SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues

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 $\alpha$-$\beta$-$\gamma$ strategy to incrementally parse SocAoG for the dynamic inference upon any incoming utterance: (i) an $\alpha$ process predicting attributes and relations conditioned on the semantics of dialogues, (ii) a $\beta$ process updating the social relations based on related attributes, and (iii) a $\gamma$ 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.

Long paper (oral) accepted by ACL-IJCNLP 2021

References in corpus (7)

• GDPNet: Refining Latent Multi-View Graph for Relation Extraction
• A Survey of Deep Learning Methods for Relation Extraction
• Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs
• Structured Attention for Unsupervised Dialogue Structure Induction
• An Embarrassingly Simple Model for Dialogue Relation Extraction
• Relation of the Relations: A New Paradigm of the Relation Extraction Problem
• Vertical-Horizontal Structured Attention for Generating Music with Chords

Cited by in corpus (1)

• ValueNet: A New Dataset for Human Value Driven Dialogue System