Abstract
In this paper we present an approach for training verb subatom embeddings. For each verb we learn several embeddings rather than only one. These embeddings include the verb itself as well as embeddings for each grammatical role of this verb. To give an example, for the verb ‘to give’ we learn four embeddings: one for the lemma ‘give’, one for the subject, one for the direct object and one for the indirect object. We have exploited these grammatical role embeddings in order to add new syntagmatic relations to WordNet. The evaluation of the new relations quality has been done extrinsically through the Knowledge-based Word Sense Disambiguation task.- Anthology ID:
- 2018.gwc-1.33
- Volume:
- Proceedings of the 9th Global Wordnet Conference
- Month:
- January
- Year:
- 2018
- Address:
- Nanyang Technological University (NTU), Singapore
- Editors:
- Francis Bond, Piek Vossen, Christiane Fellbaum
- Venue:
- GWC
- SIG:
- SIGLEX
- Publisher:
- Global Wordnet Association
- Note:
- Pages:
- 284–292
- Language:
- URL:
- https://aclanthology.org/2018.gwc-1.33
- DOI:
- Cite (ACL):
- Kiril Simov, Alexander Popov, Iliana Simova, and Petya Osenova. 2018. Grammatical Role Embeddings for Enhancements of Relation Density in the Princeton WordNet. In Proceedings of the 9th Global Wordnet Conference, pages 284–292, Nanyang Technological University (NTU), Singapore. Global Wordnet Association.
- Cite (Informal):
- Grammatical Role Embeddings for Enhancements of Relation Density in the Princeton WordNet (Simov et al., GWC 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2018.gwc-1.33.pdf