CLIRSep 26, 2021

Extracting and Inferring Personal Attributes from Dialogue

arXiv:2109.12702v2640 citations
Originality Highly original
AI Analysis

This addresses the challenge of understanding personal information in conversations for applications like social chit-chat and task-oriented dialogue, representing an incremental improvement with a novel method.

The paper tackles the problem of extracting and inferring personal attributes from human dialogue, introducing a model that combines constrained attribute generation with discriminative reranking, which outperforms baselines on both tasks.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes