Peking: Profiling Syntactic Tree Parsing Techniques for Semantic Graph Parsing

Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 459–464, Dublin, Ireland, August 23-24, 2014. Peking: Profiling Syntactic Tree Parsing Techniques for Semantic Graph Parsing Yantao Du, Fan Zhang, Weiwei Sun and Xiaojun Wan Institute of Computer Science and Technology, Peking University The MOE Key Laboratory of Computational Linguistics, Peking University {duyantao,ws,wanxiaojun}@pku.edu.cn, zhangf717@gmail.com Abstract Using the SemEval-2014 Task 8 data, we profile the syntactic tree parsing tech- niques for semantic graph parsing. In par- ticular, we implement different transition- based and graph-based models, as well as a parser ensembler, and evaluate their ef- fectiveness for semantic dependency pars- ing. Evaluation gauges how successful data-driven dependency graph parsing can be by applying existing techniques. 1 Introduction Bi-lexical dependency representation is quite pow- erful and popular to encode syntactic or semantic information, and parsing techniques under the de- pendency formalism have been well studied and advanced in the last decade. The major focus is limited to tree structures, which fortunately corre- spond to many computationally good properties. On the other hand, some leading linguistic theo- ries argue that more general graphs are needed to encode a wide variety of deep syntactic and se- mantic phenomena, e.g. topicalization, relative clauses, etc. However, algorithms for statistical graph spanning have not been well explored be- fore, and therefore it is not very clear how good data-driven parsing techniques developed for tree parsing can be for graph generating. Following several well-established syntactic theories, SemEval-2014 task 8 (Oepen et al., 2014) proposes using graphs to represent seman- tics. Considering that semantic dependency pars- ing is a quite new topic and there is little previ- ous work, we think it worth appropriately profil- ing successful tree parsing techniques for graph parsing. To this end, we build a hybrid system This work is licenced under a Creative Commons Attribution 4.0 International License. Page numbers and proceedings footer are added by the organizers. License details: http: //creativecommons.org/licenses/by/4.0/ that combines several important data-driven pars- ing techniques and evaluate their impact with the given data. In particular, we implement different transition-based and graph-based models, as well as a parser ensembler. Our experiments highlight the following facts: • Graph-based models are more effective than transition-based models. • Parser ensemble is very useful to boost the parsing accuracy. 2 Architecture We explore two kinds of basic models: One is transition-based, and the other is tree approxima- tion. Transition-based models are widely used for dependency tree parsing, and they can be adapted to graph parsing (Sagae and Tsujii, 2008; Titov et al., 2009). Here we implement 5 transition- based models for dependency graph parsing, each of which is based on different transition system. The motivation of developing tree approxima- tion models is to apply existing graph-based tree parsers to generate graphs. At the training time, we convert the dependency graphs from the train- ing data into dependency trees, and train second- order arc-factored models1. At the test phase, we parse sentences using this tree parser, and convert the output trees back into …

Content truncated to 500 words