability with the exponential of the mutual information terms of all word-governor pairs in the parse. The second lexicalization method accounts for the dependencies between the diierent arguments of a word. The model is based on a EM clustering model with word classes and se-lectional restrictions as hidden features. This model is useful for nding word classes, selec-tional restrictions and word sense probabilities.
منابع مشابه
The Role of Lexicalization and Pruning for Base Noun Phrase Grammars
This paper explores the role of lexicalization and pruning of grammars for base noun phrase identification. We modify our original framework (Cardie & Pierce 1998) to extract lexicalized treebank grammars that assign a score to each potential noun phrase based upon both the part-of-speech tag sequence and the word sequence of the phrase. We evaluate the modified framework on the “simple” and “c...
متن کاملStochastic Definite Clause Grammars
This paper introduces Stochastic Definite Clause Grammars, a stochastic variant of the wellknown Definite Clause Grammars. The grammar formalism supports parameter learning from annotated or unannotated corpora and provides a mechanism for parse selection by means of statistical inference. Unlike probabilistic contextfree grammars, it is a context-sensitive grammar formalism and it has the abil...
متن کاملMultiple Context-Free Tree Grammars and Multi-component Tree Adjoining Grammars
Strong lexicalization is the process of turning a grammar generating trees into an equivalent one, in which all rules contain a terminal leaf. It is known that tree adjoining grammars cannot be strongly lexicalized, whereas the more powerful simple context-free tree grammars can. It is demonstrated that multiple simple context-free tree grammars are as expressive as multi-component tree adjoini...
متن کاملUsing Lexicalized Grammars and Headedness for Approximate Plan Recognition
This paper presents a new algorithm for plan recognition using an action grammar formalism based on Combinatory Catagorial Grammar, that requires a significant shift in thinking about the problem of plan recognition. This approach makes significant use of the concepts of lexicalization and headedness from natural language parsing. It argues that lexicalization of action grammars can help plan r...
متن کاملOptimizing the Computational Lexicalization of Large Grammars
The computational lexicalization of a grammar is the optimization of the links between lexicalized rules and lexical items in order to improve the quality of the bottom-up filtering during parsing. This problem is N P-comple te and untractable on large grammars. An approximation algorithm is presented. The quality of the suboptimal solution is evaluated on real-world grammars as well as on rand...
متن کامل