On Few-Shot Prompting for Controllable Question-Answer Generation in Narrative Comprehension

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2024

Autores

Leite, B (Autor) Outra; Henrique Lopes Cardoso (Autor) FEUP

Ata de Conferência Internacional

Título: Proceedings of the 16th International Conference on Computer Supported Education, CSEDU 2024, Angers, France, May 2-4, 2024, Volume 2.

Páginas: 63-74

16th International Conference on Computer Supported Education, CSEDU 2024

Angers, 2 May 2024 through 4 May 2024

Indexação

Scopus - 0 Citações

Outras Informações

ID Authenticus: P-010-J3T

DOI: 10.5220/0012623800003693

Abstract (EN): Question Generation aims to automatically generate questions based on a given input provided as context. A controllable question generation scheme focuses on generating questions with specific attributes, allowing better control. In this study, we propose a few-shot prompting strategy for controlling the generation of question-answer pairs from children¿s narrative texts. We aim to control two attributes: the question¿s explicitness and underlying narrative elements. With empirical evaluation, we show the effectiveness of controlling the generation process by employing few-shot prompting side by side with a reference model. Our experiments highlight instances where the few-shot strategy surpasses the reference model, particularly in scenarios such as semantic closeness evaluation and the diversity and coherency of question-answer pairs. However, these improvements are not always statistically significant. The code is publicly available at github.com/bernardoleite/few-shot-prompting-qg-control. Copyright © 2024 by SCITEPRESS ¿ Science and Technology Publications, Lda.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 11