An Attentional Neural Conversation Model with Improved Specificity

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.

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• Effective Approaches to Attention-based Neural Machine Translation
• How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
• Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
• Reinforcement Learning Neural Turing Machines - Revised
• deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets

Cited by in corpus (9)

• A Survey on Dialogue Systems: Recent Advances and New Frontiers
• Recent advances in conversational NLP : Towards the standardization of Chatbot building
• Deep Learning Based Chatbot Models
• Flexible and Scalable State Tracking Framework for Goal-Oriented Dialogue Systems
• Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators
• Natural Language Generation with Neural Variational Models
• Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward
• Listening between the Lines: Learning Personal Attributes from Conversations
• Lightweight Decoding Strategies for Increasing Specificity