Incremental dependency parsing based on headed context-free grammar
نویسندگان
چکیده
This paper proposes the incremental dependency parsing method based on the context-free grammar with dependency information. In the proposed method, the reachability, which represents the relation between categories, is used. In parallel to the inputting of sentence, the dependency, which is the relation between the modifying word and the modified word, is computed. In the proposed method, the parse tree to cover the inputted fragment of the sentence is not needed. Consequently, the method can compute the dependency more efficiently than the method that computes the dependency from the parse tree. As a result of a parsing experiment using ATIS corpus, the proposed method utilizing the reachability is demonstrated to be effective in reducing the parsing time. © 2005 Wiley Periodicals, Inc. Syst Comp Jpn, 36(2): 63–77, 2005; Published online in Wiley InterScience (www.interscience. wiley.com). DOI 10.1002/scj.10524
منابع مشابه
Implications of a Structured Vecto- rial Semantic Framework for Incre- mental Interpretation
Previous corpus studies have shown that the memory usage of a syntactic processing model based on a simple right-corner grammar transform (Schuler et al. 2008, 2010) corresponds to recent estimates of human short-term memory capacity (Miller 1956, Cowan 2001). This article describes a study of the memory usage of a straightforward extension of this model to incremental semantic processing, show...
متن کاملTransition-based dependency parsing as latent-variable constituent parsing
We provide a theoretical argument that a common form of projective transitionbased dependency parsing is less powerful than constituent parsing using latent variables. The argument is a proof that, under reasonable assumptions, a transition-based dependency parser can be converted to a latent-variable context-free grammar producing equivalent structures.
متن کاملA Simple String-Rewriting Formalism For Dependency Grammar
Recently, dependency grammar has gained renewed attention as empirical methods in parsing have emphasized the importance of relations between words, which is what dependency grammars model explicitly, but context-free phrase-structure grammars do not. While there has been much work on formalizing dependency grammar and on parsing algorithms for dependency grammars in the past, there is not a co...
متن کاملA Syntactified Direct Translation Model with Linear-time Decoding
Recent syntactic extensions of statistical translation models work with a synchronous context-free or tree-substitution grammar extracted from an automatically parsed parallel corpus. The decoders accompanying these extensions typically exceed quadratic time complexity. This paper extends the Direct Translation Model 2 (DTM2) with syntax while maintaining linear-time decoding. We employ a linea...
متن کاملCombine Constituent and Dependency Parsing via Reranking
This paper presents a reranking approach to combining constituent and dependency parsing, aimed at improving parsing performance on both sides. Most previous combination methods rely on complicated joint decoding to integrate graphand transition-based dependency models. Instead, our approach makes use of a high-performance probabilistic context free grammar (PCFG) model to output k-best candida...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Systems and Computers in Japan
دوره 36 شماره
صفحات -
تاریخ انتشار 2005