Explicit Sentence Compression for Neural Machine Translation

State-of-the-art Transformer-based neural machine translation (NMT) systems still follow a standard encoder-decoder framework, in which source sentence representation can be well done by an encoder with self-attention mechanism. Though Transformer-based encoder may effectively capture general information in its resulting source sentence representation, the backbone information, which stands for the gist of a sentence, is not specifically focused on. In this paper, we propose an explicit sentence compression method to enhance the source sentence representation for NMT. In practice, an explicit sentence compression goal used to learn the backbone information in a sentence. We propose three ways, including backbone source-side fusion, targetside fusion, and both-side fusion, to integrate the compressed sentence into NMT. Our empirical tests on the WMT Englishto-French and English-to-German translation tasks show that the proposed sentence compression method significantly improves the translation performances over strong baselines.

Authors

• Zuchao Li Wuhan University
• Rui Wang
• Kehai Chen Harbin Institute of Technology (Shenzhen)
• Masao Utiyama National Institute of Information and Communications Technology
• Eiichiro Sumita National Institute of Information and Communications Technology
• Zhuosheng Zhang Shanghai Jiao Tong University
• Hai Zhao Department of Computer Science and Engineering, Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3

Keywords

No keywords are indexed for this paper.