Word Segmentation as Unsupervised Constituency Parsing

Raquel G. Alhama


Abstract
Word identification from continuous input is typically viewed as a segmentation task. Experiments with human adults suggest that familiarity with syntactic structures in their native language also influences word identification in artificial languages; however, the relation between syntactic processing and word identification is yet unclear. This work takes one step forward by exploring a radically different approach of word identification, in which segmentation of a continuous input is viewed as a process isomorphic to unsupervised constituency parsing. Besides formalizing the approach, this study reports simulations of human experiments with DIORA (Drozdov et al., 2020), a neural unsupervised constituency parser. Results show that this model can reproduce human behavior in word identification experiments, suggesting that this is a viable approach to study word identification and its relation to syntactic processing.
Anthology ID:
2022.acl-long.283
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4103–4112
Language:
URL:
https://aclanthology.org/2022.acl-long.283
DOI:
10.18653/v1/2022.acl-long.283
Bibkey:
Cite (ACL):
Raquel G. Alhama. 2022. Word Segmentation as Unsupervised Constituency Parsing. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4103–4112, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Word Segmentation as Unsupervised Constituency Parsing (Alhama, ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.283.pdf
Video:
 https://aclanthology.org/2022.acl-long.283.mp4
Data
OpenSubtitles