One Sense per Translation
This work addresses word sense disambiguation for natural language processing, offering a novel theoretical foundation and method, but it is incremental as it builds on existing translation-based approaches.
The paper tackled the problem of using translations for word sense disambiguation by defining theoretical properties, including One Sense per Translation, and developed a method that achieved 93% precision in intrinsic evaluation and up to 4.6% F1-score improvement in extrinsic tests.
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.