Joint Extraction of Entities and Overlapping Relations Using Position-Attentive Sequence Labeling

Dai, Dai; Xiao, Xinyan; Lyu, Yajuan; Dou, Shan; She, Qiaoqiao; Wang, Haifeng

doi:10.1609/aaai.v33i01.33016300

Cited by 114 publications

(101 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, we hope to improve our work by the utilization of better model-based pattern extractor, and resorting to latent variable model (Kim et al, 2018) for jointly modeling instance selector. What is more, we also hope to verify the effectiveness of our method on more tasks, including open information extraction and event extraction, and also overlapping relation extraction models (Dai et al, 2019).…”

Section: Resultsmentioning

confidence: 89%

ARNOR: Attention Regularization based Noise Reduction for Distant Supervision Relation Classification

Jia¹,

Dai²,

Xiao³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

Distant supervision is widely used in relation classification in order to create large-scale training data by aligning a knowledge base with an unlabeled corpus. However, it also introduces amounts of noisy labels where a contextual sentence actually does not express the labeled relation. In this paper, we propose ARNOR, a novel Attention Regularization based NOise Reduction framework for distant supervision relation classification. ARNOR assumes that a trustable relation label should be explained by the neural attention model. Specifically, our ARNOR framework iteratively learns an interpretable model and utilizes it to select trustable instances. We first introduce attention regularization to force the model to pay attention to the patterns which explain the relation labels, so as to make the model more interpretable. Then, if the learned model can clearly locate the relation patterns of a candidate instance in training set, we will select it as a trustable instance for further training step. According to the experiments on NYT data, our ARNOR framework achieves significant improvements over state-of-the-art methods in both relation classification performance and noise reduction effect.

show abstract

Section: Resultsmentioning

confidence: 89%

ARNOR: Attention Regularization based Noise Reduction for Distant Supervision Relation Classification

Jia¹,

Dai²,

Xiao³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Previous neural methods proposed for jointly extracting entities and relations can generally be categorized into three classes. The first class models the joint extraction task as a sequence labeling problem Dai et al, 2019;Takanobu et al, 2019;Yu et al, 2019). Among the proposed works, was the first to introduce a tagging strategy to address the problem, transferring the joint extraction task to a sequence labelling problem.…”

Section: Related Workmentioning

confidence: 99%

“…However, this method has the fundamental weakness of addressing the overlapping problem of relational facts in the text. To meet it, (Dai et al, 2019) proposed a position-attentive tagging scheme to solve the overlapping problem. Meanwhile, (Takanobu et al, 2019;Yu et al, 2019) approach the problem by decomposing the joint extraction task into two sequence labeling sub-tasks, to address the joint entity and relation extraction problem.…”

Section: Related Workmentioning

confidence: 99%

Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations

Sun¹,

Zhang²,

Mensah³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

The idea of using multi-task learning approaches to address the joint extraction of entity and relation is motivated by the relatedness between the entity recognition task and the relation classification task. Existing methods using multi-task learning techniques to address the problem learn interactions among the two tasks through a shared network, where the shared information is passed into the taskspecific networks for prediction. However, such an approach hinders the model from learning explicit interactions between the two tasks to improve the performance on the individual tasks. As a solution, we design a multitask learning model which we refer to as recurrent interaction network which allows the learning of interactions dynamically, to effectively model task-specific features for classification. Empirical studies on two real-world datasets confirm the superiority of the proposed model.

show abstract

“…To address the overlapping issue, many entity-guided joint learning methods, such as PA-LSTM [Dai et al, 2019] and ETL-Span [Yu et al, 2020] are proposed. They perform head entities recognition as the first step, and develop some joint decoding strategies for extracting the corresponding tail entities and relations.…”

Section: Introductionmentioning

confidence: 99%

A Relation-Specific Attention Network for Joint Entity and Relation Extraction

Yuan

Zhou

Pan

et al. 2020

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Joint extraction of entities and relations is an important task in natural language processing (NLP), which aims to capture all relational triplets from plain texts. This is a big challenge due to some of the triplets extracted from one sentence may have overlapping entities. Most existing methods perform entity recognition followed by relation detection between every possible entity pairs, which usually suffers from numerous redundant operations. In this paper, we propose a relation-specific attention network (RSAN) to handle the issue. Our RSAN utilizes relation-aware attention mechanism to construct specific sentence representations for each relation, and then performs sequence labeling to extract its corresponding head and tail entities. Experiments on two public datasets show that our model can effectively extract overlapping triplets and achieve state-of-the-art performance.

show abstract

Joint Extraction of Entities and Overlapping Relations Using Position-Attentive Sequence Labeling

Cited by 114 publications

References 18 publications

ARNOR: Attention Regularization based Noise Reduction for Distant Supervision Relation Classification

ARNOR: Attention Regularization based Noise Reduction for Distant Supervision Relation Classification

Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations

A Relation-Specific Attention Network for Joint Entity and Relation Extraction

Contact Info

Product

Resources

About