SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues

• URL: http://arxiv.org/abs/2106.01006v1
• Date: Wed, 2 Jun 2021 08:07:42 GMT
• Title: SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues
• Authors: Liang Qiu, Yuan Liang, Yizhou Zhao, Pan Lu, Baolin Peng, Zhou Yu, Ying Nian Wu, Song-Chun Zhu
• Abstract summary: Inferring social relations from dialogues is vital for building emotionally intelligent robots. We model the social network as an And-or Graph, named SocAoG, for the consistency of relations among a group. Empirical results on DialogRE and MovieGraph show that our model infers social relations more accurately than the state-of-the-art methods.
• Score: 112.94918467195637
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Social Orientation: A New Feature for Dialogue Analysis [15.192659799728181]
  We introduce a new data set of dialogue utterances machine-labeled with social orientation tags. We show that social orientation tags improve task performance, especially in low-resource settings. We also demonstrate how social orientation tags help explain the outcomes of social interactions when used in neural models.
  arXiv  Detail & Related papers  (2024-02-26T01:55:45Z)
• TOD-Flow: Modeling the Structure of Task-Oriented Dialogues [77.15457469745364]
  We propose a novel approach focusing on inferring the TOD-Flow graph from dialogue data annotated with dialog acts. The inferred TOD-Flow graph can be easily integrated with any dialogue model to improve its prediction performance, transparency, and controllability.
  arXiv  Detail & Related papers  (2023-12-07T20:06:23Z)
• Sequential annotations for naturally-occurring HRI: first insights [0.0]
  We explain the methodology we developed for improving the interactions accomplished by an embedded conversational agent. We are creating a corpus of naturally-occurring interactions that will be made available to the community.
  arXiv  Detail & Related papers  (2023-08-29T08:07:26Z)
• Improving (Dis)agreement Detection with Inductive Social Relation Information From Comment-Reply Interactions [49.305189190372765]
  Social relation information can play an assistant role in the (dis)agreement task besides textual information. We propose a novel method to extract such relation information from (dis)agreement data into an inductive social relation graph. We find social relations can boost the performance of the (dis)agreement detection model, especially for the long-token comment-reply pairs.
  arXiv  Detail & Related papers  (2023-02-08T09:09:47Z)
• Social Processes: Self-Supervised Forecasting of Nonverbal Cues in Social Conversations [22.302509912465077]
  We take the first step in the direction of a bottom-up self-supervised approach in the domain of social human interactions. We formulate the task of Social Cue Forecasting to leverage the larger amount of unlabeled low-level behavior cues. We propose the Social Process (SP) models--socially aware sequence-to-sequence (Seq2Seq) models within the Neural Process (NP) family.
  arXiv  Detail & Related papers  (2021-07-28T18:01:08Z)
• Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing [52.24507547010127]
  Cross-domain context-dependent semantic parsing is a new focus of research. We present a dynamic graph framework that effectively modelling contextual utterances, tokens, database schemas, and their complicated interaction as the conversation proceeds. The proposed framework outperforms all existing models by large margins, achieving new state-of-the-art performance on two large-scale benchmarks.
  arXiv  Detail & Related papers  (2021-01-05T18:11:29Z)
• Dialogue Discourse-Aware Graph Convolutional Networks for Abstractive Meeting Summarization [24.646506847760822]
  We develop a dialogue discourse-Aware Graph Convolutional Networks (DDA-GCN) for meeting summarization. We first transform the entire meeting text with dialogue discourse relations into a discourse graph and then use DDA-GCN to encode the semantic representation of the graph. Finally, we employ a Recurrent Neural Network to generate the summary.
  arXiv  Detail & Related papers  (2020-12-07T07:51:38Z)
• Graph-Based Social Relation Reasoning [101.9402771161935]
  We propose a graph relational reasoning network (GR2N) for social relation recognition. Our method considers the paradigm of jointly inferring the relations by constructing a social relation graph. Experimental results illustrate that our method generates a reasonable and consistent social relation graph.
  arXiv  Detail & Related papers  (2020-07-15T03:01:11Z)
• Recursive Social Behavior Graph for Trajectory Prediction [49.005219590582676]
  We formulate social representations supervised by group-based annotations into a social behavior graph, called Recursive Social Behavior Graph. With the guidance of Recursive Social Behavior Graph, we surpass state-of-the-art method on ETH and UCY dataset for 11.1% in ADE and 10.8% in FDE.
  arXiv  Detail & Related papers  (2020-04-22T06:01:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.