Файл:Emulating Human Conversations using Convolutional Neural Network-based IR 1606.07056v1.pdf

Abhay Prakash Microsoft, India abprak@microsoft.com Chris Brockett Microsoft Research, Redmond, WA, USA chrisbkt@microsoft.com Puneet Agrawal Microsoft, India punagr@microsoft.com

ABSTRACT

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.

Categories and Subject Descriptors

H.3.3 [Information Storage And Retrieval]: Information Search and Retrieval;

I.2.7 [Artificial Intelligence]: Natural Language Processing

Keywords Chat bot; Deep learning; Structured Semantics; Conversational agent; Convolutional Networks; Twitter data