Title :
Connective prediction using machine learning for implicit discourse relation classification
Author :
Xu, Yu ; Lan, Man ; Lu, Yue ; Niu, Zheng Yu ; Tan, Chew Lim
Author_Institution :
East China Normal Univ., Shanghai, China
Abstract :
Implicit discourse relation classification is a challenge task due to missing discourse connective. Some work directly adopted machine learning algorithms and linguistically informed features to address this task. However, one interesting solution is to automatically predict implicit discourse connective. In this paper, we present a novel two-step machine learning-based approach to implicit discourse relation classification. We first use machine learning method to automatically predict the discourse connective that can best express the implicit discourse relation. Then the predicted implicit discourse connective is used to classify the implicit discourse relation. Experiments on Penn Discourse Treebank 2.0 (PDTB) and Biomedical Discourse Relation Bank (BioDRB) show that our method performs better than the baseline system and previous work.
Keywords :
learning (artificial intelligence); natural language processing; pattern classification; BioDRB; PDTB; Penn Discourse Treebank 2.0; automatically implicit discourse connective prediction; biomedical discourse relation bank; implicit discourse relation classification; machine learning algorithms; two-step machine learning-based approach; Optimization; Support vector machines;
Conference_Titel :
Neural Networks (IJCNN), The 2012 International Joint Conference on
Conference_Location :
Brisbane, QLD
Print_ISBN :
978-1-4673-1488-6
Electronic_ISBN :
2161-4393
DOI :
10.1109/IJCNN.2012.6252548