Abstract
Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite to evaluate segmentation strategies on different types of morphological phenomena in a controlled, semi-synthetic setting. In our experiments, we compare how well machine translation models trained on subword- and character-level can translate these morphological phenomena. We find that learning to analyse and generate morphologically complex surface representations is still challenging, especially for non-concatenative morphological phenomena like reduplication or vowel harmony and for rare word stems. Based on our results, we recommend that novel text representation strategies be tested on a range of typologically diverse languages to minimise the risk of adopting a strategy that inadvertently disadvantages certain languages.- Anthology ID:
- 2021.findings-emnlp.60
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 689–705
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.60
- DOI:
- 10.18653/v1/2021.findings-emnlp.60
- Cite (ACL):
- Chantal Amrhein and Rico Sennrich. 2021. How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 689–705, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology? (Amrhein & Sennrich, Findings 2021)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2021.findings-emnlp.60.pdf
- Code
- zurichnlp/segtest