Seminar: Bridging the gap between askers and high quality answers in community Question Answering services
24th Aug 2017 11:00am-12:00pm
Presenter/Speaker: Dr Alejandro Figueroa, Andres Bello University, Chile
Community Question-Answering (cQA) sites are massive repositories for user-generated content, where members prompt questions expecting satisfactory answers from other members. However, in this dynamic, there is an intrinsic delay between the moment questions are posted to the arrival of acceptable responses. Therefore, cQA platforms have the pressing need for promoting unresolved questions to potential answerers and for taking advantage of resolved questions contained in their archives, whenever possible.
In a four-year government funded project, we have been studying several factors of cQA platforms that can help to mitigate this problem such as question and answer analysis, archive search and paraphrase detection. More precisely, this project focuses its attention on discriminant learning and the effectiveness of assorted features. Since this project is about to end, this talk will be an excellent opportunity of putting things together and drawing some conclusions. More specifically, we will talk about the work done on question analysis, namely the automatic detection of four dimensions: temporality, intent, motivation and gender.
Alejandro Figueroa is a member of the Andres Bello University, Santiago, Chile. He received his Ph.D. in Computational Linguistics from Universitaet des Saarlandes, Saarbruecken, Germany (2010). Dr. Figueroa has also been a researcher at DFKI (the German Center for Artificial Intelligence), Saarbruecken, Germany, and Yahoo! Research Lab in Barcelona, Spain. From 2010 and 2015, he was also a researcher at Yahoo! Labs, Santiago, Chile. His research interests question-answering systems, natural language processing, machine learning and information retrieval.