Attention Word Embedding

Shashank Sonkar, Andrew Waters, Richard Baraniuk


Abstract
Word embedding models learn semantically rich vector representations of words and are widely used to initialize natural processing language (NLP) models. The popular continuous bag-of-words (CBOW) model of word2vec learns a vector embedding by masking a given word in a sentence and then using the other words as a context to predict it. A limitation of CBOW is that it equally weights the context words when making a prediction, which is inefficient, since some words have higher predictive value than others. We tackle this inefficiency by introducing the Attention Word Embedding (AWE) model, which integrates the attention mechanism into the CBOW model. We also propose AWE-S, which incorporates subword information. We demonstrate that AWE and AWE-S outperform the state-of-the-art word embedding models both on a variety of word similarity datasets and when used for initialization of NLP models.
Anthology ID:
2020.coling-main.608
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
6894–6902
Language:
URL:
https://aclanthology.org/2020.coling-main.608
DOI:
10.18653/v1/2020.coling-main.608
Bibkey:
Cite (ACL):
Shashank Sonkar, Andrew Waters, and Richard Baraniuk. 2020. Attention Word Embedding. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6894–6902, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Attention Word Embedding (Sonkar et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.608.pdf
Data
SICKSNLI