Effective Graph Context Representation for Document-level Machine Translation

Effective Graph Context Representation for Document-level Machine Translation

Kehai Chen, Muyun Yang, Masao Utiyama, Eiichiro Sumita, Rui Wang, Min Zhang

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Main Track. Pages 4079-4085. https://doi.org/10.24963/ijcai.2022/566

Document-level neural machine translation (DocNMT) universally encodes several local sentences or the entire document. Thus, DocNMT does not consider the relevance of document-level contextual information, for example, some context (i.e., content words, logical order, and co-occurrence relation) is more effective than another auxiliary context (i.e., functional and auxiliary words). To address this issue, we first utilize the word frequency information to recognize content words in the input document, and then use heuristical relations to summarize content words and sentences as a graph structure without relying on external syntactic knowledge. Furthermore, we apply graph attention networks to this graph structure to learn its feature representation, which allows DocNMT to more effectively capture the document-level context. Experimental results on several widely-used document-level benchmarks demonstrated the effectiveness of the proposed approach.
Keywords:
Natural Language Processing: Machine Translation and Multilinguality
Natural Language Processing: Language Generation