Analytical Methods for Interpretable Ultradense Word Embeddings

Philipp Dufter, Hinrich Schütze


Abstract
Word embeddings are useful for a wide variety of tasks, but they lack interpretability. By rotating word spaces, interpretable dimensions can be identified while preserving the information contained in the embeddings without any loss. In this work, we investigate three methods for making word spaces interpretable by rotation: Densifier (Rothe et al., 2016), linear SVMs and DensRay, a new method we propose. In contrast to Densifier, DensRay can be computed in closed form, is hyperparameter-free and thus more robust than Densifier. We evaluate the three methods on lexicon induction and set-based word analogy. In addition we provide qualitative insights as to how interpretable word spaces can be used for removing gender bias from embeddings.
Anthology ID:
D19-1111
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
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1185–1191
Language:
URL:
https://aclanthology.org/D19-1111
DOI:
10.18653/v1/D19-1111
Bibkey:
Cite (ACL):
Philipp Dufter and Hinrich Schütze. 2019. Analytical Methods for Interpretable Ultradense Word Embeddings. 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 1185–1191, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Analytical Methods for Interpretable Ultradense Word Embeddings (Dufter & Schütze, EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/D19-1111.pdf
Attachment:
 D19-1111.Attachment.pdf
Code
 pdufter/densray