Selective Attention for Context-aware Neural Machine Translation
This work addresses the challenge of document-level translation for machine translation systems, offering a scalable solution to improve fluency and quality, though it is incremental in nature.
The authors tackled the problem of achieving fluent, high-quality document-level neural machine translation by proposing a scalable hierarchical attention approach that selectively focuses on relevant sentences and words in the context. Their method significantly outperformed context-agnostic and context-aware baselines in English-German translation experiments.
Despite the progress made in sentence-level NMT, current systems still fall short at achieving fluent, good quality translation for a full document. Recent works in context-aware NMT consider only a few previous sentences as context and may not scale to entire documents. To this end, we propose a novel and scalable top-down approach to hierarchical attention for context-aware NMT which uses sparse attention to selectively focus on relevant sentences in the document context and then attends to key words in those sentences. We also propose single-level attention approaches based on sentence or word-level information in the context. The document-level context representation, produced from these attention modules, is integrated into the encoder or decoder of the Transformer model depending on whether we use monolingual or bilingual context. Our experiments and evaluation on English-German datasets in different document MT settings show that our selective attention approach not only significantly outperforms context-agnostic baselines but also surpasses context-aware baselines in most cases.