Joint Word and Morpheme Segmentation with Bayesian Non-Parametric Models

Shu Okabe, François Yvon


Abstract
Language documentation often requires segmenting transcriptions of utterances collected on the field into words and morphemes. While these two tasks are typically performed in succession, we study here Bayesian models for simultaneously segmenting utterances at these two levels. Our aim is twofold: (a) to study the effect of explicitly introducing a hierarchy of units in joint segmentation models; (b) to further assess whether these two levels can be better identified through weak supervision. For this, we first consider a deterministic coupling between independent models; then design and evaluate hierarchical Bayesian models. Experiments with two under-resourced languages (Japhug and Tsez) allow us to better understand the value of various types of weak supervision. In our analysis, we use these results to revisit the distributional hypotheses behind Bayesian segmentation models and evaluate their validity for language documentation data.
Anthology ID:
2023.findings-eacl.48
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
640–654
Language:
URL:
https://aclanthology.org/2023.findings-eacl.48
DOI:
10.18653/v1/2023.findings-eacl.48
Bibkey:
Cite (ACL):
Shu Okabe and François Yvon. 2023. Joint Word and Morpheme Segmentation with Bayesian Non-Parametric Models. In Findings of the Association for Computational Linguistics: EACL 2023, pages 640–654, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Joint Word and Morpheme Segmentation with Bayesian Non-Parametric Models (Okabe & Yvon, Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-eacl.48.pdf
Video:
 https://aclanthology.org/2023.findings-eacl.48.mp4