Heterogenous affinity graph inference network for document-level relation extraction

Li, Rongzhen; Jiang, Zhong Ping; Xue, Zhongxuan; Dai, Qizhu; Li, Xue

doi:10.1016/j.knosys.2022.109146

Cited by 9 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use recent competitive models as baselines for comparison, including Coref [ 30 ], SSAN [ 31 ], GAIN [ 20 ], ATLOP [ 32 ], DocuNet [ 33 ], EIDER [ 34 ], SAIS [ 35 ], HAG [ 36 ], and AFLKD [ 23 ].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced Heterogeneous Graph Attention Network with a Novel Multilabel Focal Loss for Document-Level Relation Extraction

Chen,

Shi

2024

Entropy

View full text Add to dashboard Cite

Recent years have seen a rise in interest in document-level relation extraction, which is defined as extracting all relations between entities in multiple sentences of a document. Typically, there are multiple mentions corresponding to a single entity in this context. Previous research predominantly employed a holistic representation for each entity to predict relations, but this approach often overlooks valuable information contained in fine-grained entity mentions. We contend that relation prediction and inference should be grounded in specific entity mentions rather than abstract entity concepts. To address this, our paper proposes a two-stage mention-level framework based on an enhanced heterogeneous graph attention network for document-level relation extraction. Our framework employs two different strategies to model intra-sentential and inter-sentential relations between fine-grained entity mentions, yielding local mention representations for intra-sentential relation prediction and global mention representations for inter-sentential relation prediction. For inter-sentential relation prediction and inference, we propose an enhanced heterogeneous graph attention network to better model the long-distance semantic relationships and design an entity-coreference path-based inference strategy to conduct relation inference. Moreover, we introduce a novel cross-entropy-based multilabel focal loss function to address the class imbalance problem and multilabel prediction simultaneously. Comprehensive experiments have been conducted to verify the effectiveness of our framework. Experimental results show that our approach significantly outperforms the existing methods.

show abstract

Section: Methodsmentioning

confidence: 99%

“…HAG [ 36 ] proposes a heterogeneous affinity graph inference network, which utilizes coref-aware relation modeling and a noise suppression mechanism to address the long-distance reasoning challenges in document-level RE.…”

Section: Methodsmentioning

confidence: 99%

Enhanced Heterogeneous Graph Attention Network with a Novel Multilabel Focal Loss for Document-Level Relation Extraction

Chen,

Shi

2024

Entropy

View full text Add to dashboard Cite

show abstract

“…Xue et al [24] generated a latent multi-view graph using a Gaussian graph generator to capture the possible relationships among tokens. Li et al [7] devised a heterogeneous affinity graph inference network with noise suppression mechanism to build the long-distance reasoning chain in document-level RE.…”

Section: Related Workmentioning

confidence: 99%

“…Conventional works that obtained relational facts within a single sentence (sentence-level) ignored these complex facts across multiple sentences. Over the past few years, researches on the document-level RE [1][2][3][4][5][6][7] provide in-depth insights into the RE task, where transformer-based and graphbased methods are widely applied. All these methods suffer from noise in the text, and a necessary longrange semantic dependency among all mentions is a way around this issue.…”

Section: Introductionmentioning

confidence: 99%

Denoising Graph Inference Network for Document-Level Relation Extraction

Wang

Qin

Duan

et al. 2023

Big Data Min. Anal.

View full text Add to dashboard Cite

Relation Extraction (RE) is to obtain a predefined relation type of two entities mentioned in a piece of text, e.g., a sentence-level or a document-level text. Most existing studies suffer from the noise in the text, and necessary pruning is of great importance. The conventional sentence-level RE task addresses this issue by a denoising method using the shortest dependency path to build a long-range semantic dependency between entity pairs. However, this kind of denoising method is scarce in document-level RE. In this work, we explicitly model a denoised document-level graph based on linguistic knowledge to capture various long-range semantic dependencies among entities. We first formalize a Syntactic Dependency Tree forest (SDT-forest) by introducing the syntax and discourse dependency relation. Then, the Steiner tree algorithm extracts a mention-level denoised graph, Steiner Graph (SG), removing linguistically irrelevant words from the SDT-forest. We then devise a slide residual attention to highlight word-level evidence on text and SG. Finally, the classification is established on the SG to infer the relations of entity pairs. We conduct extensive experiments on three public datasets. The results evidence that our method is beneficial to establish long-range semantic dependency and can improve the classification performance with longer texts.

show abstract

Document-level relation extraction via commonsense knowledge enhanced graph representation learning

Dai,

Li,

Xue

et al. 2024

Appl Intell

View full text Add to dashboard Cite

Heterogenous affinity graph inference network for document-level relation extraction

Cited by 9 publications

References 27 publications

Enhanced Heterogeneous Graph Attention Network with a Novel Multilabel Focal Loss for Document-Level Relation Extraction

Enhanced Heterogeneous Graph Attention Network with a Novel Multilabel Focal Loss for Document-Level Relation Extraction

Denoising Graph Inference Network for Document-Level Relation Extraction

Document-level relation extraction via commonsense knowledge enhanced graph representation learning

Contact Info

Product

Resources

About