Joint Optimization for Chinese POS Tagging and Dependency Parsing

Abstract

Abstract-Dependency parsing has gained more and more interest in natural language processing in recent years due to its simplicity and general applicability for diverse languages. Previous work demonstrates that part-of-speech (POS) is an indispensable feature in dependency parsing since pure lexical features suffer from serious data sparseness problem. However, due to little morphological changes, Chinese POS tagging has proven to be much more challenging than morphology-richer languages such as English (94% vs. 97% on POS tagging accuracy). This leads to severe error propagation for Chinese dependency parsing. Our experiments show that parsing accuracy drops by about 6% when replacing manual POS tags of the input sentence with automatic ones generated by a state-of-the-art statistical POS tagger. To address this issue, this paper proposes a solution by jointly optimizing POS tagging and dependency parsing in a unique model. We propose for our joint models several dynamic programming based decoding algorithms which can incorporate rich POS tagging and syntactic features. Then we present an effective pruning strategy to reduce the search space of candidate POS tags, leading to significant improvement of parsing speed. Experimental results on two Chinese data sets, i.e. Penn Chinese Treebank 5.1 and Penn Chinese Treebank 7, demonstrate that our joint models significantly improve both the state-of-the-art tagging and parsing accuracies. Detailed analysis shows that the joint method can help resolve syntax-sensitive POS ambiguities . In return, the POS tags become more reliable and helpful for parsing since the syntactic features are used in POS tagging. This is the fundamental reason for the performance improvement.Index Terms-Dependency parsing, dynamic programming, joint models, part-of-speech tagging.

A Survey of Natural Language Query Builder Interface for Structured Databases using Dependency Parsing

“…Several joint models and their corresponding decoding algorithms which can incorporate different feature sets are proposed in this paper. The experimental results show that joint models can significantly improve the state-of-the-art POS tagging parsing accuracies [3].…”

An improved joint model: POS tagging and dependency parsing

“…Li et al (2011) proposes graphbased joint models according to syntactic features. It defines first-, second-, and third-order joint models [4]. Li et al (2012) presents a graph-based joint model.…”

Joint Model of Korean Part-of-Speech Tagging and Dependency Parsing with Partial Tagged Corpus

“…Li et al [15] applied a joint model to Chinese POS tagging and dependency parsing using a graph-based model and pruning method. This model showed better accuracy than a state-of-the-art parsing method by approximately 1.5%.…”

“…The proposed model employs a fully tagged corpus (both POS and syntactic) as well as an only POS tagged corpus. Existing studies on such joint models have been limited to only using a fully tagged corpus [15], [16]. Thus, it has been difficult for the joint models to achieve a higher performance than the state-of-the-art POS tagging method on account of the small corpus problem.…”