SOFTCARDINALITY: Hierarchical text overlap for student response analysis

Sergio Jimenez, Claudia Becerra, Alexander Gelbukh

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

34 Citas (Scopus)

Resumen

In this paper we describe our system used to participate in the Student-Response-Analysis task-7 at SemEval 2013. This system is based on text overlap through the soft cardinality and a new mechanism for weight propagation. Although there are several official performance measures, taking into account the overall accuracy throughout the two availabe data sets (Beetle and SciEntsBank), our system ranked first in the 2 way classification task and second in the others. Furthermore, our system performs particularly well with “unseen-domains” instances, which was the more challenging test set. This paper also describes another system that integrates this method with the lexical-overlap baseline provided by the task organizers obtaining better results than the best official results. We concluded that the soft cardinality method is a very competitive baseline for the automatic evaluation of student responses.

Idioma originalInglés
Título de la publicación alojada*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics
EditorialAssociation for Computational Linguistics (ACL)
Páginas280-284
Número de páginas5
ISBN (versión digital)9781937284497
EstadoPublicada - 2013
Evento2nd Joint Conference on Lexical and Computational Semantics, *SEM 2013 - Atlanta, Estados Unidos
Duración: 13 jun. 201314 jun. 2013

Serie de la publicación

Nombre*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics
Volumen2

Conferencia

Conferencia2nd Joint Conference on Lexical and Computational Semantics, *SEM 2013
País/TerritorioEstados Unidos
CiudadAtlanta
Período13/06/1314/06/13

Huella

Profundice en los temas de investigación de 'SOFTCARDINALITY: Hierarchical text overlap for student response analysis'. En conjunto forman una huella única.

Citar esto