Crosslingual Transfer Learning for Low-Resource Languages Based on Multilingual Colexification Graphs
Yihong Liu, Haotian Ye, Leonie Weissweiler, Renhao Pei, Hinrich Schuetze
Abstract
In comparative linguistics, colexification refers to the phenomenon of a lexical form conveying two or more distinct meanings. Existing work on colexification patterns relies on annotated word lists, limiting scalability and usefulness in NLP. In contrast, we identify colexification patterns of more than 2,000 concepts across 1,335 languages directly from an unannotated parallel corpus. We then propose simple and effective methods to build multilingual graphs from the colexification patterns: ColexNet and ColexNet+. ColexNet’s nodes are concepts and its edges are colexifications. In ColexNet+, concept nodes are additionally linked through intermediate nodes, each representing an ngram in one of 1,334 languages. We use ColexNet+ to train \overrightarrow{\mbox{ColexNet+}}, high-quality multilingual embeddings that are well-suited for transfer learning. In our experiments, we first show that ColexNet achieves high recall on CLICS, a dataset of crosslingual colexifications. We then evaluate \overrightarrow{\mbox{ColexNet+}} on roundtrip translation, sentence retrieval and sentence classification and show that our embeddings surpass several transfer learning baselines. This demonstrates the benefits of using colexification as a source of information in multilingual NLP.- Anthology ID:
- 2023.findings-emnlp.562
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8376–8401
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.562
- DOI:
- 10.18653/v1/2023.findings-emnlp.562
- Cite (ACL):
- Yihong Liu, Haotian Ye, Leonie Weissweiler, Renhao Pei, and Hinrich Schuetze. 2023. Crosslingual Transfer Learning for Low-Resource Languages Based on Multilingual Colexification Graphs. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8376–8401, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Crosslingual Transfer Learning for Low-Resource Languages Based on Multilingual Colexification Graphs (Liu et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/ingest-2024-clasp/2023.findings-emnlp.562.pdf