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:
- 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)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.determit-1.7.pdf