SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues
This work addresses the challenge of building emotionally intelligent robots by improving social relation inference from dialogues, though it appears incremental in its approach.
The paper tackled the problem of inferring social relations from dialogues by modeling social networks as an And-or Graph (SocAoG) and proposing an incremental parsing strategy with α-β-γ processes. The result showed that the model achieved more accurate social relation inference than state-of-the-art methods on DialogRE and MovieGraph datasets.
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.