An end-to-end multi-task learning to link framework for emotion-cause pair extraction

Song, Haolin; Song, Dawei

doi:10.1117/12.2607175

Cited by 11 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two-step [1]: This model is a two-step pipeline framework based on multi-tasks. E2EECPE [3]: This method is an end-to-end based framework to predict sentiment-to-cause links. PairGCN [4]: The method uses graph convolution to model the dependencies of neighboring clauses.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Clause Level Attention Network for Emotion Cause Pair Extraction

Chen¹,

Zhang²,

Ye³

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The Emotion-Cause Pair Extraction task aims to identify one or more pairs of emotion-causes in a document, and earlier work has focused on the implicit interaction between ECPE and two auxiliary tasks Emotion Extraction and Cause Extraction. However, existing models cannot capture the complex connection between emotion and cause. To address this problem, we propose an end-to-end model. The model utilizes properties of graph attention networks (GATs) to model the bidirectional dependencies between emotion and cause clauses, and experimental results on a benchmark emotion cause corpus verify the feasibility of our approach.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Song et al [3] treated this problem as a link prediction task and learned a link from the emotion clause to the cause clause. Chen et al [4] used graph convolutional networks to emulate the dependencies of neighboring clauses.…”

Section: Related Workmentioning

confidence: 99%

Clause Level Attention Network for Emotion Cause Pair Extraction

Chen¹,

Zhang²,

Ye³

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…To solve the above problems, end-to-end models were proposed and have become the mainstream [5], [6], [28], [29] for ECPE tasks. Wei et al [6] enhanced the clause representation by Kernel-based relative position embedding.…”

Section: A Emotion-cause Analysis On Documentsmentioning

confidence: 99%

Hierarchical Shared Encoder with Task-specific Transformer Layer Selection for Emotion-Cause Pair Extraction

Su,

Huang,

et al. 2024

IEEE Trans. Affective Comput.

View full text Add to dashboard Cite

Emotion Cause Pair Extraction (ECPE) aims to extract emotions and their causes from a document. Powerful emotion and cause extraction abilities have proven essential in achieving accurate ECPE. However, most existing methods employ shared feature learning of emotion extraction and cause extraction, which can harm the abilities of both tasks as they focus on different information (i.e., task-specific features). Moreover, shared feature learning of the two tasks also leads to the label imbalance problem. To address these issues, this paper proposes a multi-task learning framework named Hierarchical Shared Encoder with Task-specific Transformer Layer Selection (HSE-TTLS). The model achieves ECPE via two subtasks: Emotion Extraction (EE) and Emotion Cause Extraction (ECE). The design of two subtasks for ECPE corresponds to the fact that cause clauses are emotion-dependent and significantly alleviates the label imbalance problem. To effectively extract task-specific features for EE and ECE, we employ BERT as the token-level encoder and select task-specific optimal layers for the two subtasks. Focal loss is used as the objective function for EE to further alleviate the label imbalance problem. Extensive experiments on benchmark ECPE corpus demonstrate the effectiveness of HSE-TTLS, which outperforms state-of-the-art baseline methods by at least 1.56% on the F1 score.

show abstract

“…Recently, some graph structure-based approaches are proposed. Song et al [53] treated ECPE as a link prediction task of directed graph; however, they did not adopt a GNN that is more suitable for graph structure modeling. Despite Fan et al [54] introduced a novel approach that regards ECPE as an action prediction task in directed graph construction; their model is not based on GNN, either.…”

Section: End-to-end Ecpementioning

confidence: 99%

A Hierarchical Heterogeneous Graph Attention Network for Emotion-Cause Pair Extraction

Liu

et al. 2022

Electronics

View full text Add to dashboard Cite

Recently, graph neural networks (GNN), due to their compelling representation learning ability, have been exploited to deal with emotion-cause pair extraction (ECPE). However, current GNN-based ECPE methods mostly concentrate on modeling the local dependency relation between homogeneous nodes at the semantic granularity of clauses or clause pairs, while they fail to take full advantage of the rich semantic information in the document. To solve this problem, we propose a novel hierarchical heterogeneous graph attention network to model global semantic relations among nodes. Especially, our method introduces all types of semantic elements involved in the ECPE, not just clauses or clause pairs. Specifically, we first model the dependency between clauses and words, in which word nodes are also exploited as an intermediary for the association between clause nodes. Secondly, a pair-level subgraph is constructed to explore the correlation between the pair nodes and their different neighboring nodes. Representation learning of clauses and clause pairs is achieved by two-level heterogeneous graph attention networks. Experiments on the benchmark datasets show that our proposed model achieves a significant improvement over 13 compared methods.

show abstract

An end-to-end multi-task learning to link framework for emotion-cause pair extraction

Cited by 11 publications

References 11 publications

Clause Level Attention Network for Emotion Cause Pair Extraction

Clause Level Attention Network for Emotion Cause Pair Extraction

Hierarchical Shared Encoder with Task-specific Transformer Layer Selection for Emotion-Cause Pair Extraction

A Hierarchical Heterogeneous Graph Attention Network for Emotion-Cause Pair Extraction

Contact Info

Product

Resources

About