LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Space

Tasnim Mohiuddin, M Saiful Bari, Shafiq Joty


Abstract
Most of the successful and predominant methods for Bilingual Lexicon Induction (BLI) are mapping-based, where a linear mapping function is learned with the assumption that the word embedding spaces of different languages exhibit similar geometric structures (i.e. approximately isomorphic). However, several recent studies have criticized this simplified assumption showing that it does not hold in general even for closely related languages. In this work, we propose a novel semi-supervised method to learn cross-lingual word embeddings for BLI. Our model is independent of the isomorphic assumption and uses non-linear mapping in the latent space of two independently pre-trained autoencoders. Through extensive experiments on fifteen (15) different language pairs (in both directions) comprising resource-rich and low-resource languages from two different datasets, we demonstrate that our method outperforms existing models by a good margin. Ablation studies show the importance of different model components and the necessity of non-linear mapping.
Anthology ID:
2020.emnlp-main.215
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2712–2723
Language:
URL:
https://aclanthology.org/2020.emnlp-main.215
DOI:
10.18653/v1/2020.emnlp-main.215
Bibkey:
Cite (ACL):
Tasnim Mohiuddin, M Saiful Bari, and Shafiq Joty. 2020. LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Space. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2712–2723, Online. Association for Computational Linguistics.
Cite (Informal):
LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Space (Mohiuddin et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.215.pdf
Video:
 https://slideslive.com/38938789