Prompt learning based unsupervised relation extraction model

doi:10.11772/j.issn.1001-9081.2022071133

Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (7): 2010-2016.DOI: 10.11772/j.issn.1001-9081.2022071133

Special Issue: 第39届CCF中国数据库学术会议(NDBC 2022)

• The 39th CCF National Database Conference (NDBC 2022) • Previous Articles Next Articles

Prompt learning based unsupervised relation extraction model

Menglin HUANG¹, Lei DUAN¹^,²(), Yuanhao ZHANG¹, Peiyan WANG¹, Renhao LI¹

^1.College of Computer Science，Sichuan University，Chengdu Sichuan 610065，China
^2.Med -X Center for Informatics，Sichuan University，Chengdu Sichuan 610041，China

Received:2022-07-12 Revised:2022-08-11 Accepted:2022-08-22 Online:2022-09-23 Published:2023-07-10
Contact: Lei DUAN
About author:HUANG Menglin， born in 1998， M. S. candidate. Her research interests include natural language processing.
DUAN Lei， born in 1981， Ph. D.， professor. His research interests include data mining.
ZHANG Yuanhao， born in 1999， M. S. candidate. His research interests include natural language processing.
WANG Peiyan， born in 1997， M. S. candidate. Her research interests include knowledge graph completion.
LI Renhao， born in 1997， M. S. candidate. His research interests include natural language processing.
Supported by:
National Natural Science Foundation of China(61972268);Project of Med-X Center for Informatics, Sichuan University(YGJC001)

基于Prompt学习的无监督关系抽取模型

黄梦林¹, 段磊¹^,²(), 张袁昊¹, 王培妍¹, 李仁昊¹

^1.四川大学计算机学院，成都 610065
^2.四川大学 “医学+信息”中心，成都 610041

通讯作者: 段磊
作者简介:黄梦林（1998—），女，重庆人，硕士研究生，CCF会员，主要研究方向：自然语言处理；
段磊（1981—），男，四川成都人，教授，博士，CCF高级会员，主要研究方向：数据挖掘；
张袁昊（1999—），男，安徽宁国人，硕士研究生，CCF会员，主要研究方向：自然语言处理；
王培妍（1997—），女，吉林通化人，硕士研究生，CCF会员，主要研究方向：知识图谱补全；
李仁昊（1997—），男，北京人，硕士研究生，CCF会员，主要研究方向：自然语言处理。
基金资助:
国家自然科学基金资助项目(61972268);四川大学“医学+信息”中心融合创新项目(YGJC001)

Abstract

Abstract:

Unsupervised relation extraction aims to extract the semantic relations between entities from unlabeled natural language text. Currently， unsupervised relation extraction models based on Variational Auto-Encoder （VAE） architecture provide supervised signals to train model through reconstruction loss， which offers a new idea to complete unsupervised relation extraction tasks. Focusing on the issue that this kind of models cannot understand contextual information effectively and relies on dataset inductive biases， a Prompt-based learning based Unsupervised Relation Extraction （PURE） model was proposed， including a relation extraction module and a link prediction module. In the relation extraction module， a context-aware Prompt template function was designed to fuse the contextual information， and the unsupervised relation extraction task was converted into a mask prediction task， so as to make full use of the knowledge obtained during pre-training phase to extract relations. In the link prediction module， supervised signals were provided for the relation extraction module by predicting the missing entities in the triples to assist model training. Extensive experiments on two public real-world relation extraction datasets were carried out. The results show that PURE model can use contextual information effectively and does not rely on dataset inductive biases， and has the evaluation index B-cubed F1 improved by 3.3 percentage points on NYT dataset compared with the state-of-the-art VAE architecture-based model UREVA （Variational Autoencoder-based Unsupervised Relation Extraction model）.

Key words: unsupervised relation extraction, Prompt learning, Variational Auto-Encoder (VAE), Pre-trained Language Model (PLM), unsupervised learning

摘要：

无监督关系抽取旨在从无标签的自然语言文本中抽取实体之间的语义关系。目前，基于变分自编码器（VAE）架构的无监督关系抽取模型通过重构损失提供监督信号来训练模型，这为完成无监督关系抽取任务提供了新思路。针对此类模型无法有效地理解上下文信息、依赖数据集归纳偏置的问题，提出基于Prompt学习的无监督关系抽取（PURE）模型，其中包括关系抽取和链接预测两个模块。在关系抽取模块中设计了上下文感知的Prompt模板函数以融入上下文信息，并将无监督关系抽取任务转换为掩码预测任务，从而充分利用预训练阶段获得的知识完成关系抽取。在链接预测模块中则通过预测关系三元组中的缺失实体提供监督信号联合训练两个模块。在两个公开真实关系抽取数据集上进行了大量实验，得到的结果表明PURE模型能有效利用上下文信息并且不依赖数据集归纳偏置，相较于目前最优的基于VAE架构的模型UREVA （Variational Autoencoder-based Unsupervised Relation Extraction model）在NYT数据集上的B-cubed F1指标上提升了3.3个百分点。

关键词: 无监督关系抽取, Prompt学习, 变分自编码器, 预训练语言模型, 无监督学习

CLC Number:

TP391

Menglin HUANG, Lei DUAN, Yuanhao ZHANG, Peiyan WANG, Renhao LI. Prompt learning based unsupervised relation extraction model[J]. Journal of Computer Applications, 2023, 43(7): 2010-2016.

