| Download | - View final version: Zero-shot query generation for approximate search algorithm evaluation (PDF, 397 KiB)
|
|---|
| Link | https://aclanthology.org/2025.computel-main.7/ |
|---|
| Author | Search for: Pine, Aidan1ORCID identifier: https://orcid.org/0000-0001-6552-5324; Search for: Huggins-Daines, David; Search for: Leeming, Carmen; Search for: Littell, Patrick1ORCID identifier: https://orcid.org/0000-0002-7173-0225; Search for: Montler, Timothy; Search for: Souter, Heather; Search for: Turin, Mark |
|---|
| Affiliation | - National Research Council Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | Eight Workshop on the Use of Computational Methods in the Study of Endangered Languages (ComputEL-8), March 4-5, 2025, Honolulu, Hawaii, US |
|---|
| 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. |
|---|
| Publication date | 2025-03-04 |
|---|
| Publisher | Association for Computational Linguistics |
|---|
| Licence | |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 9fac9e31-71c3-48c3-98d6-9a46f121f374 |
|---|
| Record created | 2025-07-31 |
|---|
| Record modified | 2025-08-05 |
|---|
