An Attentional Neural Conversation Model with Improved Specificity
This work addresses the issue of non-specific responses in dialogue systems for help desk applications, representing an incremental improvement over existing neural conversation models.
The authors tackled the problem of generating specific responses in neural conversation models for help desk dialogues, and their model outperformed previous architectures by incorporating an attention mechanism conditioned on intention and an IDF term to improve specificity.
In this paper we propose a neural conversation model for conducting dialogues. We demonstrate the use of this model to generate help desk responses, where users are asking questions about PC applications. Our model is distinguished by two characteristics. First, it models intention across turns with a recurrent network, and incorporates an attention model that is conditioned on the representation of intention. Secondly, it avoids generating non-specific responses by incorporating an IDF term in the objective function. The model is evaluated both as a pure generation model in which a help-desk response is generated from scratch, and as a retrieval model with performance measured using recall rates of the correct response. Experimental results indicate that the model outperforms previously proposed neural conversation architectures, and that using specificity in the objective function significantly improves performances for both generation and retrieval.