Multi-view Inference for Relation Extraction with Uncertain Knowledge

Li, Bo; Ye, Wei; Huang, Canming; Zhang, Shikun

doi:10.1609/aaai.v35i15.17563

Cited by 17 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Structured Self-Attention Network (SSAN) ( Xu et al, 2021 ): A model that effectively combines such a structural prior while interactively performing contextual and structural inference of entities. Multi-view Inference framework for relation extraction with uncertain knowledge (MIUK) ( Li et al, 2021 ): This model designs a multi-view reasoning framework, which systematically integrates local context and global knowledge in reference view, entity view and concept view. Adaptive Thresholding and Localized cOntext Pooling (ATLOP) ( Zhou et al, 2021 ): This model proposes adaptive threshold and local context pooling techniques, which help alleviate the multi-entity problem.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing cross-evidence reasoning graph for document-level relation extraction

Pi,

Lu,

Zhu

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

The objective of document-level relation extraction (RE) is to identify the semantic connections that exist between named entities present within a document. However, most entities are distributed among different sentences, there is a need for inter-entity relation prediction across sentences. Existing research has focused on framing sentences throughout documents to predict relationships between entities. However, not all sentences play a substantial role in relation extraction, which inevitably introduces noisy information. Based on this phenomenon, we believe that we can extract evidence sentences in advance and use these evidence sentences to construct graphs to mine semantic information between entities. Thus, we present a document-level RE model that leverages an Enhancing Cross-evidence Reasoning Graph (ECRG) for improved performance. Specifically, we design an evidence extraction rule based on center-sentence to pre-extract higher-quality evidence. Then, this evidence is constructed into evidence graphs to mine the connections between mentions within the same evidence. In addition, we construct entity-level graphs by aggregating mentions from the same entities within the evidence graphs, aiming to capture distant interactions between entities. Experiments result on both DocRED and RE-DocRED datasets demonstrate that our model improves entity RE performance compared to existing work.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Multi-view Inference framework for relation extraction with uncertain knowledge (MIUK) ( Li et al, 2021 ): This model designs a multi-view reasoning framework, which systematically integrates local context and global knowledge in reference view, entity view and concept view.…”

Section: Methodsmentioning

confidence: 99%

Enhancing cross-evidence reasoning graph for document-level relation extraction

Pi,

Lu,

Zhu

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…DocuNet (Zhang et al, 2021) and KD-DocRE (Tan et al, 2022a) extended the ATLOP architecture by increasing interactions between entities and incorporating knowledge distillation, respectively. Besides, other DocRE models attempted to leverage auxiliary information for relation prediction, such as meta dependency paths (Nan et al, 2020), external knowledge bases (Li et al, 2021a), and evidences (Xie et al, 2022;Xiao et al, 2022). We additionally provide detailed comparison with existing works in Section 3.3.…”

Section: Related Work Document-level Relation Extraction (Docre)mentioning

confidence: 99%

Towards Integration of Discriminability and Robustness for Document-Level Relation Extraction

Guo,

Kok,

Bing

2023

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

View full text Add to dashboard Cite

Document-level relation extraction (DocRE)predicts relations for entity pairs that rely on long-range context-dependent reasoning in a document. As a typical multi-label classification problem, DocRE faces the challenge of effectively distinguishing a small set of positive relations from the majority of negative ones. This challenge becomes even more difficult to overcome when there exists a significant number of annotation errors in the dataset. In this work, we aim to achieve better integration of both the discriminability and robustness for the DocRE problem. Specifically, we first design an effective loss function to endow high discriminability to both probabilistic outputs and internal representations. We innovatively customize entropy minimization and supervised contrastive learning for the challenging multi-label and long-tailed learning problems. To ameliorate the impact of label errors, we equipped our method with a novel negative label sampling strategy to strengthen the model robustness. In addition, we introduce two new data regimes to mimic more realistic scenarios with annotation errors and evaluate our sampling strategy. Experimental results verify the effectiveness of each component and show that our method achieves new state-ofthe-art results on the DocRED dataset, its recently cleaned version, Re-DocRED, and the proposed data regimes. 1 * * This work was partially done when Jia Guo was an intern at DAMO Academy, Alibaba Group.

show abstract

“…Also, there are lots of works modified convolutional neural network and recurrent neural network for RE (Santos, Xiang, and Zhou 2015;Miwa and Bansal 2016). Recently, transformer-based methods which leverage PLMs have shown impressive performances on RE (Yamada et al 2020;Xue et al 2021;Li et al 2020Li et al , 2021Roy and Pan 2021;Zhou and Chen 2021;Lyu and Chen 2021). These methods used the PLMs such as BERT and Roberta as backbone network, and designed novel components or multi-task learning framework for better performance.…”

Section: Related Workmentioning

confidence: 99%

Reviewing Labels: Label Graph Network with Top-k Prediction Set for Relation Extraction

Zhang

et al. 2023

AAAI

View full text Add to dashboard Cite

The typical way for relation extraction is fine-tuning large pre-trained language models on task-specific datasets, then selecting the label with the highest probability of the output distribution as the final prediction. However, the usage of the Top-k prediction set for a given sample is commonly overlooked. In this paper, we first reveal that the Top-k prediction set of a given sample contains useful information for predicting the correct label. To effectively utilizes the Top-k prediction set, we propose Label Graph Network with Top-k Prediction Set, termed as KLG. Specifically, for a given sample, we build a label graph to review candidate labels in the Top-k prediction set and learn the connections between them. We also design a dynamic k selection mechanism to learn more powerful and discriminative relation representation. Our experiments show that KLG achieves the best performances on three relation extraction datasets. Moreover, we observe thatKLG is more effective in dealing with long-tailed classes.

show abstract

Multi-view Inference for Relation Extraction with Uncertain Knowledge

Cited by 17 publications

References 16 publications

Enhancing cross-evidence reasoning graph for document-level relation extraction

Enhancing cross-evidence reasoning graph for document-level relation extraction

Towards Integration of Discriminability and Robustness for Document-Level Relation Extraction

Reviewing Labels: Label Graph Network with Top-k Prediction Set for Relation Extraction

Contact Info

Product

Resources

About