Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation
This addresses translation quality issues for users of NMT systems by enhancing sense disambiguation, though it is incremental as it builds on existing WSD and NMT methods.
The paper tackles the problem of ambiguous words in neural machine translation by integrating weakly supervised word sense disambiguation, resulting in improvements of over one BLEU point on five language pairs and up to +20% accuracy for challenging words.
This paper demonstrates that word sense disambiguation (WSD) can improve neural machine translation (NMT) by widening the source context considered when modeling the senses of potentially ambiguous words. We first introduce three adaptive clustering algorithms for WSD, based on k-means, Chinese restaurant processes, and random walks, which are then applied to large word contexts represented in a low-rank space and evaluated on SemEval shared-task data. We then learn word vectors jointly with sense vectors defined by our best WSD method, within a state-of-the-art NMT system. We show that the concatenation of these vectors, and the use of a sense selection mechanism based on the weighted average of sense vectors, outperforms several baselines including sense-aware ones. This is demonstrated by translation on five language pairs. The improvements are above one BLEU point over strong NMT baselines, +4% accuracy over all ambiguous nouns and verbs, or +20% when scored manually over several challenging words.