Abstract
Given a set of instances of some relation, the relation induction task is to predict which other word pairs are likely to be related in the same way. While it is natural to use word embeddings for this task, standard approaches based on vector translations turn out to perform poorly. To address this issue, we propose two probabilistic relation induction models. The first model is based on translations, but uses Gaussians to explicitly model the variability of these translations and to encode soft constraints on the source and target words that may be chosen. In the second model, we use Bayesian linear regression to encode the assumption that there is a linear relationship between the vector representations of related words, which is considerably weaker than the assumption underlying translation based models.- Anthology ID:
- C18-1138
- Volume:
- Proceedings of the 27th International Conference on Computational Linguistics
- Month:
- August
- Year:
- 2018
- Address:
- Santa Fe, New Mexico, USA
- Editors:
- Emily M. Bender, Leon Derczynski, Pierre Isabelle
- Venue:
- COLING
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1627–1637
- Language:
- URL:
- https://aclanthology.org/C18-1138
- DOI:
- Cite (ACL):
- Zied Bouraoui, Shoaib Jameel, and Steven Schockaert. 2018. Relation Induction in Word Embeddings Revisited. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1627–1637, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
- Cite (Informal):
- Relation Induction in Word Embeddings Revisited (Bouraoui et al., COLING 2018)
- PDF:
- https://preview.aclanthology.org/naacl24-info/C18-1138.pdf