Microsoft Research Asia at the NTCIR-13 STC-2 Task

This paper describes our approaches in NTCIR-13 on short text conversation(STC) task (Chinese). For retrieval-based method, we propose a response matching and ranking model which takes not only the text information into account, but also considers visual features of images corresponding to the text. For generation-based method, we propose the emotion-aware neural response generation model. Based on the attention-based sequence-to-sequence model, our model generates emotional responses by involving emotion information while decoding. Official results show that both emotion and image information improve the effectiveness of response retrieving or generating, and our best run gains 0.1822 for mean nDCG@1 , 0.3002 for mean P and 0.3241 for mean nERR@10.