Title: Willow: a system to automatically assess students' free-text answers by using a combination of shallow NLP techniques
Authors: Diana Perez-Marin, Ismael Pascual-Nieto
Addresses: Dpto. Lenguajes y Sistemas Informaticos I, Escuela Tecnica Superior Ingenieria Informatica, Universidad Rey Juan Carlos, 2025 office, Edificio Ampliacion del Rectorado, Calle Tulipan s/n, Mostoles, Madrid 28933, Spain. ' Universidad Autonoma de Madrid, 207 office, Escuela Politecnica Superior, Calle Francisco Tomas y Valiente, 11, Madrid 28049, Spain
Abstract: In this paper, a new approach to automatically assessing students| short free-text answers is presented. It has been implemented into the multilingual web-based application called Willow. Willow is able to formulate a question (chosen randomly or according to the students| personal features) and, to score the answer, written in Spanish or in English, by using a combination of shallow NLP techniques such as stemming, removal of closed-class words, word sense disambiguation or multiword term identification. Several experiments have been carried out to identify the best combination of techniques for each language to find the optimal configuration in each case.
Keywords: free-text assessment; shallow natural language processing; e-assessment; electronic assessment; online learning; e-learning; electronic learning; internet; world wide web; Willow; student assessments; free-text answers; multilingual applications; web-based applications; question formulation; random questions; personal features; scores; answers; Spanish language; English language; stemming; closed-class words; word sense disambiguation; multiword term identification; optimal configurations; Spain; continuing education; life-long learning; automatic free-text evaluation.
International Journal of Continuing Engineering Education and Life-Long Learning, 2011 Vol.21 No.2/3, pp.155 - 169
Published online: 20 May 2011 *Full-text access for editors Access for subscribers Purchase this article Comment on this article