How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?

Chantal Amrhein, Rico Sennrich


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
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
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
Bibkey:
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)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.60.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.60.mp4
Code
 zurichnlp/segtest