Making Better Use of Bilingual Information for Cross-Lingual AMR Parsing

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1537–1547 August 1–6, 2021. ©2021 Association for Computational Linguistics 1537 Making Better Use of Bilingual Information for Cross-Lingual AMR Parsing Yitao Cai, Zhe Lin and Xiaojun Wan Wangxuan Institute of Computer Technology, Peking University Center for Data Science, Peking University The MOE Key Laboratory of Computational Linguistics, Peking University {caiyitao,linzhe,wanxiaojun}@pku.edu.cn Abstract Abstract Meaning Representation (AMR) is a rooted, labeled, acyclic graph representing the semantics of natural language. As previous works show, although AMR is designed for En- glish at first, it can also represent semantics in other languages. However, they find that con- cepts in their predicted AMR graphs are less specific. We argue that the misprediction of concepts is due to the high relevance between English tokens and AMR concepts. In this work, we introduce bilingual input, namely the translated texts as well as non-English texts, in order to enable the model to predict more ac- curate concepts. Besides, we also introduce an auxiliary task, requiring the decoder to predict the English sequences at the same time. The auxiliary task can help the decoder understand what exactly the corresponding English tokens are. Our proposed cross-lingual AMR parser surpasses previous state-of-the-art parser by 10.6 points on Smatch F1 score. The ablation study also demonstrates the efficacy of our pro- posed modules. 1 Introduction Abstract Meaning Representation (AMR) (Ba- narescu et al., 2013) is a rooted, labeled, acyclic graph representing sentence-level semantic of text. Nodes in the graph are concepts in the texts and edges in the graph are relations between concepts. Since AMR abstracts away from syntax and pre- serves only semantic information, it can be applied to many semantic related tasks such as summariza- tion (Liu et al., 2015; Liao et al., 2018), paraphrase detection (Issa et al., 2018), machine translation (Song et al., 2019) and so on. Previous works on AMR parsing mainly focus on English, since AMR is designed for English texts and parallel corpus of non-English texts and AMRs are scarce. Early work of AMR announces that AMR is biased towards English and is not an interlingua (Banarescu et al., 2013). Besides, some studies show that aligning AMR with non- English language is not always possible (Xue et al., 2014; Hajic et al., 2014). However, recent stud- ies (Damonte and Cohen, 2018; Blloshmi et al., 2020) show that AMR parsers are able to recover AMR structures when there are structural differ- ences between languages, which demonstrate that it is capable to overcome many translation diver- gences. Therefore, it is possible for us to parse texts in target (non-English) languages into AMRs. Another problem of cross-lingual AMR parsing is the scarcity of parallel corpus. Unlike machine translation or sentiment classification which have abundant resources on the Internet, we can only get non-English text and AMR pairs by human annotation. Damonte and Cohen (2018) align a non-English token with an AMR node if they can be mapped to the same English token to construct training set. They further …

Content truncated to 500 words