Litcius/Paper detail

Graph Based Network with Contextualized Representations of Turns in Dialogue

Bongseok Lee, Yong Suk Choi

2021Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing44 citationsDOIOpen Access PDF

Abstract

to extract relation(s) between two arguments that appear in a dialogue. Because dialogues have the characteristics of high personal pronoun occurrences and low information density, and since most relational facts in dialogues are not supported by any single sentence, dialogue-based relation extraction requires a comprehensive understanding of dialogue. In this paper, we propose the TUrn COntext awaRE Graph Convolutional Network (TUCORE-GCN) modeled by paying attention to the way people understand dialogues. In addition, we propose a novel approach which treats the task of emotion recognition in conversations (ERC) as a dialoguebased RE. Experiments on a dialogue-based RE dataset and three ERC datasets demonstrate that our model is very effective in various dialogue-based natural language understanding tasks.

Topics & Concepts

Computer scienceRelation (database)Natural language processingRelationship extractionTask (project management)SentenceArtificial intelligenceBenchmark (surveying)GraphContext (archaeology)PronounCode (set theory)Information extractionTheoretical computer scienceLinguisticsData miningSet (abstract data type)ManagementGeographyPhilosophyEconomicsGeodesyBiologyProgramming languagePaleontologyTopic ModelingSentiment Analysis and Opinion MiningNatural Language Processing Techniques
Graph Based Network with Contextualized Representations of Turns in Dialogue | Litcius