Abstract
Recent years have seen exceptional strides in the task of automatic morphological inflection generation. However, for a long tail of languages the necessary resources are hard to come by, and state-of-the-art neural methods that work well under higher resource settings perform poorly in the face of a paucity of data. In response, we propose a battery of improvements that greatly improve performance under such low-resource conditions. First, we present a novel two-step attention architecture for the inflection decoder. In addition, we investigate the effects of cross-lingual transfer from single and multiple languages, as well as monolingual data hallucination. The macro-averaged accuracy of our models outperforms the state-of-the-art by 15 percentage points. Also, we identify the crucial factors for success with cross-lingual transfer for morphological inflection: typological similarity and a common representation across languages.- Anthology ID:
- D19-1091
- Volume:
- Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Editors:
- Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
- Venues:
- EMNLP | IJCNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 984–996
- Language:
- URL:
- https://aclanthology.org/D19-1091
- DOI:
- 10.18653/v1/D19-1091
- Cite (ACL):
- Antonios Anastasopoulos and Graham Neubig. 2019. Pushing the Limits of Low-Resource Morphological Inflection. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 984–996, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Pushing the Limits of Low-Resource Morphological Inflection (Anastasopoulos & Neubig, EMNLP-IJCNLP 2019)
- PDF:
- https://preview.aclanthology.org/naacl24-info/D19-1091.pdf
- Code
- antonisa/inflection + additional community code