# One Sense per Translation

arXiv: https://arxiv.org/abs/2106.06082 · HTML: https://mlsanity.com/paper/2106.06082/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 78 references that are in the map.
- First posted on arXiv 10 Jun 2021.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Exploiting Similarities among Languages for Machine Translation](https://mlsanity.com/paper/1309.4168/) (2013)
- [Moving Down the Long Tail of Word Sense Disambiguation with Gloss-Informed Biencoders](https://mlsanity.com/paper/2005.02590/) (2020)
- [Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation](https://mlsanity.com/paper/1906.10007/) (2019)
- [Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations](https://mlsanity.com/paper/1910.00194/) (2019)
- [LMMS Reloaded: Transformer-based Sense Embeddings for Disambiguation and Beyond](https://mlsanity.com/paper/2105.12449/) (2021)
- [FEWS: Large-Scale, Low-Shot Word Sense Disambiguation with the Dictionary](https://mlsanity.com/paper/2102.07983/) (2021)
- [Handling Homographs in Neural Machine Translation](https://mlsanity.com/paper/1708.06510/) (2017)
- [Don't Neglect the Obvious: On the Role of Unambiguous Words in Word Sense Disambiguation](https://mlsanity.com/paper/2004.14325/) (2020)
- [One Homonym per Translation](https://mlsanity.com/paper/1904.08533/) (2019)
- [Synonymy = Translational Equivalence](https://mlsanity.com/paper/2004.13886/) (2020)

## Abstract (arXiv)

Word sense disambiguation (WSD) is the task of determining the sense of a word in context. Translations have been used in WSD as a source of knowledge, and even as a means of delimiting word senses. In this paper, we define three theoretical properties of the relationship between senses and translations, and argue that they constitute necessary conditions for using translations as sense inventories. The key property of One Sense per Translation (OSPT) provides a foundation for a translation-based WSD method. The results of an intrinsic evaluation experiment indicate that our method achieves a precision of approximately 93% compared to manual corpus annotations. Our extrinsic evaluation experiments demonstrate WSD improvements of up to 4.6% F1-score on difficult WSD datasets.