Given a text, a question on that text, and a set of candidate answers, a system must select the correct answer from a set of 2-7 candidate answers. Additionally, each question-answer pair instance includes a short explanation as reasoning support for choosing a candidate answer.
Publication
Marco Antonio Sobrevilla Cabezudo, Diego Diestra, Rodrigo López, Erasmo Gómez, Arturo Oncevay, Fernando Alva-Manchego (2022) Overview of ReCoRES at IberLEF 2022: Reading Comprehension and Reasoning Explanation for Spanish. Procesamiento del Lenguaje Natural, Revista nº 69, septiembre de 2022, pp. 281-287.
Language
Spanish
NLP topic
Abstract task
Year
2022
Publication link
Ranking metric
Accuracy
Task results
System | Accuracy Sort ascending |
---|---|
MRCPUCP | 0.7591 |
SADDA | 0.7254 |
Versae & Nandezgarcia | 0.4067 |