Emulating Human Conversations using Convolutional Neural Network-based IR
This work addresses the need for more human-like conversational agents in interfaces, though it appears incremental as it builds on existing IR and neural network methods.
The paper tackled the problem of designing conversational agents that emulate human-like interactions by introducing a context-sensitive information retrieval model using convolutional deep structured semantic neural networks with character trigrams. The result showed that this approach significantly outperformed conventional baselines in terms of response relevance.
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.