NAISS
SUPR
NAISS Projects
SUPR
Natural Lanuage Autoformalisation for Corpus Search
Dnr:

NAISS 2025/22-1576

Type:

NAISS Small Compute

Principal Investigator:

Ekaterina Voloshina

Affiliation:

Chalmers tekniska högskola

Start Date:

2025-12-12

End Date:

2026-02-01

Primary Classification:

10208: Natural Language Processing

Webpage:

Allocation

Abstract

The project focuses on translating natural language descriptions of linguistic phenomena to corpus search queries. We have made a survey and collected a golden standard dataset and we have created a synthetic parallel dataset of queries and natural descriptions. We have used prompting techniques and fine-tuning of Large Language Models to generate correct queries from a natural language description using Grammar-Constrained Decoding and without it. We would like to run some additional tests and submit the paper to ACL conference (A* star)