SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues

TL;DR

This paper introduces SocAoG, a novel incremental graph parsing method for social relation inference in dialogues, improving accuracy by modeling dynamic social relations through a structured, multi-step process.

Contribution

The paper proposes SocAoG, an incremental parsing framework with an $ ext{α}$-$ ext{β}$-$ ext{γ}$ strategy for dynamic social relation inference in dialogues, advancing beyond prior static models.

Findings

Outperforms state-of-the-art on DialogRE and MovieGraph datasets.

The three processes in SocAoG complement each other for better inference.

Demonstrates effective dynamic relational inference through case studies.

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.