Extracting and Inferring Personal Attributes from Dialogue

Zhilin Wang, Xuhui Zhou, Rik Koncel-Kedziorski, Alex Marin, Fei Xia


Abstract
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.
Anthology ID:
2022.nlp4convai-1.6
Volume:
Proceedings of the 4th Workshop on NLP for Conversational AI
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
NLP4ConvAI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
58–69
Language:
URL:
https://aclanthology.org/2022.nlp4convai-1.6
DOI:
10.18653/v1/2022.nlp4convai-1.6
Bibkey:
Cite (ACL):
Zhilin Wang, Xuhui Zhou, Rik Koncel-Kedziorski, Alex Marin, and Fei Xia. 2022. Extracting and Inferring Personal Attributes from Dialogue. In Proceedings of the 4th Workshop on NLP for Conversational AI, pages 58–69, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Extracting and Inferring Personal Attributes from Dialogue (Wang et al., NLP4ConvAI 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.nlp4convai-1.6.pdf
Video:
 https://aclanthology.org/2022.nlp4convai-1.6.mp4
Code
 zhilin123/personal_attributes
Data
ConceptNetUniversal Dependencies