Neural conversational models tend to produce generic or safe responses in different contexts, e.g., reply \textit{"Of course"} to narrative statements or \textit{"I don't know"} to questions. In this paper, we propose an end-to-end approach to avoid such problem in neural generative models. Additional memory mechanisms have been introduced to standard sequence-to-sequence (seq2seq) models, so that context can be considered while generating sentences. Three seq2seq models, which memorize a fix-sized contextual vector from hidden input, hidden input/output and a gated contextual attention structure respectively, have been trained and tested on a dataset of labeled question-answering pairs in Chinese. The model with contextual attention outperforms others including the state-of-the-art seq2seq models on perplexity test. The novel contextual model generates diverse and robust responses, and is able to carry out conversations on a wide range of topics appropriately.
@article{arxiv.1607.05809,
title = {Neural Contextual Conversation Learning with Labeled Question-Answering Pairs},
author = {Kun Xiong and Anqi Cui and Zefeng Zhang and Ming Li},
journal= {arXiv preprint arXiv:1607.05809},
year = {2016}
}