Personalization in Goal-Oriented Dialog

Abstract

The main goal of modeling human conversation is to create agents which can interact with people in both open-ended and goal-oriented scenarios. End-to-end trained neural dialog systems are an important line of research for such generalized dialog models as they do not resort to any situation-specific handcrafting of rules. However, incorporating personalization into such systems is a largely unexplored topic as there are no existing corpora to facilitate such work. In this paper, we present a new dataset of goal-oriented dialogs which are influenced by speaker profiles attached to them. We analyze the shortcomings of an existing end-to-end dialog system based on Memory Networks and propose modifications to the architecture which enable personalization. We also investigate personalization in dialog as a multi-task learning problem, and show that a single model which shares features among various profiles outperforms separate models for each profile.

Accepted at NIPS 2017 Conversational AI Workshop; Code and data at https://github.com/chaitjo/personalized-dialog

Cited by in corpus (21)

• Personalizing Dialogue Agents: I have a dog, do you have pets too?
• Personalized Dialogue Generation with Diversified Traits
• Deep Learning Based Chatbot Models
• Training Millions of Personalized Dialogue Agents
• Computational Politeness in Natural Language Processing: A Survey
• Towards Retrieval-based Conversational Recommendation
• You Impress Me: Dialogue Generation via Mutual Persona Perception
• Getting To Know You: User Attribute Extraction from Dialogues
• MoEL: Mixture of Empathetic Listeners
• Generating Personalized Dialogue via Multi-Task Meta-Learning
• Learning Personalized End-to-End Goal-Oriented Dialog
• Towards End-to-End Learning for Efficient Dialogue Agent by Modeling Looking-ahead Ability
• DialogAct2Vec: Towards End-to-End Dialogue Agent by Multi-Task Representation Learning
• EmpBot: A T5-based Empathetic Chatbot focusing on Sentiments
• Personal Health Knowledge Graph for Clinically Relevant Diet Recommendations
• Correction of Faulty Background Knowledge based on Condition Aware and Revise Transformer for Question Answering
• Predicting gender and age categories in English conversations using lexical, non-lexical, and turn-taking features
• Listening between the Lines: Learning Personal Attributes from Conversations
• Personalizing Dialogue Agents via Meta-Learning
• AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions
• Learning to Learn End-to-End Goal-Oriented Dialog From Related Dialog Tasks