SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues

Liang Qiu, Yuan Liang, Yizhou Zhao, Pan Lu, Baolin Peng, Zhou Yu, Ying Nian Wu, Song-Chun Zhu


Abstract
Inferring social relations from dialogues is vital for building emotionally intelligent robots to interpret human language better and act accordingly. We model the social network as an And-or Graph, named SocAoG, for the consistency of relations among a group and leveraging attributes as inference cues. Moreover, we formulate a sequential structure prediction task, and propose an 𝛼-𝛽-𝛾 strategy to incrementally parse SocAoG for the dynamic inference upon any incoming utterance: (i) an 𝛼 process predicting attributes and relations conditioned on the semantics of dialogues, (ii) a 𝛽 process updating the social relations based on related attributes, and (iii) a 𝛾 process updating individual’s attributes based on interpersonal social relations. Empirical results on DialogRE and MovieGraph show that our model infers social relations more accurately than the state-of-the-art methods. Moreover, the ablation study shows the three processes complement each other, and the case study demonstrates the dynamic relational inference.
Anthology ID:
2021.acl-long.54
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
658–670
Language:
URL:
https://aclanthology.org/2021.acl-long.54
DOI:
10.18653/v1/2021.acl-long.54
Bibkey:
Cite (ACL):
Liang Qiu, Yuan Liang, Yizhou Zhao, Pan Lu, Baolin Peng, Zhou Yu, Ying Nian Wu, and Song-Chun Zhu. 2021. SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 658–670, Online. Association for Computational Linguistics.
Cite (Informal):
SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues (Qiu et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.54.pdf
Video:
 https://aclanthology.org/2021.acl-long.54.mp4
Data
DialogRE