Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning

Qin, Pengda; Wang, Xu; Wang, William Yang

doi:10.18653/v1/p18-1199

Cited by 210 publications

(152 citation statements)

References 20 publications

Supporting

Mentioning

150

Contrasting

Order By: Relevance

“…work focuses on sentence-level RE, i.e., extracting relational facts from a single sentence. In recent years, various neural models have been explored to encode relational patterns of entities for sentence-level RE, and achieve state-of-theart performance (Socher et al, 2012;Zeng et al, 2014Zeng et al, , 2015dos Santos et al, 2015;Xiao and Liu, 2016;Cai et al, 2016;Lin et al, 2016;Wu et al, 2017;Qin et al, 2018;Han et al, 2018a).…”

Section: Introductionmentioning

confidence: 99%

DocRED: A Large-Scale Document-Level Relation Extraction Dataset

Yao

et al. 2019

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

376

417

View full text Add to dashboard Cite

Multiple entities in a document generally exhibit complex inter-sentence relations, and cannot be well handled by existing relation extraction (RE) methods that typically focus on extracting intra-sentence relations for single entity pairs. In order to accelerate the research on document-level RE, we introduce DocRED, a new dataset constructed from Wikipedia and Wikidata with three features: (1) DocRED annotates both named entities and relations, and is the largest humanannotated dataset for document-level RE from plain text; (2) DocRED requires reading multiple sentences in a document to extract entities and infer their relations by synthesizing all information of the document; (3) along with the human-annotated data, we also offer large-scale distantly supervised data, which enables DocRED to be adopted for both supervised and weakly supervised scenarios. In order to verify the challenges of documentlevel RE, we implement recent state-of-the-art methods for RE and conduct a thorough evaluation of these methods on DocRED. Empirical results show that DocRED is challenging for existing RE methods, which indicates that document-level RE remains an open problem and requires further efforts. Based on the detailed analysis on the experiments, we discuss multiple promising directions for future research. We make DocRED and the code for our baselines publicly available at https: //github.com/thunlp/DocRED. * indicates equal contribution

show abstract

Section: Introductionmentioning

confidence: 99%

DocRED: A Large-Scale Document-Level Relation Extraction Dataset

Yao

et al. 2019

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

376

417

View full text Add to dashboard Cite

show abstract

“…com/tyliupku/soft-label-RE. Table 5: AUC values of previous work and our models, where ATT BL+DSGAN and ATT BL+RL are two models proposed in (Qin et al, 2018a) and (Qin et al, 2018b) respectively, † indicates the baseline result reported in (Qin et al, 2018a,b) and ‡ indicates the baseline result given by our implementation.…”

Section: Pr Curvesmentioning

confidence: 99%

Distant Supervision Relation Extraction with Intra-Bag and Inter-Bag Attentions

Ye¹,

Ling²

2019

Proceedings of the 2019 Conference of the North

105

View full text Add to dashboard Cite

This paper presents a neural relation extraction method to deal with the noisy training data generated by distant supervision. Previous studies mainly focus on sentence-level de-noising by designing neural networks with intra-bag attentions. In this paper, both intrabag and inter-bag attentions are considered in order to deal with the noise at sentence-level and bag-level respectively. First, relationaware bag representations are calculated by weighting sentence embeddings using intrabag attentions. Here, each possible relation is utilized as the query for attention calculation instead of only using the target relation in conventional methods. Furthermore, the representation of a group of bags in the training set which share the same relation label is calculated by weighting bag representations using a similarity-based inter-bag attention module. Finally, a bag group is utilized as a training sample when building our relation extractor. Experimental results on the New York Times dataset demonstrate the effectiveness of our proposed intra-bag and inter-bag attention modules. Our method also achieves better relation extraction accuracy than state-of-the-art methods on this dataset 1 .

show abstract

“…DSGAN (Qin et al, 2018a), a GAN-based method, was also used to recognize true positive instances from noisy datasets. To further alleviate the effect of wrong labeling problem, soft-label training algorithm (Liu et al, 2017b), reinforcement learning methods (Feng et al, 2018;Qin et al, 2018b) and additional side information (Vashishth et al, 2018;Wang et al, 2018) have been used. Most recently, a few methods focused on the pre-training embeddings for word tokens and relations including adversarial training (Wu et al, 2017), transfer learning (Liu et al, 2018) and relation decoder (Su et al, 2018).…”

Section: Related Workmentioning

confidence: 99%

Untitled

Zhang

Jia

et al. 2019

Proceedings of the 2019 Conference of the North

View full text Add to dashboard Cite

Distant supervision has been widely used in relation extraction tasks without hand-labeled datasets recently. However, the automatically constructed datasets comprise numbers of wrongly labeled negative instances due to the incompleteness of knowledge bases, which is neglected by current distant supervised methods resulting in seriously misleading in both training and testing processes. To address this issue, we propose a novel semi-distant supervision approach for relation extraction by constructing a small accurate dataset and properly leveraging numerous instances without relation labels. In our approach, we construct accurate instances by both knowledge base and entity descriptions determined to avoid wrong negative labeling and further utilize unlabeled instances sufficiently using generative adversarial network (GAN) framework. Experimental results on real-world datasets show that our approach can achieve significant improvements in distant supervised relation extraction over strong baselines.

show abstract

Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning

Cited by 210 publications

References 20 publications

DocRED: A Large-Scale Document-Level Relation Extraction Dataset

DocRED: A Large-Scale Document-Level Relation Extraction Dataset

Distant Supervision Relation Extraction with Intra-Bag and Inter-Bag Attentions

Untitled

Contact Info

Product

Resources

About