tailieunhanh - Báo cáo khoa học: "Utilizing Dependency Language Models for Graph-based Dependency Parsing Models"

Most previous graph-based parsing models increase decoding complexity when they use high-order features due to exact-inference decoding. In this paper, we present an approach to enriching high-order feature representations for graph-based dependency parsing models using a dependency language model and beam search. The dependency language model is built on a large-amount of additional autoparsed data that is processed by a baseline parser. | Utilizing Dependency Language Models for Graph-based Dependency Parsing Models Wenliang Chen Min Zhangi and Haizhou Li Human Language Technology Institute for Infocomm Research Singapore wechen mzhang hli @ Abstract Most previous graph-based parsing models increase decoding complexity when they use high-order features due to exact-inference decoding. In this paper we present an approach to enriching high-order feature representations for graph-based dependency parsing models using a dependency language model and beam search. The dependency language model is built on a large-amount of additional autoparsed data that is processed by a baseline parser. Based on the dependency language model we represent a set of features for the parsing model. Finally the features are efficiently integrated into the parsing model during decoding using beam search. Our approach has two advantages. Firstly we utilize rich high-order features defined over a view of large scope and additional large raw corpus. Secondly our approach does not increase the decoding complexity. We evaluate the proposed approach on English and Chinese data. The experimental results show that our new parser achieves the best accuracy on the Chinese data and comparable accuracy with the best known systems on the English data. 1 Introduction In recent years there are many data-driven models that have been proposed for dependency parsing McDonald and Nivre 2007 . Among them graphbased dependency parsing models have achieved state-of-the-art performance for a wide range of languages as shown in recent CoNLL shared tasks Corresponding author 213 Buchholz and Marsi 2006 Nivre et al. 2007 . In the graph-based models dependency parsing is treated as a structured prediction problem in which the graphs are usually represented as factored structures. The information of the factored structures decides the features that the models can utilize. There are several previous studies that exploit high-order .