Question Classification by Structure Induction

Menno van Zaanen, Luiz Augusto Sangoi Pizzato, Diego Mollá

Abstract: In this article we introduce a new approach (and several implementations) to the task of question classification. The approach extracts structural information using machine learning techniques and the patterns found are used to classify the questions. The approach fits in between the machine learning and handcrafting of regular expressions (as it was done in the past) and combines the best of both: classifiers can be generated automatically and the output can be investigated and manually optimised if needed.