Semantic Role Labeling with Heterogeneous Syntactic Knowledge

Proceedings of the 28th International Conference on Computational Linguistics, pages 2979–2990 Barcelona, Spain (Online), December 8-13, 2020 2979 Semantic Role Labeling with Heterogeneous Syntactic Knowledge Qingrong Xia1, Rui Wang2, Zhenghua Li1, Yue Zhang2, Min Zhang1∗ 1Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, China 2Alibaba Group 1kirosummer.nlp@gmail.com, {zhli13, minzhang}@suda.edu.cn 2{masi.wr, shiyu.zy}@alibaba-inc.com Abstract Recently, due to the interplay between syntax and semantics, incorporating syntactic knowledge into neural semantic role labeling (SRL) has achieved much attention. Most of the previous syntax-aware SRL works focus on explicitly modeling homogeneous syntactic knowledge over tree outputs. In this work, we propose to encode heterogeneous syntactic knowledge for SRL from both explicit and implicit representations. First, we introduce graph convolutional net- works to explicitly encode multiple heterogeneous dependency parse trees. Second, we extract the implicit syntactic representations from syntactic parser trained with heterogeneous treebanks. Finally, we inject the two types of heterogeneous syntax-aware representations into the base SRL model as extra inputs. We conduct experiments on two widely-used benchmark datasets, i.e., Chinese Proposition Bank 1.0 and English CoNLL-2005 dataset. Experimental results show that incorporating heterogeneous syntactic knowledge brings significant improvements over strong baselines. We further conduct detailed analysis to gain insights on the usefulness of heteroge- neous (vs. homogeneous) syntactic knowledge and the effectiveness of our proposed approaches for modeling such knowledge. 1 Introduction Semantic role labeling (SRL) is a fundamental task in natural language processing (NLP), which aims to find the predicate argument structures (Who did what to whom, when and where, etc.) in a sentence (see Figure 1 as an example). Recent SRL works can mostly be divided into two categories, i.e., syntax-aware (Roth and Lapata, 2016; He et al., 2018b; Strubell et al., 2018) and syntax-agnostic (He et al., 2017; He et al., 2018a) approaches according to whether incorporating syntactic knowledge or not. Most syntax-agnostic works employ deep BiLSTM or self-attention encoder to encode the contextual information of natural sentences, with various kinds of scorers to predict the probabilities of BIO-based semantic roles (He et al., 2017; Tan et al., 2018) or predicate-argument-role tuples (He et al., 2018a; Li et al., 2019). Motivated by the strong interplay between syntax and semantics, researchers explore various approaches to integrate syntactic knowledge into syntax-agnostic models. Roth and Lapata (2016) pro- pose to use dependency-based embeddings in a neural SRL model for dependency-based SRL. He et al. (2018b) introduce k-order pruning algorithm to prune arguments according to dependency trees. How- ever, previous syntax-aware works mainly employ singleton/homogeneous automatic dependency trees, which are generated by a syntactic parser trained on a specific syntactic treebank, like Penn Treebank (PTB) (Marcus et al., 1994). Our work follows the syntax-aware approach and enhances SRL with heterogeneous syntactic knowl- edge. We define heterogeneous syntactic treebanks as treebanks that follow different annotation guide- lines. All is well known, there exist many published dependency treebanks that follow different anno- tation guidelines, i.e., English PTB (Marcus et al., 1994), Universal Dependencies (UD) (Silveira et al., 2014), Penn Chinese Treebank (PCTB) (Xue …

Content truncated to 500 words