This paper describes QCRI’s participation in SemEval-2015 Task 3 “Answer Selection in Community Question Answering”, which targeted real-life Web forums, and was offered in both Arabic and English. We apply a supervised machine learning approach considering a manifold of features including among others word n-grams, text similarity, sentiment analysis, the presence of specific words, and the context of a comment. Our approach was the best performing one in the Arabic subtask and the third best in the two English subtasks.

@inproceedings{nicosia-et-al-semeval-15, abstract = {This paper describes QCRI’s participation in SemEval-2015 Task 3 “Answer Selection in Community Question Answering”, which targeted real-life Web forums, and was offered in both Arabic and English. We apply a supervised machine learning approach considering a manifold of features including among others word n-grams, text similarity, sentiment analysis, the presence of specific words, and the context of a comment. Our approach was the best performing one in the Arabic subtask and the third best in the two English subtasks.}, address = {Denver, Colorado, USA}, author = {Massimo Nicosia and Simone Filice and Alberto Barron-Cedeno and Iman Saleh and Hamdy Mubarak and Wei Gao and Preslav Nakov and Giovanni Da San Martino and Alessandro Moschitti and Kareem Darwish and Llu{\i}s M\`{a}rquez and Shafiq R. Joty and Walid Magdy}, booktitle = {Proceedings of the 9th International Workshop on Semantic Evaluation}, month = {June}, pages = {203--209}, series = {SemEval'15}, title = {{QCRI:} Answer Selection for Community Question Answering - Experiments for Arabic and English}, url = {http://aclweb.org/anthology/S/S15/S15-2036.pdf}, year = {2015} }