Attention with Intention for a Neural Network Conversation Model
This work addresses the challenge of improving conversation quality in AI dialogue systems, but it appears incremental as it builds on existing neural network approaches without specifying major breakthroughs.
The paper tackled the problem of generating natural responses in dialogue systems by modeling attention and intention processes with a neural network, and the result was a model that produces natural responses to user inputs without requiring labeled data.
In a conversation or a dialogue process, attention and intention play intrinsic roles. This paper proposes a neural network based approach that models the attention and intention processes. It essentially consists of three recurrent networks. The encoder network is a word-level model representing source side sentences. The intention network is a recurrent network that models the dynamics of the intention process. The decoder network is a recurrent network produces responses to the input from the source side. It is a language model that is dependent on the intention and has an attention mechanism to attend to particular source side words, when predicting a symbol in the response. The model is trained end-to-end without labeling data. Experiments show that this model generates natural responses to user inputs.