This repo implements the code for LlamATE, a framework to verify the impact of domain specificity on ATE when using in-context learning prompts in open-sourced LLM-based chat models.
Please install all the necessary libraries noted in requirements.txt using this command:
pip install -r requirements.txt
The experiments were conducted on ACTER datasets:
| ACTER dataset | |
|---|---|
| Languages | English, French, and Dutch |
| Domains | Corruption, Wind energy, Equitation, Heart failure |
Download the ACTER dataset at here and save into ACTER folder.
- License: Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) (https://creativecommons.org/licenses/by-nc-sa/4.0/)
- Reference: Please cite the following paper if you use this method for your research
@inproceedings{tran2024llamate,
title={LlamATE: Automated Term Extraction Using Large-scale Generative Language Models},
author={Tran, Hanh Thi Hong and González-Gallardo, Carlos-Emiliano and Doucet, Antoine and Pollak, Senja},
booktitle={Computational Terminology Special Issue - Terminology},
year={2024},
note={Accepted}
}