# Handling Homographs in Neural Machine Translation

arXiv: https://arxiv.org/abs/1708.06510 · HTML: https://mlsanity.com/paper/1708.06510/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Aug 2017.

## Built on by (most cited first, 11 of 11)

- [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)
- [A Survey on Semantic Processing Techniques](https://mlsanity.com/paper/2310.18345/) (2023)
- [DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translation](https://mlsanity.com/paper/2504.20371/) (2025)
- [Translate to Disambiguate: Zero-shot Multilingual Word Sense Disambiguation with Pretrained Language Models](https://mlsanity.com/paper/2304.13803/) (2023)
- [Improving Word Sense Disambiguation in Neural Machine Translation with Salient Document Context](https://mlsanity.com/paper/2311.15507/) (2023)
- [Word Sense Linking: Disambiguating Outside the Sandbox](https://mlsanity.com/paper/2412.09370/) (2024)
- [One Sense per Translation](https://mlsanity.com/paper/2106.06082/) (2021)
- [From Pivots to Graphs: Augmented CycleDensity as a Generalization to One Time InverseConsultation](https://mlsanity.com/paper/2108.12459/) (2021)
- [Learning Homographic Disambiguation Representation for Neural Machine Translation](https://mlsanity.com/paper/2304.05860/) (2023)

## Abstract (arXiv)

Homographs, words with different meanings but the same surface form, have long caused difficulty for machine translation systems, as it is difficult to select the correct translation based on the context. However, with the advent of neural machine translation (NMT) systems, which can theoretically take into account global sentential context, one may hypothesize that this problem has been alleviated. In this paper, we first provide empirical evidence that existing NMT systems in fact still have significant problems in properly translating ambiguous words. We then proceed to describe methods, inspired by the word sense disambiguation literature, that model the context of the input word with context-aware word embeddings that help to differentiate the word sense be- fore feeding it into the encoder. Experiments on three language pairs demonstrate that such models improve the performance of NMT systems both in terms of BLEU score and in the accuracy of translating homographs.