Implicit Discourse Relation Recognition by Selecting Typical Training Examples.

Implicit discourse relation recognition is a challenging task in the natural language processing field, but important to many applications such as question answering, summarizat ion and so on. Previous research used either art ificially created implicit discourse relat ions with connectives removed from explicit relations or annotated implicit relat ions as training data to detect the possible implicit relations, and do not further discern which examples are fit to be training data. This paper is the first time to apply a different typical/atypical perspective to select the most suitable discourse relation examples as training data. To differentiate typical and atypical examples for each discourse relation, a novel single centroid clustering algorithm is proposed. With this typical/atypical distinction, we aim to recognize those easily identified discourse relations more precisely so as to promote the performance of the implicit relation recognition. The experimental results verify that the proposed new method outperforms the state -of-the-art methods. © 2012 The COLING.