Abstract
Recent works on cross-lingual word embeddings have been mainly focused on linear-mapping-based approaches, where pre-trained word embeddings are mapped into a shared vector space using a linear transformation. However, there is a limitation in such approaches–they follow a key assumption: words with similar meanings share similar geometric arrangements between their monolingual word embeddings, which suggest that there is a linear relationship between languages. However, such assumption may not hold for all language pairs across all semantic concepts. We investigate whether non-linear mappings can better describe the relationship between different languages by utilising kernel Canonical Correlation Analysis (KCCA). Experimental results on five language pairs show an improvement over current state-of-art results in both supervised and self-learning scenarios, confirming that non-linear mapping is a better way to describe the relationship between languages.- Anthology ID:
- 2020.lrec-1.440
- Volume:
- Proceedings of the Twelfth Language Resources and Evaluation Conference
- Month:
- May
- Year:
- 2020
- Address:
- Marseille, France
- Venue:
- LREC
- SIG:
- Publisher:
- European Language Resources Association
- Note:
- Pages:
- 3583–3589
- Language:
- English
- URL:
- https://aclanthology.org/2020.lrec-1.440
- DOI:
- Cite (ACL):
- Jiawei Zhao and Andrew Gilman. 2020. Non-Linearity in Mapping Based Cross-Lingual Word Embeddings. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 3583–3589, Marseille, France. European Language Resources Association.
- Cite (Informal):
- Non-Linearity in Mapping Based Cross-Lingual Word Embeddings (Zhao & Gilman, LREC 2020)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2020.lrec-1.440.pdf