Best of Both Worlds: Making Word Sense Embeddings Interpretable

Alexander Panchenko


Abstract
Word sense embeddings represent a word sense as a low-dimensional numeric vector. While this representation is potentially useful for NLP applications, its interpretability is inherently limited. We propose a simple technique that improves interpretability of sense vectors by mapping them to synsets of a lexical resource. Our experiments with AdaGram sense embeddings and BabelNet synsets show that it is possible to retrieve synsets that correspond to automatically learned sense vectors with Precision of 0.87, Recall of 0.42 and AUC of 0.78.
Anthology ID:
L16-1421
Volume:
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)
Month:
May
Year:
2016
Address:
Portorož, Slovenia
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Sara Goggi, Marko Grobelnik, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
2649–2655
Language:
URL:
https://aclanthology.org/L16-1421
DOI:
Bibkey:
Cite (ACL):
Alexander Panchenko. 2016. Best of Both Worlds: Making Word Sense Embeddings Interpretable. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 2649–2655, Portorož, Slovenia. European Language Resources Association (ELRA).
Cite (Informal):
Best of Both Worlds: Making Word Sense Embeddings Interpretable (Panchenko, LREC 2016)
Copy Citation:
PDF:
https://aclanthology.org/L16-1421.pdf