Abstract / Description of output
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.
Original language | English |
---|---|
Title of host publication | Proceedings of the First Workshop on Insights from Negative Results in NLP |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 117-125 |
Number of pages | 9 |
ISBN (Electronic) | 978-1-952148-66-8 |
Publication status | Published - 19 Nov 2020 |
Event | Workshop on Insights from Negative Results in NLP - Virtual event Duration: 19 Nov 2020 → 19 Nov 2020 https://insights-workshop.github.io/index |
Workshop
Workshop | Workshop on Insights from Negative Results in NLP |
---|---|
Abbreviated title | INSIGHTS 2020 |
City | Virtual event |
Period | 19/11/20 → 19/11/20 |
Internet address |