SINAI Participation in SimpleText Task 2 at CLEF 2023: GPT-3 in Lexical Complexity Prediction for General Audience

Abstract:

In this paper our participation in the CLEF 2023 SimpleText track’s Task 2.1 and 2.2 is described. In our approach, we explore zero-shot and few-shot learning strategies over the auto-regressive model GPT-3. Several prompts to achieve those strategies were tested. Our results were ranked among top submitted runs and demonstrated a solid performance for the task of lexical complexity prediction.

Año de publicación:

2023

Keywords:

• Auto-regressive models
• Few-shot learning
• GPT-3
• Lexical Complexity Prediction
• Prompting
• Zero-Shot learning

Fuente:

scopus