# Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation

arXiv: https://arxiv.org/abs/1810.02614 · HTML: https://mlsanity.com/paper/1810.02614/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2018.

## Built on by (most cited first, 7 of 7)

- [Subword Mapping and Anchoring across Languages](https://mlsanity.com/paper/2109.04556/) (2021)
- [Towards Effective Disambiguation for Machine Translation with Large Language Models](https://mlsanity.com/paper/2309.11668/) (2023)
- [Multilingual Word Sense Disambiguation with Unified Sense Representation](https://mlsanity.com/paper/2210.07447/) (2022)
- [Code-Switching with Word Senses for Pretraining in Neural Machine Translation](https://mlsanity.com/paper/2310.14050/) (2023)
- [Improving Word Sense Disambiguation in Neural Machine Translation with Salient Document Context](https://mlsanity.com/paper/2311.15507/) (2023)
- [Representation of professions in entertainment media: Insights into frequency and sentiment trends through computational text analysis](https://mlsanity.com/paper/2110.03873/) (2021)
- [Learning Homographic Disambiguation Representation for Neural Machine Translation](https://mlsanity.com/paper/2304.05860/) (2023)

## Abstract (arXiv)

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.