Automatic Question Categorization: a New Approach for Text Elaboration

Marcelo Adriano Amancio, Magali Sanches Duran, Sandra Maria Aluisio


Text adaptation is a normal activity of teachers to facilitate reading comprehension of specific contents; the general approaches for it are Text Simplification and Text Elaboration (TE). TE aims at clarifying, explaining information and making connections explicit in texts. In this paper, we present a new approach for TE: an automatic question categorization system which assigns wh-question labels to verbal arguments in a sentence. For example, in Mary danced yesterday. Who? is the label linking the verb danced to the argument Mary and When? links danced to the argument yesterday. This annotation is similar to semantic ro-le labeling, approached successfully via statistical language processing techniques. Specifically, we present experiments to build the system using a fine-grained question set in Portuguese lan-guage and address two key research questions: (1) Which machine-learning algorithm presents the best results? (2) Which problems this task presents and how to overcome them? Keywords: Text Elaboration, Semantic Role Labeling, Wh-question labels.

Texto completo: