Enhancing Lexical Complexity Prediction through Few-shot Learning with Gpt-3

Jenny Alexandra Ortiz-Zambrano, César Humberto Espín-Riofrío, Arturo Montejo-Ráez


Abstract
This paper describes an experiment to evaluate the ability of the GPT-3 language model to classify terms regarding their lexical complexity. This was achieved through the creation and evaluation of different versions of the model: text-Davinci-002 y text-Davinci-003 and prompts for few-shot learning to determine the complexity of the words. The results obtained on the CompLex dataset achieve a minimum average error of 0.0856. Although this is not better than the state of the art (which is 0.0609), it is a performing and promising approach to lexical complexity prediction without the need for model fine-tuning.
Anthology ID:
2024.determit-1.7
Volume:
Proceedings of the Workshop on DeTermIt! Evaluating Text Difficulty in a Multilingual Context @ LREC-COLING 2024
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Giorgio Maria Di Nunzio, Federica Vezzani, Liana Ermakova, Hosein Azarbonyad, Jaap Kamps
Venues:
DeTermIt | WS
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
68–76
Language:
URL:
https://aclanthology.org/2024.determit-1.7
DOI:
Bibkey:
Cite (ACL):
Jenny Alexandra Ortiz-Zambrano, César Humberto Espín-Riofrío, and Arturo Montejo-Ráez. 2024. Enhancing Lexical Complexity Prediction through Few-shot Learning with Gpt-3. In Proceedings of the Workshop on DeTermIt! Evaluating Text Difficulty in a Multilingual Context @ LREC-COLING 2024, pages 68–76, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Enhancing Lexical Complexity Prediction through Few-shot Learning with Gpt-3 (Ortiz-Zambrano et al., DeTermIt-WS 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.determit-1.7.pdf