Aligning Vector-spaces with Noisy Supervised Lexicon

Noa Yehezkel Lubin, Jacob Goldberger, Yoav Goldberg


Abstract
The problem of learning to translate between two vector spaces given a set of aligned points arises in several application areas of NLP. Current solutions assume that the lexicon which defines the alignment pairs is noise-free. We consider the case where the set of aligned points is allowed to contain an amount of noise, in the form of incorrect lexicon pairs and show that this arises in practice by analyzing the edited dictionaries after the cleaning process. We demonstrate that such noise substantially degrades the accuracy of the learned translation when using current methods. We propose a model that accounts for noisy pairs. This is achieved by introducing a generative model with a compatible iterative EM algorithm. The algorithm jointly learns the noise level in the lexicon, finds the set of noisy pairs, and learns the mapping between the spaces. We demonstrate the effectiveness of our proposed algorithm on two alignment problems: bilingual word embedding translation, and mapping between diachronic embedding spaces for recovering the semantic shifts of words across time periods.
Anthology ID:
N19-1045
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
460–465
Language:
URL:
https://aclanthology.org/N19-1045
DOI:
10.18653/v1/N19-1045
Bibkey:
Cite (ACL):
Noa Yehezkel Lubin, Jacob Goldberger, and Yoav Goldberg. 2019. Aligning Vector-spaces with Noisy Supervised Lexicon. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 460–465, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Aligning Vector-spaces with Noisy Supervised Lexicon (Yehezkel Lubin et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1045.pdf
Code
 NoaKel/Noise-Aware-Alignment