Exploring Long Tail Data in Distantly Supervised Relation Extraction

Gui, Yaocheng; Liu, Qian; Zhu, Man; Gao, Zhiqiang

doi:10.1007/978-3-319-50496-4_44

Cited by 9 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are few studies on long-tail relation extraction, among which Gui et al [24] proposed an explanation-based approach, while Lei et al [25] utilized external knowledge (logic rules); later studies focused on datasets with hierarchical structures, such as NYT, Han et al [26] proposed a hierarchical attention mechanism scheme for long-tail relations in relation extraction, Zhang et al [27] combined the embedding representation obtained after pre-training by graph convolutional networks [28] into the hierarchical structure of relations, but this class of methods does not work well on other datasets, so this paper uses the traditional approach, i.e., mitigating the data imbalance problem by increasing the loss of small class samples.…”

Section: Related Workmentioning

confidence: 99%

Medical Relation Extraction from Electronic Medical Records

2022

Proceedings of WCSE 2022 Spring Event: 2022 9th International Conference on Industrial Engineering and Applications

View full text Add to dashboard Cite

In the field of natural language processing, relation extraction (RE) aims to identify the relationship between entities from text and is a vital step for subsequent tasks such as question answering and Knowledge Graph (KG). Comparing to the general domain text the relationship extraction from electronic medical records (EMRs) is more challenging due to the high-density distribution of entities of EMRs. In addition, relationship extraction usually suffers from the long-tail problem. The training data mainly focuses on a few types of relations, leading to the lack of sufficient annotations for the remaining types of relations, which is more severe in electronic medical records. To address the above problems, this paper proposes a segmented attentional Convolutional Neural Network (CNN+SegAtt) for medical relationship extraction and combines it with modified typed entity representations, which significantly improve the semantic learning ability from electronic medical records. A loss function with category weights is also proposed to facilitate the extraction of long-tail relationships. Experiments are conducted on the publicly available medical corpus 2010 i2b2/VA. The results show that the value of F1 reached 73.13%, better than that of existing methods, and the values of F1 for the small category samples are also significantly improved.

show abstract

Section: Related Workmentioning

confidence: 99%

Medical Relation Extraction from Electronic Medical Records

2022

Proceedings of WCSE 2022 Spring Event: 2022 9th International Conference on Industrial Engineering and Applications

View full text Add to dashboard Cite

show abstract

“…Krause et al [50] develop an RE system, which can automatically learn the rules for long-tailed relations from Web. To generate fewer but more precise rules, Gui et al [51] apply explanation-based learning to improve the RE system. However, the above methods merely handle each relation in isolation, regardless of the implicit associations between relations.…”

Section: Long-tailed Relation Extraction In Dsrementioning

confidence: 99%

Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs

Liang¹,

Liu²,

Liu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Label noise and long-tailed distributions are two major challenges in distantly supervised relation extraction. Recent studies have shown great progress on denoising, but pay little attention to the problem of long-tailed relations. In this paper, we introduce constraint graphs to model the dependencies between relation labels. On top of that, we further propose a novel constraint graph-based relation extraction framework(CGRE) to handle the two challenges simultaneously. CGRE employs graph convolution networks (GCNs) to propagate information from data-rich relation nodes to data-poor relation nodes, and thus boosts the representation learning of long-tailed relations. To further improve the noise immunity, a constraint-aware attention module is designed in CGRE to integrate the constraint information. Experimental results on a widely-used benchmark dataset indicate that our approach achieves significant improvements over the previous methods for both denoising and long-tailed relation extraction. Our dataset and codes are available at https://github.com/tmliang/CGRE.

show abstract

“…There are only a few studies on long-tail for RE (Gui et al, 2016;Lei et al, 2018;Han et al, 2018b). Of these, (Gui et al, 2016) proposed an explanation-based approach, whereas (Lei et al, 2018) utilized external knowledge (logic rules). These studies treat each relation in isolation, regardless of the rich semantic correlations between the relations.…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks

Zhang

Deng

Sun

et al. 2019

Proceedings of the 2019 Conference of the North

221

View full text Add to dashboard Cite

We propose a distance supervised relation extraction approach for long-tailed, imbalanced data which is prevalent in real-world settings. Here, the challenge is to learn accurate "fewshot" models for classes existing at the tail of the class distribution, for which little data is available. Inspired by the rich semantic correlations between classes at the long tail and those at the head, we take advantage of the knowledge from data-rich classes at the head of the distribution to boost the performance of the data-poor classes at the tail. First, we propose to leverage implicit relational knowledge among class labels from knowledge graph embeddings and learn explicit relational knowledge using graph convolution networks. Second, we integrate that relational knowledge into relation extraction model by coarse-tofine knowledge-aware attention mechanism. We demonstrate our results for a large-scale benchmark dataset which show that our approach significantly outperforms other baselines, especially for long-tail relations.1

show abstract

Exploring Long Tail Data in Distantly Supervised Relation Extraction

Cited by 9 publications

References 12 publications

Medical Relation Extraction from Electronic Medical Records

Medical Relation Extraction from Electronic Medical Records

Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs

Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks

Contact Info

Product

Resources

About