Extracting and Inferring Personal Attributes from Dialogue
Not on the map. Why?
Abstract (arXiv)
Personal attributes represent structured information about a person, such as their hobbies, pets, family, likes and dislikes. We introduce the tasks of extracting and inferring personal attributes from human-human dialogue, and analyze the linguistic demands of these tasks. To meet these challenges, we introduce a simple and extensible model that combines an autoregressive language model utilizing constrained attribute generation with a discriminative reranker. Our model outperforms strong baselines on extracting personal attributes as well as inferring personal attributes that are not contained verbatim in utterances and instead requires commonsense reasoning and lexical inferences, which occur frequently in everyday conversation. Finally, we demonstrate the benefit of incorporating personal attributes in social chit-chat and task-oriented dialogue settings.
Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 31 of its 49 references that are in the map. First posted on arXiv 26 Sep 2021.
Builds on
31 of 49 references.
References · 31
- 2019Language Models as Knowledge Bases?cited by 1,922
- 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
- 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
- 2020Knowledge Graphscited by 619
- 2020Recipes for building an open-domain chatbotcited by 593
- 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
- 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
- 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
- 2019Entity, Relation, and Event Extraction with Contextualized Span Representationscited by 261
- 2016A Persona-Based Neural Conversation Modelcited by 221
- 2020MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselinescited by 201
- 2019The Second Conversational Intelligence Challenge (ConvAI2)cited by 178
19 more
- 2017ParlAI: A Dialog Research Software Platformcited by 139
- 2019Taskmaster-1: Toward a Realistic and Diverse Dialog Datasetcited by 139
- 2018Dialogue Natural Language Inferencecited by 135
- 2018Training Millions of Personalized Dialogue Agentscited by 126
- 2019Text Generation from Knowledge Graphs with Graph Transformerscited by 122
- 2019Evaluating Commonsense in Pre-trained Language Modelscited by 95
- 2019A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Datacited by 74
- 2019Personalized Dialogue Generation with Diversified Traitscited by 73
- 2019Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extractioncited by 73
- 2020Dialogue-Based Relation Extractioncited by 68
- 2020Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansionscited by 49
- 2020Contrastive Triple Extraction with Generative Transformercited by 44
- 2017Personalization in Goal-Oriented Dialogcited by 28
- 2018Learning Personalized End-to-End Goal-Oriented Dialogcited by 19
- 2019Getting To Know You: User Attribute Extraction from Dialoguescited by 19
- 2016Personalizing a Dialogue System with Transfer Reinforcement Learningcited by 17
- 2019ALOHA: Artificial Learning of Human Attributes for Dialogue Agentscited by 16
- 2019Listening between the Lines: Learning Personal Attributes from Conversationscited by 15
- 2021A Cooperative Memory Network for Personalized Task-oriented Dialogue Systems with Incomplete User Profilescited by 8
Built on by
Citing papers per year: 2021: 1; 2022: 0; 2023: 2; 2024: 4; 2025: 0; 2026: 1.
8 papers.
- 2023SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHFcited by 107
- 2023Humanoid Agents: Platform for Simulating Human-like Generative Agentscited by 73
- 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
- 2024The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trendscited by 11
- 2024DEMO: Reframing Dialogue Interaction with Fine-grained Element Modelingcited by 6
- 2024Using Natural Language Inference to Improve Persona Extraction from Dialogue in a New Domaincited by 2
- 2024Tailoring Vaccine Messaging with Common-Ground Opinionscited by 2
- 2026G-Long: Graph-Enhanced Memory Management for Efficient Long-Term Dialogue Agentscited by 1
- 2026G-Long: Graph-Enhanced Memory Management for Efficient Long-Term Dialogue Agents11 Jun 2026
- 2024DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling6 Dec 2024
- 2024The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends21 Sep 2024
- 2024Tailoring Vaccine Messaging with Common-Ground Opinions17 May 2024
- 2024Using Natural Language Inference to Improve Persona Extraction from Dialogue in a New Domain12 Jan 2024
- 2023Humanoid Agents: Platform for Simulating Human-like Generative Agents9 Oct 2023
- 2023SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF9 Oct 2023
- 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systems15 Oct 2021