Online Back-Parsing for AMR-to-Text Generation

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 1206–1219, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 1206 Online Back-Parsing for AMR-to-Text Generation Xuefeng Bai♠♥ , Linfeng Song♣ , Yue Zhang♥♦ ♠ Zhejiang University, China ♥School of Engineering, Westlake University, China ♣ Tencent AI Lab, Bellevue, WA, USA ♦Institute of Advanced Technology, Westlake Institute for Advanced Study, China Abstract AMR-to-text generation aims to recover a text containing the same meaning as an input AMR graph. Current research develops increasingly powerful graph encoders to better represent AMR graphs, with decoders based on standard language modeling being used to generate outputs. We propose a decoder that back predicts projected AMR graphs on the target sentence during text generation. As the result, our outputs can better preserve the input meaning than standard decoders. Experiments on two AMR benchmarks show the superiority of our model over the previous state-of-the-art system based on graph Transformer. 1 Introduction Abstract meaning representation (AMR) (Ba- narescu et al., 2013) is a semantic graph representation that abstracts meaning away from a sentence. Figure 1 shows an AMR graph, where the nodes, such as “possible-01” and “police”, represent concepts, and the edges, such as “ARG0” and “ARG1”, indicate relations between the concepts they connect. The task of AMR- to-text generation (Konstas et al., 2017) aims to produce fluent sentences that convey consistent meaning with input AMR graphs. For example, taking the AMR in Figure 1 as input, a model can produce the sentence “The police could help the victim”. AMR-to-text generation has been shown useful for many applications such as machine translation (Song et al., 2019) and summarization (Liu et al., 2015; Yasunaga et al., 2017; Liao et al., 2018; Hardy and Vlachos, 2018). In addition, AMR-to-text generation can be a good test bed for general graph-to-sequence problems (Belz et al., 2011; Gardent et al., 2017). AMR-to-text generation has attracted increasing research attention recently. Previous work has focused on developing effective encoders for Figure 1: An example AMR graph meaning “The police could help the victim.” representing graphs. In particular, graph neural networks (Beck et al., 2018; Song et al., 2018; Guo et al., 2019) and richer graph representations (Damonte and Cohen, 2019; Hajdik et al., 2019; Ribeiro et al., 2019) have been shown to give better performances than RNN-based models (Konstas et al., 2017) on linearized graphs. Subsequent work exploited graph Transformer (Zhu et al., 2019; Cai and Lam, 2020; Wang et al., 2020), achieving better performances by directly modeling the intercorrelations between distant node pairs with relation-aware global communication. Despite the progress on the encoder side, the current state- of-the-art models use a rather standard decoder: it functions as a language model, where each word is generated given only the previous words. As a result, one limitation of such decoders is that they tend to produce fluent sentences that may not retain the meaning of input AMRs. We investigate enhancing AMR-to-text decoding by integrating online back-parsing, simultaneously predicting a projected AMR graph on …

Content truncated to 500 words