A Full End-to-End Semantic Role Labeler, Syntactic-agnostic Over Syntactic-aware?

Proceedings of the 27th International Conference on Computational Linguistics, pages 2753–2765 Santa Fe, New Mexico, USA, August 20-26, 2018. 2753 A Full End-to-End Semantic Role Labeler, Syntax-agnostic Over Syntax-aware? Jiaxun Cai1,2, Shexia He1,2, Zuchao Li1,2, Hai Zhao1,2∗ 1Department of Computer Science and Engineering, Shanghai Jiao Tong University 2Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University, Shanghai, China {caijiaxun, heshexia, charlee}@sjtu.edu.cn, zhaohai@cs.sjtu.edu.cn Abstract Semantic role labeling (SRL) is to recognize the predicate-argument structure of a sentence, in- cluding subtasks of predicate disambiguation and argument labeling. Previous studies usually formulate the entire SRL problem into two or more subtasks. For the first time, this paper in- troduces an end-to-end neural model which unifiedly tackles the predicate disambiguation and the argument labeling in one shot. Using a biaffine scorer, our model directly predicts all se- mantic role labels for all given word pairs in the sentence without relying on any syntactic parse information. Specifically, we augment the BiLSTM encoder with a non-linear transformation to further distinguish the predicate and the argument in a given sentence, and model the seman- tic role labeling process as a word pair classification task by employing the biaffine attentional mechanism. Though the proposed model is syntax-agnostic with local decoder, it outperforms the state-of-the-art syntax-aware SRL systems on the CoNLL-2008, 2009 benchmarks for both English and Chinese. To our best knowledge, we report the first syntax-agnostic SRL model that surpasses all known syntax-aware models. 1 Introduction Semantic role labeling (SRL) is a shallow semantic parsing, which is dedicated to identifying the seman- tic arguments of a predicate and labeling them with their semantic roles. SRL is considered as one of the core tasks in the natural language processing (NLP), which has been successfully applied to various downstream tasks, such as information extraction (Bastianelli et al., 2013), question answering (Shen and Lapata, 2007; Berant et al., 2013), machine translation (Xiong et al., 2012; Shi et al., 2016). Typically, SRL task can be put into two categories: constituent-based (i.e., phrase or span) SRL and dependency-based SRL. This paper will focus on the latter one popularized by CoNLL-2008 and 2009 shared tasks (Surdeanu et al., 2008; Hajiˇc et al., 2009). Most conventional SRL systems relied on sophisticated handcraft features or some declarative constraints (Pradhan et al., 2005; Zhao et al., 2009a), which suffers from poor efficiency and generalization ability. A recently tendency for SRL is adopting neural networks methods attributed to their significant success in a wide range of applications (Bai and Zhao, 2018; Zhang and Zhao, 2018). However, most of those works still heavily resort to syntactic features. Since the syntactic parsing task is equally hard as SRL and comes with its own errors, it is better to get rid of such prerequisite as in other NLP tasks. Accordingly, Marcheggiani et al. (2017) presented a neural model putting syntax aside for dependency-based SRL and obtain favorable results, which overturns the inherent belief that syntax is indispensable in SRL task (Punyakanok et al., 2008). …

Content truncated to 500 words