Conversational agents ("bots") are beginning to be widely used in conversational interfaces. To design a system that is capable of emulating human-like interactions, a conversational layer that can serve as a fabric for chat-like interaction with the agent is needed. In this paper, we introduce a model that employs Information Retrieval by utilizing convolutional deep structured semantic neural network-based features in the ranker to present human-like responses in ongoing conversation with a user. In conversations, accounting for context is critical to the retrieval model; we show that our context-sensitive approach using a Convolutional Deep Structured Semantic Model (cDSSM) with character trigrams significantly outperforms several conventional baselines in terms of the relevance of responses retrieved.
@article{arxiv.1606.07056,
title = {Emulating Human Conversations using Convolutional Neural Network-based IR},
author = {Abhay Prakash and Chris Brockett and Puneet Agrawal},
journal= {arXiv preprint arXiv:1606.07056},
year = {2016}
}
Comments
5 pages, Neu-IR'16 SIGIR Workshop on Neural Information Retrieval, July 21, 2016, Pisa, Italy