Stress Rules from Surface Forms: Experiments with Program Synthesis
Saujas Vaduguru, Partho Sarthi, Monojit Choudhury, Dipti Sharma
Abstract
Learning linguistic generalizations from only a few examples is a challenging task. Recent work has shown that program synthesis – a method to learn rules from data in the form of programs in a domain-specific language – can be used to learn phonological rules in highly data-constrained settings. In this paper, we use the problem of phonological stress placement as a case to study how the design of the domain-specific language influences the generalization ability when using the same learning algorithm. We find that encoding the distinction between consonants and vowels results in much better performance, and providing syllable-level information further improves generalization. Program synthesis, thus, provides a way to investigate how access to explicit linguistic information influences what can be learnt from a small number of examples.- Anthology ID:
- 2021.icon-main.76
- Volume:
- Proceedings of the 18th International Conference on Natural Language Processing (ICON)
- Month:
- December
- Year:
- 2021
- Address:
- National Institute of Technology Silchar, Silchar, India
- Editors:
- Sivaji Bandyopadhyay, Sobha Lalitha Devi, Pushpak Bhattacharyya
- Venue:
- ICON
- SIG:
- Publisher:
- NLP Association of India (NLPAI)
- Note:
- Pages:
- 619–628
- Language:
- URL:
- https://aclanthology.org/2021.icon-main.76
- DOI:
- Cite (ACL):
- Saujas Vaduguru, Partho Sarthi, Monojit Choudhury, and Dipti Sharma. 2021. Stress Rules from Surface Forms: Experiments with Program Synthesis. In Proceedings of the 18th International Conference on Natural Language Processing (ICON), pages 619–628, National Institute of Technology Silchar, Silchar, India. NLP Association of India (NLPAI).
- Cite (Informal):
- Stress Rules from Surface Forms: Experiments with Program Synthesis (Vaduguru et al., ICON 2021)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2021.icon-main.76.pdf