Joint Entity and Relation Extraction with a Hybrid Transformer and Reinforcement Learning Based Model

Xiao, Ya; Tan, Chengxiang; Zhai, Fan; Xu, Qian; Zhu, Wei

doi:10.1609/aaai.v34i05.6471

Cited by 27 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past several years, the deep learning-based entity relationship extraction has become a research hotspot, as it alleviates the problem of error labelling and feature extraction error propagation in a distant supervised data set. The approaches mainly include convolutional neural networks (Li et al , 2020a, 2020b; Santos et al , 2015; Zeng et al , 2014), recurrent neural networks (Katiyar and Cardie, 2017; Tourille et al , 2017), generative adversarial networks (Qin et al , 2018), deep reinforcement learning (Xiao et al , 2020) and so on. For example, Zeng et al (2014) proposed using the word vector and the word position vector as the input of the convolutional neural network (CNN) and introduced the distance information between the entity and other words, which can well take the entity information in the sentence into account for relation extraction.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The experimental results demonstrated that the proposed strategy performs better than other state-of-the-art methods. Xiao et al (2020) proposed a hybrid deep learning model by using a deep reinforcement learning module adapted from a transformer-based encoder and LSTM-based entity embedding, which improves the relation classification and noisy data filtering. Generally, the deep learning-based methods have achieved better results, compared with traditional machine learning.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Towards an entity relation extraction framework in the cross-lingual context

Xue

Wang

et al. 2021

View full text Add to dashboard Cite

Purpose Owing to the uneven distribution of annotated corpus among different languages, it is necessary to bridge the gap between low resource languages and high resource languages. From the perspective of entity relation extraction, this paper aims to extend the knowledge acquisition task from a single language context to a cross-lingual context, and to improve the relation extraction performance for low resource languages. Design/methodology/approach This paper proposes a cross-lingual adversarial relation extraction (CLARE) framework, which decomposes cross-lingual relation extraction into parallel corpus acquisition and adversarial adaptation relation extraction. Based on the proposed framework, this paper conducts extensive experiments in two tasks, i.e. the English-to-Chinese and the English-to-Arabic cross-lingual entity relation extraction. Findings The Macro-F1 values of the optimal models in the two tasks are 0.880 1 and 0.789 9, respectively, indicating that the proposed CLARE framework for CLARE can significantly improve the effect of low resource language entity relation extraction. The experimental results suggest that the proposed framework can effectively transfer the corpus as well as the annotated tags from English to Chinese and Arabic. This study reveals that the proposed approach is less human labour intensive and more effective in the cross-lingual entity relation extraction than the manual method. It shows that this approach has high generalizability among different languages. Originality/value The research results are of great significance for improving the performance of the cross-lingual knowledge acquisition. The cross-lingual transfer may greatly reduce the time and cost of the manual construction of the multi-lingual corpus. It sheds light on the knowledge acquisition and organization from the unstructured text in the era of big data.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Towards an entity relation extraction framework in the cross-lingual context

Xue

Wang

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Another related direction is the policy-based reinforcement learning (Williams, 1992;Sutton et al, 2000). Previous methods (Xiong et al, 2017;Xiao et al, 2020) usually affect the training of the main task by a policy network with separate parameters. Different from them, we directly regard the main network as the policy network and its output graph as the action distribution.…”

Section: Related Workmentioning

confidence: 99%

Efficient Mind-Map Generation via Sequence-to-Graph and Reinforced Graph Refinement

Hu¹,

Guo²,

Zhao³

et al. 2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

A mind-map is a diagram that represents the central concept and key ideas in a hierarchical way. Converting plain text into a mindmap will reveal its key semantic structure and be easier to understand. Given a document, the existing automatic mind-map generation method extracts the relationships of every sentence pair to generate the directed semantic graph for this document. The computation complexity increases exponentially with the length of the document. Moreover, it is difficult to capture the overall semantics. To deal with the above challenges, we propose an efficient mind-map generation network that converts a document into a graph via sequenceto-graph. To guarantee a meaningful mindmap, we design a graph refinement module to adjust the relation graph in a reinforcement learning manner. Extensive experimental results demonstrate that the proposed approach is more effective and efficient than the existing methods. The inference time is reduced by thousands of times compared with the existing methods. The case studies verify that the generated mind-maps better reveal the underlying semantic structures of the document.

show abstract

“…External knowledge like entity descriptions and type information has been used for RE (Yaghoobzadeh et al, 2017;Vashishth et al, 2018). Pre-trained language models contain a notable amount of semantic information and commonsense knowledge, and several works have applied them to RE (Alt et al, 2019;Xiao et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction

Hao¹,

Yu²,

Hu³

2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Distantly supervised relation extraction (RE) automatically aligns unstructured text with relation instances in a knowledge base (KB). Due to the incompleteness of current KBs, sentences implying certain relations may be annotated as N/A instances, which causes the socalled false negative (FN) problem. Current RE methods usually overlook this problem, inducing improper biases in both training and testing procedures. To address this issue, we propose a two-stage approach. First, it finds out possible FN samples by heuristically leveraging the memory mechanism of deep neural networks. Then, it aligns those unlabeled data with the training data into a unified feature space by adversarial training to assign pseudo labels and further utilize the information contained in them. Experiments on two wildlyused benchmark datasets demonstrate the effectiveness of our approach.

show abstract

Joint Entity and Relation Extraction with a Hybrid Transformer and Reinforcement Learning Based Model

Cited by 27 publications

References 23 publications

Towards an entity relation extraction framework in the cross-lingual context

Towards an entity relation extraction framework in the cross-lingual context

Efficient Mind-Map Generation via Sequence-to-Graph and Reinforced Graph Refinement

Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction

Contact Info

Product

Resources

About