Colibri Colección : Reportes de investigación, tesis de postgrado, notas de cursos, conferencias y seminarios realizados en el Instituto de Computación.Reportes de investigación, tesis de postgrado, notas de cursos, conferencias y seminarios realizados en el Instituto de Computación.https://hdl.handle.net/20.500.12008/34092024-03-29T15:27:42Z2024-03-29T15:27:42ZA tool for automatic question generation for teaching english to beginner studentsMorón, MartínScocozza, JoaquínChiruzzo, LuisRosá, Aialahttps://hdl.handle.net/20.500.12008/371572023-05-16T16:27:28Z2021-01-01T00:00:00ZTítulo: A tool for automatic question generation for teaching english to beginner students
Autor: Morón, Martín; Scocozza, Joaquín; Chiruzzo, Luis; Rosá, Aiala
Resumen: We present a tool for the automatic generation of questions from texts for ESL teaching, using resources and
methods from the Natural Language Processing (NLP) field. The approach presented in this paper is based on symbolic methods, using hand-crafted rules. The tool uses linguistic information, such as semantic roles, co-references and named entities, to generate questions and answers from a text selected by a teacher.
The generated questions are ranked in order to offer the teacher a varied set to create an exercise. All the elements can be edited in case any error is produced, since NLP tools and methods are not completely accurate. When solving an exercise, the students are given immediate feedback based on the expected answers.
A primary evaluation showed promising results, especially for “what” and “who” questions.
Descripción: 2021 40th International Conference of the Chilean Computer Science Society (SCCC), 15-19 November 2021, La Serena, Chile.2021-01-01T00:00:00ZApplication of language technologies to assist english teachingGonzález, BernabéIvagnes, IsabelLejtreger, JoaquínChiruzzo, LuisRosá, Aialahttps://hdl.handle.net/20.500.12008/371562023-05-16T16:27:18Z2021-01-01T00:00:00ZTítulo: Application of language technologies to assist english teaching
Autor: González, Bernabé; Ivagnes, Isabel; Lejtreger, Joaquín; Chiruzzo, Luis; Rosá, Aiala
Resumen: This work explores the use of standard Natural Language Processing (NLP) tools for the development of teaching
support tools.We use these methods for developing an application that allows to automatically create different types of English exercises aimed at students at the beginners level. The web application contains two interfaces, where teachers can generate four types of exercises starting from English texts, and students can solve them. The four types of exercises are: verb form exercises, noun definition exercises, use of English exercises, and
lexical relations exercises. Some of the NLP techniques and tools explored during development include: POS-tagging, language models, word embeddings, Levenshtein distance and WordNet.
Developing this tool allowed us to test the potential of Natural Language Processing techniques to generate teaching activities. As a way of validating the tool, we tested it with local teachers and found that there is an important demand for these type of tools in our country.
Descripción: 2021 40th International Conference of the Chilean Computer Science Society (SCCC), 15-19 November 2021, La Serena, Chile.2021-01-01T00:00:00ZGeneration of english question answer exercises from texts using transformers based modelsBerger, GonzaloRischewski, TatianaChiruzzo, LuisRosá, Aialahttps://hdl.handle.net/20.500.12008/371552023-05-16T16:27:08Z2022-01-01T00:00:00ZTítulo: Generation of english question answer exercises from texts using transformers based models
Autor: Berger, Gonzalo; Rischewski, Tatiana; Chiruzzo, Luis; Rosá, Aiala
Resumen: 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.
Descripción: 2022 IEEE Latin American Conference on Computational Intelligence (LA-CCI), 23-25 November 2022, Montevideo, Uruguay.2022-01-01T00:00:00ZCINACINA: Capacitación en INglés en el Aula Con INteligencia ArtificialRosá, AialaChiruzzo, LuisGóngora, SantiagoMusto, Laurahttps://hdl.handle.net/20.500.12008/371542023-05-16T16:26:55Z2021-01-01T00:00:00ZTítulo: CINACINA: Capacitación en INglés en el Aula Con INteligencia Artificial
Autor: Rosá, Aiala; Chiruzzo, Luis; Góngora, Santiago; Musto, Laura
Descripción: 14º Foro de Lenguas : Conferencias presentadas durante el decimocuarto foro de lenguas de ANEP, Oct. 2021, Montevideo, Uruguay.2021-01-01T00:00:00Z