Intelligent Question Answering Using the Wisdom of the Crowd
Speaker: Preslav Nakov, Qatar Computing Research Institute, HBKU
Location: 60 Fifth Avenue 110
Date: June 23, 2017, 11:30 a.m.
Host: Oded Regev
In recent years, community Question Answering forums such as StackOverflow, Quora, Qatar Living, etc. have gained a lot of popularity. As such forums are typically not moderated, this results in noisy and redundant content; yet, they are highly valued by users as a source of information. I will explore three general problems related to such forums, focusing on Qatar Living: (i) deciding which answers are good, (ii) finding related/duplicated questions, and (iii) finding good answers to a new question. This will involve models based on deep learning and semantic/syntactic kernels. I will further discuss extensions of this work in directions such as application to Arabic, cross-language question answering, fact checking, trollness detection, answer justification, and interactive question answering.
Dr. Preslav Nakov is a Senior Scientist at the Qatar Computing Research Institute, HBKU. His research interests include computational linguistics, machine translation, question answering, sentiment analysis, lexical semantics, Web as a corpus, and biomedical text processing. Preslav Nakov received a PhD degree in Computer Science from the University of California at Berkeley. He is Secretary of ACL SIGLEX, the Special Interest Group on the Lexicon of the Association for Computational Linguistics. He is also a Member of the Editorial Board of the Journal of Natural Language Engineering and an Associate Editor of the AI Communications journal. Preslav Nakov co-authored a Morgan & Claypool book on Semantic Relations between Nominals, two books on computer algorithms, and many research papers in top-tier conferences and journals.
In-person attendance only available to those with active NYU ID cards.