Zero-Shot Query Generation for Approximate Search Algorithm Evaluation
Aidan Pine, David Huggins-Daines, Carmen Leeming, Patrick Littell, Timothy Montler, Heather Souter, Mark Turin
Abstract
Approximate search is a valuable component of online dictionaries for learners, allowing them to find words even when they have not fully mastered the orthography or cannot reliably perceive phonemic differences in the language. However, evaluating the performance of different approximate search algorithms remains difficult in the absence of real user queries. We detail several methods for generating synthetic queries representing various user personas. We then compare the performance of several search algorithms on both real and synthetic queries in two Indigenous languages, SENĆOŦEN and Michif, that are phonologically and morphologically very different from English.- Anthology ID:
- 2025.computel-main.7
- Volume:
- Proceedings of the Eight Workshop on the Use of Computational Methods in the Study of Endangered Languages
- Month:
- March
- Year:
- 2025
- Address:
- Honolulu, Hawaii, USA
- Editors:
- Jordan Lachler, Godfred Agyapong, Antti Arppe, Sarah Moeller, Aditi Chaudhary, Shruti Rijhwani, Daisy Rosenblum
- Venues:
- ComputEL | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 65–73
- Language:
- URL:
- https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.computel-main.7/
- DOI:
- Cite (ACL):
- Aidan Pine, David Huggins-Daines, Carmen Leeming, Patrick Littell, Timothy Montler, Heather Souter, and Mark Turin. 2025. Zero-Shot Query Generation for Approximate Search Algorithm Evaluation. In Proceedings of the Eight Workshop on the Use of Computational Methods in the Study of Endangered Languages, pages 65–73, Honolulu, Hawaii, USA. Association for Computational Linguistics.
- Cite (Informal):
- Zero-Shot Query Generation for Approximate Search Algorithm Evaluation (Pine et al., ComputEL 2025)
- PDF:
- https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.computel-main.7.pdf