Document Type

Conference Paper

Publication Date

2023

DOI

10.18653/v1/2023.findings-emnlp.721

Publication Title

Findings of the Association for Computational Linguistics: EMNLP 2023

Pages

10763-10775

Conference Name

The 2023 Conference on Empirical Methods in Natural Language Processing, December 6-10, 2023, Singapore

Abstract

Bilingual lexicon induction (BLI) is the task of inducing word translations with a learned mapping function that aligns monolingual word embedding spaces in two different languages. However, most previous methods treat word embeddings as isolated entities and fail to jointly consider both the intra-space and inter-space topological relations between words. This limitation makes it challenging to align words from embedding spaces with distinct topological structures, especially when the assumption of isomorphism may not hold. To this end, we propose a novel approach called the Structure-Aware Generative Adversarial Network (SA-GAN) model to explicitly capture multiple topological structure information to achieve accurate BLI. Our model first incorporates two lightweight graph convolutional networks (GCNs) to leverage intra-space topological correlations between words for generating source and target embeddings. We then employ a GAN model to explore inter-space topological structures by learning a global mapping function that initially maps the source embeddings to the target embedding space. To further align the coarse-grained structures, we develop a pair-wised local mapping (PLM) strategy that enables word-specific transformations in an unsupervised manner. Extensive experiments conducted on public datasets, including languages with both distant and close etymological relationships, demonstrate the effectiveness of our proposed SA-GAN model.

Comments

Bibliographic information:

ISBN: 979-8-89176-061-5

Editors: Houda Bouamor, Juan Pino, Kalika Bali.

Rights

© 2023 Association for Computational Linguistics.

Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International (CC BY 4.0) License.

Original Publication Citation

Han, B., Tao, Q., Li, L., & Xiong, Z. (2023). A Structure-Aware Generative Adversarial Network for bilingual lexicon induction. In H. Bouamor, J. Pino, & K. Bali (Eds), Findings of the Association for Computational Linguistics: EMNLP 2023 (pp. 10763-10775). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.findings-emnlp.721

Download

Share

COinS