Embedding Structured Dictionary Entries

Steven Wilson, Walid Magdy, Barbara McGillivray, Gareth Tyson


Abstract
Previous work has shown how to effectively use external resources such as dictionaries to improve English-language word embeddings, either by manipulating the training process or by applying post-hoc adjustments to the embedding space. We experiment with a multi-task learning approach for explicitly incorporating the structured elements of dictionary entries, such as user-assigned tags and usage examples, when learning embeddings for dictionary headwords. Our work generalizes several existing models for learning word embeddings from dictionaries. However, we find that the most effective representations overall are learned by simply training with a skip-gram objective over the concatenated text of all entries in the dictionary, giving no particular focus to the structure of the entries.
Anthology ID:
2020.insights-1.18
Volume:
Proceedings of the First Workshop on Insights from Negative Results in NLP
Month:
November
Year:
2020
Address:
Online
Editors:
Anna Rogers, João Sedoc, Anna Rumshisky
Venue:
insights
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
117–125
Language:
URL:
https://aclanthology.org/2020.insights-1.18
DOI:
10.18653/v1/2020.insights-1.18
Bibkey:
Cite (ACL):
Steven Wilson, Walid Magdy, Barbara McGillivray, and Gareth Tyson. 2020. Embedding Structured Dictionary Entries. In Proceedings of the First Workshop on Insights from Negative Results in NLP, pages 117–125, Online. Association for Computational Linguistics.
Cite (Informal):
Embedding Structured Dictionary Entries (Wilson et al., insights 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.insights-1.18.pdf
Video:
 https://slideslive.com/38940805