Abstract
In relation to extraction tasks, distant supervision is a very effective method, which can automatically generate training data via aligning KBs and texts, thereby solving the problem of manually labeling data. However, distant supervision inevitably accompanies the wrong labeling problem. The paper presents a neural relation extraction method to deal with the problem of noisy words and poor feature information in the one-sentence bags generated by distant supervision. Previous studies mainly focus on sentence-level denoising and even bag-level denoising by designing neural networks. In the paper, we propose a piecewise convolutional neural network with position attention and similar bag attention for distant supervision relation extraction(PCNN-PATT-SBA). First, we propose a position attention based on Gaussian distribution, by modeling the position relationship between non-entity words and entity words to assign weights for the words of the sentence, which is expected to reduce the influence of those noisy words. In addition, we propose similar bag attention based on the feature similarity between different bags, which merges the features of similar bags to solve the problem of poor feature information in one-sentence bags. Experimental results on the New York Times dataset demonstrate the effectiveness of our proposed position attention and similar bag attention modules. Our method also achieves better relation extraction accuracy than state-of-the-art methods on this dataset. And compared to the bag-of-sentence attention model, the P value is increased by 6.9%, Compared with selective attention over instances (PCNN-ATT), an increase of 25.6%, compared to Instance-Level Adversarial Training (PCNN-HATT), an increase of 12.1%.
Similar content being viewed by others
References
Zelenko D, Aone C, Richardella A (2003) Kernel methods for relation extraction. J Mach Learn Res 3(6):1083–1106
Mooney RJ, Bunescu R. (2005) Subsequence kernels for relation extraction, pp 171–178
Sadeghi F, Divvala SK, Farhadi A (2015) Viske: Visual knowledge extraction and question answering by visual verification of relation phrases, pp 1456–1464
Ravichandran D, Hovy E (2002) Learning surface text patterns for a question answering system, pp 41–47
Yan Y, Okazaki N, Matsuo Y, Yang Z, Ishizuka M (2009) Unsupervised relation extraction by mining wikipedia texts using information from the web, pp 1021–1029
Zeng D, Liu K, Lai S, Zhou G, Zhao J (2014) Relation classification via convolutional deep neural network, pp 2335–2344
Santos CND, Xiang B, Zhou B (2015) Classifying relations by ranking with convolutional neural networks 1:626–634
Miwa M, Bansal M (2016) End-to-end relation extraction using lstms on sequences and tree structures 1:1105–1116
Mintz M, Bills S, Snow R, Jurafsky D (2009) Distant supervision for relation extraction without labeled data, pp 1003–1011
Bollacker K, Evans C, Paritosh P, Sturge T, Taylor J (2008) Freebase: a collaboratively created graph database for structuring human knowledge, pp 1247–1250
Lin Y, Shen S, Liu Z, Luan H, Sun M (2016) Neural relation extraction with selective attention over instances 1:2124– 2133
Riedel S, Yao L, Mccallum A (2010) Modeling relations and their mentions without labeled text, pp 148–163
Hoffmann R, Zhang C, Ling X, Zettlemoyer L, Weld DS (2011) Knowledge-based weak supervision for information extraction of overlapping relations, pp 541–550
Surdeanu M, Tibshirani J, Nallapati R, Manning CD (2012) Multi-instance multi-label learning for relation extraction, pp 455– 465
Lecun Y, Bengio Y, Hinton GE (2015) Deep learning. Nature 521(7553):436–444
Socher R, Huval B, Manning CD, Ng AY (2012) Semantic compositionality through recursive matrix-vector spaces, pp 1201–1211
Zeng D, Liu K, Chen Y, Zhao J (2015) Distant supervision for relation extraction via piecewise convolutional neural networks, pp 1753–1762
Ji G, Liu K, He S, Zhao J (2017) Distant supervision for relation extraction with sentence-level attention and entity descriptions, pp 3060–3066
Liu T, Wang K, Chang B, Sui Z (2017) A soft-label method for noise-tolerant distantly supervised relation extraction, pp 1790–1795
Yuan Y, Liu L, Tang S, Zhang Z, Zhuang Y, Pu S, Wu F, Ren X (2019) Cross-relation cross-bag attention for distantly-supervised relation extraction 33(01):419–426
Zhang Y, Zhong V, Chen D, Angeli G, Manning CD (2017) Position-aware attention and supervised data improve slot filling, pp 35–45
Li Y, Long G, Shen T, Zhou T, Yao L, Huo H, Jiang J Self-attention enhanced selective gate with entity-aware embedding for distantly supervised relation extraction, arXiv:Computation and Language
Ye Z, Ling Z (2019) Distant supervision relation extraction with intra-bag and inter-bag attentions, pp 2810–2819
Vilnis L, Mccallum A Word representations via gaussian embedding, arXiv: Computation and Language
Du J, Han J, Way A, Wan D (2018) Multi-level structured self-attentions for distantly supervised relation extraction, pp 2216–2225
Zhou P, Xu J, Qi Z, Bao H, Chen Z, Xu B (2018) Distant supervision for relation extraction with hierarchical selective attention, vol 108
Acknowledgements
This work is supported by the National Natural Science Foundation of China (62066022).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, W., Wang, Q., Wu, J. et al. Piecewise convolutional neural networks with position attention and similar bag attention for distant supervision relation extraction. Appl Intell 52, 4599–4609 (2022). https://doi.org/10.1007/s10489-021-02632-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02632-8