Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
This paper presents a higher-order model for constituent parsing aimed at utilizing more local structural context to decide the score of a grammar rule instance in a parse tree. Experiments on English and Chinese treebanks confirm its advantage over its first-order version. It achieves its best F1 scores of 91.86% and 85.58% on the two languages, respectively, and further pushes them to 92.80% and 85.60% via combination with other highperformance parsers. | Higher-Order Constituent Parsing and Parser Combination Xiao Chen and Chunyu Kit Department of Chinese Translation and Linguistics City University of Hong Kong Tat Chee Avenue Kowloon Hong Kong SAR China cxiao2 ctckit @cityu.edu.hk Abstract This paper presents a higher-order model for constituent parsing aimed at utilizing more local structural context to decide the score of a grammar rule instance in a parse tree. Experiments on English and Chinese treebanks confirm its advantage over its first-order version. It achieves its best F1 scores of 91.86 and 85.58 on the two languages respectively and further pushes them to 92.80 and 85.60 via combination with other high-performance parsers. 1 Introduction Factorization is crucial to discriminative parsing. Previous discriminative parsing models usually factor a parse tree into a set of parts. Each part is scored separately to ensure tractability. In dependency parsing DP the number of dependencies in a part is called the order of a DP model Koo and Collins 2010 . Accordingly existing graph-based DP models can be categorized into tree groups namely the first-order Eisner 1996 McDonald et al. 2005a McDonald et al. 2005b second-order McDonald and Pereira 2006 Carreras 2007 and third-order Koo and Collins 2010 models. Similarly we can define the order of constituent parsing in terms of the number of grammar rules in a part. Then the previous discriminative constituent parsing models Johnson 2001 Henderson 2004 Taskar et al. 2004 Petrov and Klein 2008a The research reported in this paper was partially supported by the Research Grants Council of HKSAR China through the GRF Grant 9041597 CityU 144410 . 1 Petrov and Klein 2008b Finkel et al. 2008 are the first-order ones because there is only one grammar rule in a part. The discriminative re-scoring models Collins 2000 Collins and Duffy 2002 Charniak and Johnson 2005 Huang 2008 can be viewed as previous attempts to higher-order constituent parsing using some parts containing .
