Personalized Dialogue Generation with Diversified Traits

Abstract

Endowing a dialogue system with particular personality traits is essential to deliver more human-like conversations. However, due to the challenge of embodying personality via language expression and the lack of large-scale persona-labeled dialogue data, this research problem is still far from well-studied. In this paper, we investigate the problem of incorporating explicit personality traits in dialogue generation to deliver personalized dialogues. To this end, firstly, we construct PersonalDialog, a large-scale multi-turn dialogue dataset containing various traits from a large number of speakers. The dataset consists of 20.83M sessions and 56.25M utterances from 8.47M speakers. Each utterance is associated with a speaker who is marked with traits like Age, Gender, Location, Interest Tags, etc. Several anonymization schemes are designed to protect the privacy of each speaker. This large-scale dataset will facilitate not only the study of personalized dialogue generation, but also other researches on sociolinguistics or social science. Secondly, to study how personality traits can be captured and addressed in dialogue generation, we propose persona-aware dialogue generation models within the sequence to sequence learning framework. Explicit personality traits (structured by key-value pairs) are embedded using a trait fusion module. During the decoding process, two techniques, namely persona-aware attention and persona-aware bias, are devised to capture and address trait-related information. Experiments demonstrate that our model is able to address proper traits in different contexts. Case studies also show interesting results for this challenging research problem.

arXiv commentPlease contact [zhengyinhe1 at 163 dot com] for the PersonalDialog dataset

References in corpus (13)

• Sequence to Sequence Learning with Neural Networks
• A systematic study of the class imbalance problem in convolutional neural networks
• A Neural Conversational Model
• Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs
• A Diversity-Promoting Objective Function for Neural Conversation Models
• Personalizing Dialogue Agents: I have a dog, do you have pets too?
• A Survey of Available Corpora for Building Data-Driven Dialogue Systems
• A Persona-Based Neural Conversation Model
• Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
• Personalization in Goal-Oriented Dialog
• Assigning personality/identity to a chatting machine for coherent conversation generation
• Training Millions of Personalized Dialogue Agents
• Low-Rank RNN Adaptation for Context-Aware Language Modeling

Cited by in corpus (24)

• Challenges in Building Intelligent Open-domain Dialog Systems
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training
• Neural Language Generation: Formulation, Methods, and Evaluation
• Improving Personality Consistency in Conversation by Persona Extending
• A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Data
• Profile Consistency Identification for Open-domain Dialogue Agents
• OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
• A Neural Topical Expansion Framework for Unstructured Persona-oriented Dialogue Generation
• Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation
• BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data
• Conditional Text Generation for Harmonious Human-Machine Interaction
• A Stack-Propagation Framework for Low-Resource Personalized Dialogue Generation
• A Large-Scale Chinese Short-Text Conversation Dataset
• Emily: Developing An Emotion-affective Open-Domain Chatbot with Knowledge Graph-based Persona
• Generating Personalized Dialogue via Multi-Task Meta-Learning
• Document-editing Assistants and Model-based Reinforcement Learning as a Path to Conversational AI
• Partner Matters! An Empirical Study on Fusing Personas for Personalized Response Selection in Retrieval-Based Chatbots
• Guiding Topic Flows in the Generative Chatbot by Enhancing the ConceptNet with the Conversation Corpora
• Dialogue Distillation: Open-Domain Dialogue Augmentation Using Unpaired Data
• Learning to Predict Persona Information forDialogue Personalization without Explicit Persona Description
• Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System
• Improvement of a dedicated model for open domain persona-aware dialogue generation
• Conversational Semantic Role Labeling