Harnessing holistic discourse features and triadic interaction for sentiment quadruple extraction in dialogues

• Main Authors: LI, Bobo, FEI, Hao, LIAO, Lizi, et al
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Feature models; Heterogeneous graph; Performance; Artificial Intelligence and Robotics; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/9640; https://ink.library.smu.edu.sg/context/sis_research/article/10640/viewcontent/Harnessing_Holistic_Discourse_Features_and_Triadic_Interaction_for_Sentiment_Quadruple_Extraction_in_Dialogues.pdf
• Institution: Singapore Management University

Dialogue Aspect-based Sentiment Quadruple (DiaASQ) is a newly-emergent task aiming to extract the sentiment quadruple (i.e., targets, aspects, opinions, and sentiments) from conversations. While showing promising performance, the prior DiaASQ approach unfortunately falls prey to the key crux of DiaASQ, including insufficient modeling of discourse features, and lacking quadruple extraction, which hinders furthertask improvement. To this end, we introduce a novel framework that not only capitalizes on comprehensive discourse feature modeling, but also captures the intrinsic interaction for optimal quadruple extraction. On the one hand, drawing upon multiple discourse features, our approach constructs a token-level heterogeneous graph and enhances token interactions through a heterogeneous attention network. We further propose a novel triadic scorer, strengthening weak token relations within a quadruple, thereby enhancing the cohesion of the quadruple extraction. Experimental results on the DiaASQ benchmark showcase that our model significantly out-performs existing baselines across both English and Chinesedatasets. Our code is available at https://bit.ly/3v27pqA.