sakuraSAT team from Nguyen lab., Intelligent Robotics Area, achieved a Discovery Challenge Award (Second-Best System of the cQA Challenge: Learning to Re-Rank Questions for Community Question Answering), in ECML-PKDD 2016.

ECML (European Conference on Machine Learning) is an annual and a top-tier conference on machine learning. ECML2016 is joined with PKDD (Principles and Practice of Knowledge Discovery), a top-tier conference on data mining. This event is the premier European machine learning and data mining conference and builds upon a very successful series of 26 ECML and 19 PKDD conferences, which have been jointly organized for the past 15 years. The event includes technical and industrial presentations on cutting-edge and challenging problems in both machine learning and data mining.


■Date awarded
September 23, 2016

■Title
Learning to Rank Questions for Community Question Answering with Ranking SVM

■Abstract
This paper presents our method to retrieve relevant queries given a new question in the context of Discovery Challenge: Learning to Re-Ranking Questions for Community Question Answering competition. In order to do that, a set of learning to rank methods was investigated to select an appropriate method. The selected method was optimized on training data by using a search strategy. After optimizing, the method was applied to development and test set. Results from the competition indicate that the performance of our method outperforms almost participants and show that Ranking SVM is efficient for retrieving relevant queries in community question answering.

■Comment
We are sakuraSAT team in Nguyen laboratory. We are very honored and thankful for the award. We would like to thank our supervisor - Prof. Le-Minh Nguyen for guiding the team with deep discussions during the participation of the competition. We also really thankful to JAIST and other members in Nguyen Lab for many supports to receive this award.

September　29,2016