TY - JOUR
T1 - A knowledge-guided graph attention network for emotion-cause pair extraction
AU - Zhu, Peican
AU - Wang, Botao
AU - Tang, Keke
AU - Zhang, Haifeng
AU - Cui, Xiaodong
AU - Wang, Zhen
N1 - Publisher Copyright:
© 2023 Elsevier B.V.
PY - 2024/2/28
Y1 - 2024/2/28
N2 - Emotion-Cause Pair Extraction (ECPE) is a research objective focused on identifying and extracting all emotion-clause and cause-clause pairs from unannotated emotional text. Traditional methodologies have predominantly employed attention mechanisms or joint learning techniques for feature information interaction. However, these approaches often overlook the aggregation of features under the guidance of external knowledge. To enhance performance in addressing this ECPE challenge, we propose a novel knowledge-guided graph attention network, i.e., GAT-ECPE. This model chiefly relies on an interclause dependency graph as a guiding principle. By employing this knowledge-guided graph attention network, we can proficiently combine semantic and structural information between clauses. In addition, an interpair possibility graph, derived from the outcomes of subtasks, is integrated as an additional guiding principle. As such, we are able to aggregate features between clause pairs, thereby facilitating interaction between multiple tasks. Extensive experiments were conducted to validate our proposed model, and the obtained results demonstrate its superiority when compared to 12 considered baselines. In terms of performance metrics, our model achieves an F1 score F1 of 74.92% and a recall R of 77.52%. These values significantly outperform those achieved by state-of-the-art approaches, indicating the effectiveness and superiority of our GAT-ECPE.
AB - Emotion-Cause Pair Extraction (ECPE) is a research objective focused on identifying and extracting all emotion-clause and cause-clause pairs from unannotated emotional text. Traditional methodologies have predominantly employed attention mechanisms or joint learning techniques for feature information interaction. However, these approaches often overlook the aggregation of features under the guidance of external knowledge. To enhance performance in addressing this ECPE challenge, we propose a novel knowledge-guided graph attention network, i.e., GAT-ECPE. This model chiefly relies on an interclause dependency graph as a guiding principle. By employing this knowledge-guided graph attention network, we can proficiently combine semantic and structural information between clauses. In addition, an interpair possibility graph, derived from the outcomes of subtasks, is integrated as an additional guiding principle. As such, we are able to aggregate features between clause pairs, thereby facilitating interaction between multiple tasks. Extensive experiments were conducted to validate our proposed model, and the obtained results demonstrate its superiority when compared to 12 considered baselines. In terms of performance metrics, our model achieves an F1 score F1 of 74.92% and a recall R of 77.52%. These values significantly outperform those achieved by state-of-the-art approaches, indicating the effectiveness and superiority of our GAT-ECPE.
KW - Emotion-cause pair extraction
KW - Graph attention network
KW - Multi-task learning
UR - http://www.scopus.com/inward/record.url?scp=85182700127&partnerID=8YFLogxK
U2 - 10.1016/j.knosys.2023.111342
DO - 10.1016/j.knosys.2023.111342
M3 - 文章
AN - SCOPUS:85182700127
SN - 0950-7051
VL - 286
JO - Knowledge-Based Systems
JF - Knowledge-Based Systems
M1 - 111342
ER -