english Icono del idioma   español Icono del idioma  

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12008/37155 How to cite
Title: Generation of english question answer exercises from texts using transformers based models
Authors: Berger, Gonzalo
Rischewski, Tatiana
Chiruzzo, Luis
Rosá, Aiala
Type: Ponencia
Keywords: NLP for language teaching, Question & answering, Transformers, Neural language models
Issue Date: 2022
Abstract: This paper studies the use of NLP techniques, in particular, neural language models, for the generation of question/answer exercises from English texts. The experiments aim to generate beginner-level exercises from simple texts, to be used in teaching ESL (English as a Second Language) to children. The approach we present in this paper is based on four stages: a pre-processing stage that, among other basic tasks, applies a co-reference resolution tool; an answer candidate selection stage, which is based on semantic role labeling; a question generation stage, which takes as input the text with the resolved co-references and returns a set of questions for each answer candidate using a language model based on the Transformers architecture; and a post-processing stage that adjusts the format of the generated questions. The question generation model was evaluated on a benchmark obtaining similar results to those of previous works, and the complete pipeline was evaluated on a corpus specifically created for this task, achieving good results.
Description: 2022 IEEE Latin American Conference on Computational Intelligence (LA-CCI), 23-25 November 2022, Montevideo, Uruguay.
Publisher: IEEE
Sponsors: Agencia Nacional de Investigación e Innovación. Proyecto FSED_2_2020_1_163587.
DOI: 10.1109/LA-CCI54402.2022.9981171
Citation: Berger, G., Rischewski, T., Chiruzzo, L. y otros. Generation of english question answer exercises from texts using transformers based models [en línea] EN : 2022 IEEE Latin American Conference on Computational Intelligence (LA-CCI), 23-25 November 2022, Montevideo, Uruguay. 5 p. DOI: 10.1109/LA-CCI54402.2022.9981171
License: Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0)
Appears in Collections:Reportes Técnicos - Instituto de Computación

Files in This Item:
File Description SizeFormat  
BRCR22.pdfPonencia178,45 kBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons