学生のTran, Van KhanhさんがKSE 2017においてBest Student Awardを受賞

 学生のTran, Van Khanhさん(博士後期課程3年、知能ロボティクス領域グェン研究室)がKSE 2017においてBest Student Awardを受賞しました。

 The KSE conference is an open international forum for presentation, discussion and exchange of the latest advances and challenges in research of Knowledge and Systems Engineering. The main objective of the conference is to bring together researchers, academics, practitioners and students not only to share research results and practical applications but also to foster collaboration in research and education in KSE.


 Van Khanh Tran, Van Tao Nguyen, Le Minh Nguyen

 Enhanced Semantic Refinement Gate for RNN-based Neural Language Generator

 Natural language generation (NLG) plays an important role in a Spoken Dialogue System. Recurrent Neural Network (RNN)-based approaches have shown promising in tackling NLG tasks. This paper presents approaches to enhance gating mechanism applied for RNN-based natural language generator, in which an attentive dialog act representation is introduced, and
two gating mechanisms are proposed to semantically gate input sequences before RNN computation. The proposed RNN-based generators can be learned from unaligned data by jointly training both sentence planning and surface realization to produce natural
language responses. The model was extensively evaluated on four different NLG domains. The results show that the proposed generators achieved better performance on all the NLG domains in comparison to the previous generators.

 I am very honored and grateful to receive the Best Student Paper Award at KSE 2017 conference. First of all, I would like to express my greatest gratitude to my supervisor, Associate Professor NGUYEN Minh Le, who advises me and gives me many instructive comments during my research. His support creates a great environment to encourage me both in studying and in social life. It is also to especially thank Professor Satoshi Tojo and all members in Nguyen lab for their comments and discussions. Last but not least, I would like to thank my family members for their infinite love, which is the biggest encouragement for my study.