Specializing Word Embeddings (for Parsing) by Information Bottleneck

Xiang Lisa Li, Jason Eisner


Abstract
Pre-trained word embeddings like ELMo and BERT contain rich syntactic and semantic information, resulting in state-of-the-art performance on various tasks. We propose a very fast variational information bottleneck (VIB) method to nonlinearly compress these embeddings, keeping only the information that helps a discriminative parser. We compress each word embedding to either a discrete tag or a continuous vector. In the discrete version, our automatically compressed tags form an alternative tag set: we show experimentally that our tags capture most of the information in traditional POS tag annotations, but our tag sequences can be parsed more accurately at the same level of tag granularity. In the continuous version, we show experimentally that moderately compressing the word embeddings by our method yields a more accurate parser in 8 of 9 languages, unlike simple dimensionality reduction.
Anthology ID:
D19-1276
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2744–2754
Language:
URL:
https://aclanthology.org/D19-1276
DOI:
10.18653/v1/D19-1276
Award:
 Best Paper
Bibkey:
Cite (ACL):
Xiang Lisa Li and Jason Eisner. 2019. Specializing Word Embeddings (for Parsing) by Information Bottleneck. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2744–2754, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Specializing Word Embeddings (for Parsing) by Information Bottleneck (Li & Eisner, EMNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/D19-1276.pdf
Attachment:
 D19-1276.Attachment.pdf