An Attentional Neural Conversation Model with Improved Specificity

TL;DR

This paper introduces a neural conversation model that enhances specificity and intention modeling to generate more relevant help desk responses, outperforming previous models in both generation and retrieval tasks.

Contribution

It presents a novel neural conversation architecture that incorporates intention modeling and an IDF-based objective to improve response relevance and specificity.

Findings

Model outperforms previous neural conversation architectures.

Incorporating IDF improves response relevance and specificity.

Effective in both response generation and retrieval tasks.

Abstract

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.