Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations

Sun, Kai; Zhang, Richong; Mensah, Samuel; Mao, Yongyi; Li, Xudong

doi:10.18653/v1/2020.emnlp-main.304

Cited by 25 publications

(8 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare our model with three kinds of models in recent years: (1) seq2seq-based methods, including CopyRE [5] and WDec [14], (2) MLT-based methods, including GraphRel [18], CopyMTL [16] and RIN [19], (3) tagging-based methods, including NovelTagging [4], ETL-Span [7] and CasRel [8]. Table I shows the results of our models and other baseline methods.…”

Section: Comparison Models and Resultsmentioning

confidence: 99%

“…[18] gained considerable improvement through building relation-weighted graph convolutional networks (GCN). [19] designed a novel multitask learning architecture that enables dynamic interaction and mutual learning between NER and RC, which improves the ability to extract triples. Although effective, they lack the elegance to handle complex scenarios, such as EPO cases.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Attention Guided Filter for Jointly Extracting Entities and Classifying Relations

Chen¹

2021

Proceedings of the 33rd International Conference on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

Jointly extracting entities and classifying relations aims to detect all possible triples from unstructured text with a single model. Tagging-based method effectively improves the performance of jointly relation extraction. However, some taggingbased approaches ignored that one entity pair may exist multiple relations and others set an empirical threshold value for selecting one or more relevant relations, which becomes the bottlenecks of the model. As a solution, we propose the attention guided filter, namely, AGFRel, which introduces transformer blocks to learn the number of relations for every entity pair to filter out irrelevant relations. Moreover, each module of the model has a multi-head attention guided layer to highlight valuable information. Extensive experimental results show that AGFRel is capable of gaining better performance on various tasks including overlapping triples extraction and multiple triples extraction. On NYT and WebNLG public datasets, our model obtains F1 score 90.8 and 91.9 respectively and achieves a new state-of-the-art performance.

show abstract

Section: Comparison Models and Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Attention Guided Filter for Jointly Extracting Entities and Classifying Relations

Chen¹

2021

Proceedings of the 33rd International Conference on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

show abstract

“…On all datasets, we run our model 5 times and the averaged results are taken as the final reported results. Baselines Following strong state-of-the-art models are taken as baselines, including: ETL-Span [26], WDec [16], RSAN [27], RIN [19], CasRel [24], TPLinker [23], StereoRel [22], PRGC [33], R-BPtrNet [3], PMEI [20], and CGT [25]. Most results of these baselines are copied from their original papers directly.…”

Section: Experiments 41 Experiments Settingsmentioning

confidence: 99%

A Simple but Effective Bidirectional Framework for Relational Triple Extraction

Ren

Zhang

Zhao

et al. 2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Tagging based relational triple extraction methods are attracting growing research attention recently. However, most of these methods take a unidirectional extraction framework that first extracts all subjects and then extracts objects and relations simultaneously based on the subjects extracted. This framework has an obvious deficiency that it is too sensitive to the extraction results of subjects. To overcome this deficiency, we propose a bidirectional extraction framework based method that extracts triples based on the entity pairs extracted from two complementary directions. Concretely, we first extract all possible subject-object pairs from two paralleled directions. These two extraction directions are connected by a shared encoder component, thus the extraction features from one direction can flow to another direction and vice versa. By this way, the extractions of two directions can boost and complement each other. Next, we assign all possible relations for each entity pair by a biaffine model. During training, we observe that the share structure will lead to a convergence rate inconsistency issue which is harmful to performance. So we propose a share-aware learning mechanism to address it. We evaluate the proposed model on multiple benchmark datasets. Extensive experimental results show that the proposed model is very effective and it achieves state-of-the-art results on all of these datasets. Moreover, experiments show that both the proposed bidirectional extraction framework and the share-aware learning mechanism have good adaptability and can be used to improve the performance of other tagging based methods. The source code of our work is available at: https://github.com/neukg/BiRTE.

show abstract

“…Baselines We compare our model with following strong state-of-the-art RTE models: CopyRE (Zeng et al, 2018), GraphRel (Fu et al, 2019), Copy-MTL , OrderCopyRE (Zeng et al, 2019), ETL-Span (Yu et al, 2019), WDec (Nayak and Ng, 2020), RSAN , RIN (Sun et al, 2020), CasRel (Wei et al, 2020), TPLinker , SPN (Sui et al, 2020), and PMEI (Sun et al, 2021).…”

Section: Experimental Settingsmentioning

confidence: 99%

A Novel Global Feature-Oriented Relational Triple Extraction Model based on Table Filling

Ren

Zhang

Yin

et al. 2021

Preprint

View full text Add to dashboard Cite

Table filling based relational triple extraction methods are attracting growing research interests due to their promising performance and their abilities on extracting triples from complex sentences. However, this kind of methods are far from their full potential because most of them only focus on using local features but ignore the global associations of relations and of token pairs, which increases the possibility of overlooking some important information during triple extraction. To overcome this deficiency, we propose a global feature-oriented triple extraction model that makes full use of the mentioned two kinds of global associations. Specifically, we first generate a table feature for each relation. Then two kinds of global associations are mined from the generated table features. Next, the mined global associations are integrated into the table feature of each relation. This "generate-mine-integrate" process is performed multiple times so that the table feature of each relation is refined step by step. Finally, each relation's table is filled based on its refined table feature, and all triples linked to this relation are extracted based on its filled table. We evaluate the proposed model on three benchmark datasets. Experimental results show our model is effective and it achieves state-of-the-art results on all of these datasets.

show abstract

Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations

Cited by 25 publications

References 38 publications

Attention Guided Filter for Jointly Extracting Entities and Classifying Relations

Attention Guided Filter for Jointly Extracting Entities and Classifying Relations

A Simple but Effective Bidirectional Framework for Relational Triple Extraction

A Novel Global Feature-Oriented Relational Triple Extraction Model based on Table Filling

Contact Info

Product

Resources

About