Extracting Chinese question-answer pairs from online forums. Wang, B., Liu, B., Sun, C., Wang, X., & Sun, L. In 2009 IEEE International Conference on Systems, Man and Cybernetics, pages 1159–1164, October, 2009. ISSN: 1062-922X
doi  abstract   bibtex   
Extracting question-answer pairs from online forums is a meaningful work due to the huge amount of valuable user generated resource contained in forums. In this paper we consider the problem of extracting Chinese question-answer pairs for the first time. We present a strategy to detect Chinese questions and their answers. We propose a sequential rule based method to find questions in a forum thread, then we adopt non-textual features based on forum structure to improve the performance of answer detecting in the same thread. Experimental results show that our techniques are very effective.
@inproceedings{Wang_etal:2009,
	title = {Extracting {Chinese} question-answer pairs from online forums},
	doi = {10.1109/ICSMC.2009.5345956},
	abstract = {Extracting question-answer pairs from online forums is a meaningful work due to the huge amount of valuable user generated resource contained in forums. In this paper we consider the problem of extracting Chinese question-answer pairs for the first time. We present a strategy to detect Chinese questions and their answers. We propose a sequential rule based method to find questions in a forum thread, then we adopt non-textual features based on forum structure to improve the performance of answer detecting in the same thread. Experimental results show that our techniques are very effective.},
	booktitle = {2009 {IEEE} {International} {Conference} on {Systems}, {Man} and {Cybernetics}},
	author = {Wang, Baoxun and Liu, Bingquan and Sun, Chengjie and Wang, Xiaolong and Sun, Lin},
	month = oct,
	year = {2009},
	note = {ISSN: 1062-922X},
	keywords = {Computer science, Cybernetics, Data mining, Feature extraction, Humans, Natural languages, Sun, Testing, USA Councils, Yarn, classification, information extraction, labeled sequential rules, nontextual features, question answering},
	pages = {1159--1164},
}

Downloads: 0