Abstract
We introduce a method for embedding words as probability densities in a low-dimensional space. Rather than assuming that a word embedding is fixed across the entire text collection, as in standard word embedding methods, in our Bayesian model we generate it from a word-specific prior density for each occurrence of a given word. Intuitively, for each word, the prior density encodes the distribution of its potential ‘meanings’. These prior densities are conceptually similar to Gaussian embeddings of ėwcitevilnis2014word. Interestingly, unlike the Gaussian embeddings, we can also obtain context-specific densities: they encode uncertainty about the sense of a word given its context and correspond to the approximate posterior distributions within our model. The context-dependent densities have many potential applications: for example, we show that they can be directly used in the lexical substitution task. We describe an effective estimation method based on the variational autoencoding framework. We demonstrate the effectiveness of our embedding technique on a range of standard benchmarks.- Anthology ID:
- C18-1151
- 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:
- 1775–1789
- Language:
- URL:
- https://aclanthology.org/C18-1151
- DOI:
- Cite (ACL):
- Arthur Bražinskas, Serhii Havrylov, and Ivan Titov. 2018. Embedding Words as Distributions with a Bayesian Skip-gram Model. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1775–1789, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
- Cite (Informal):
- Embedding Words as Distributions with a Bayesian Skip-gram Model (Bražinskas et al., COLING 2018)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/C18-1151.pdf
- Code
- ixlan/BSG