We consider the importance of different utterances in the context for selecting the response usually depends on the current query. In this paper, we propose the model TripleNet to fully model the task with the triple <context, query, response> instead of <context, response> in previous works. The heart of TripleNet is a novel attention mechanism named triple attention to model the relationships within the triple at four levels. The new mechanism updates the representation for each element based on the attention with the other two concurrently and symmetrically. We match the triple <C, Q, R> centered on the response from char to context level for prediction. Experimental results on two large-scale multi-turn response selection datasets show that the proposed model can significantly outperform the state-of-the-art methods. TripleNet source code is available at https://github.com/wtma/TripleNet
@article{arxiv.1909.10666,
title = {TripleNet: Triple Attention Network for Multi-Turn Response Selection in Retrieval-based Chatbots},
author = {Wentao Ma and Yiming Cui and Nan Shao and Su He and Wei-Nan Zhang and Ting Liu and Shijin Wang and Guoping Hu},
journal= {arXiv preprint arXiv:1909.10666},
year = {2019}
}
Comments
10 pages, accepted as a conference paper at CoNLL 2019