Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction
Dialogue-based relation extraction (DiaRE) aims to detect the structural information from unstructured utterances in dialogues. Existing relation extraction models may be unsatisfactory under such a conversational setting, due to the entangled logic and information sparsity issues in utterances involving multiple speakers. To this end, we introduce SOLS, a novel model which can explicitly induce speaker-oriented latent structures for better DiaRE. Specifically, we learn latent structures to capture the relationships among tokens beyond the utterance boundaries, alleviating the entangled logic issue. During the learning process, our speaker-specific regularization method progressively highlights speaker-related key clues and erases the irrelevant ones, alleviating the information sparsity issue. Experiments on three public datasets demonstrate the effectiveness of our proposed approach.
Code (1)
Tasks
Dialog Relation ExtractionRelationRelation ExtractionSimilar Papers 제목 키워드 기반
Dependency Dialogue Acts -- Annotation Scheme and Case Study
In this paper, we introduce Dependency Dialogue Acts (DDA), a novel framework for capturing the structure of speaker-intentions in multi-party dialogues. DDA combines and adapts features from existing dialogue annotation…
Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph
Conversational semantic role labeling (CSRL) is a newly proposed task that uncovers the shallow semantic structures in a dialogue text. Unfortunately several important characteristics of the CSRL task have been overlooke…
Language ModelingLanguage ModellingSemantic Role LabelingDER-GCN: Dialogue and Event Relation-Aware Graph Convolutional Neural Network for Multimodal Dialogue Emotion Recognition
With the continuous development of deep learning (DL), the task of multimodal dialogue emotion recognition (MDER) has recently received extensive research attention, which is also an essential branch of DL. The MDER aims…
Contrastive LearningEmotion RecognitionMultimodal Emotion RecognitionRepresentation LearningCSDS: A Fine-Grained Chinese Dataset for Customer Service Dialogue Summarization
Dialogue summarization has drawn much attention recently. Especially in the customer service domain, agents could use dialogue summaries to help boost their works by quickly knowing customer's issues and service progress…
AtmosERC: Modeling Dialogue-Level Affective Atmosphere for Emotion Recognition in Conversation
Emotion Recognition in Conversation (ERC) aims to predict utterance-level emotions in dialogues and has largely advanced through context-centric modeling. However, global context is a heterogeneous signal, and not all co…
Emotion Recognition in Conversation