黄梦林, 段磊, 张袁昊, 王培妍, 李仁昊. 基于Prompt学习的无监督关系抽取模型[J]. 《计算机应用》唯一官方网站, 2023, 43(7): 2010-2016.

Figures/Tables 8

References 26

1	李冬梅，张扬，李东远，等.实体关系抽取方法研究综述［J］.计算机研究与发展， 2020， 57（7）： 1424-1448. 10.7544/issn1000-1239.2020.20190358
	LI D M， ZHANG Y， LI D Y， et al. Review of entity relation extraction methods［J］. Journal of Computer Research and Development， 2020， 57（7）： 1424-1448. 10.7544/issn1000-1239.2020.20190358
2	CHEN T， SHI H C， LIU L Y， et al. Empower distantly supervised relation extraction with collaborative adversarial training ［C］// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2021： 12675-12682. 10.1609/aaai.v35i14.17501
3	YAO L M， HAGHIGHI A， RIEDEL S， et al. Structured relation discovery using generative models ［C］// Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing. Stroudsburg， PA： ACL， 2011： 1456-1466.
4	MARCHEGGIANI D， TITOV I. Discrete-state variational autoencoders for joint discovery and factorization of relations［J］. Transactions of the Association for Computational Linguistics， 2016， 4： 231-244. 10.1162/tacl_a_00095
5	SIMON É， GUIGUE V， PIWOWARSKI B. Unsupervised information extraction： regularizing discriminative approaches with relation distribution losses ［C］// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg， PA： ACL， 2019： 1378-1387. 10.18653/v1/p19-1133
6	TRAN T T， LE P， ANANIADOU S. Revisiting unsupervised relation extraction ［C］// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg， PA： ACL， 2020： 7498-7505. 10.18653/v1/2020.acl-main.669
7	YUAN C H， ELDARDIRY H. Unsupervised relation extraction： a variational autoencoder approach ［C］// Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Stroudsburg， PA： ACL， 2021： 1929-1938. 10.18653/v1/2021.emnlp-main.147
8	LIU P F， YUAN W Z， FU J L， et al. Pre-train， prompt， and predict： a systematic survey of prompting methods in natural language processing［EB/OL］. （2021-07-28）［2022-05-22］. . 10.1145/3560815
9	HU X， ZHANG C， XU Y， et al. SelfORE： self-supervised relational feature learning for open relation extraction ［C］// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsburg： ACL， 2020： 3673-3682. 10.18653/v1/2020.emnlp-main.299
10	LIU F C， YAN L Y， LIN H Y， et al. Element intervention for open relation extraction ［C］// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing （Volume 1： Long Papers）. Stroudsburg， PA： ACL， 2021： 4683-4693. 10.18653/v1/2021.acl-long.361
11	LIU S L， HU X M， ZHANG C W， et al. HiURE： hierarchical exemplar contrastive learning for unsupervised relation extraction ［C］// Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies. Stroudsburg， PA： ACL， 2022： 5970-5980. 10.18653/v1/2022.naacl-main.437
12	DEVLIN J， CHANG M W， LEE K， et al. BERT： pre-training of deep bidirectional transformers for language understanding ［C］// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies， Volume 1（Long and Short Papers）. Stroudsburg， PA： ACL， 2019： 4171-4186. 10.18653/v1/n18-2
13	LIU Y H， OTT M， GOYAL N， et al. RoBERTa： a robustly optimized BERT pretraining approach［EB/OL］. （2019-07-26）［2022-05-06］. .
14	PETRONI F， ROCKTÄSCHEL T， RIEDEL S， et al. Language models as knowledge bases？［C］// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg， PA： ACL， 2019： 2463-2473. 10.18653/v1/d19-1250
15	GOSWAMI A， BHAT A， OHANA H， et al. Unsupervised relation extraction from language models using constrained cloze completion ［C］// Findings of the Association for Computational Linguistics： EMNLP 2020. Stroudsburg， PA： ACL， 2020： 1263-1276. 10.18653/v1/2020.findings-emnlp.113
16	CHEN X， ZHANG N Y， XIE X， et al. KnowPrompt： knowledge-aware prompt-tuning with synergistic optimization for relation extraction ［C］// Proceedings of the ACM Web Conference 2022. New York： ACM， 2022： 2778-2788. 10.1145/3485447.3511998
17	NICKEL M， TRESP V， KRIEGEL H P. A three-way model for collective learning on multi-relational data ［C］// Proceedings of the 28th International Conference on Machine Learning. Madison， WI： Omnipress， 2011： 809-816. 10.1145/2187836.2187874
18	RIEDEL S， YAO L M， McCALLUM A， et al. Relation extraction with matrix factorization and universal schemas ［C］// Proceedings of the 2013 Conference of the North American Chapter of the Association of Computational Linguistics： Human Language Technologies. Stroudsburg， PA： ACL， 2013： 74-84.
19	SANDHAUS E. The New York times annotated corpus［DS/OL］. ［2022-05-11］. . 10.1007/978-3-319-64158-4_4
20	HENDRICKX I， KIM S N， KOZAREVA Z， et al. SemEval-2010 Task 8： multi-way classification of semantic relations between pairs of nominal ［C］// Proceedings of the 5th International Workshop on Semantic Evaluation. Stroudsburg， PA： ACL， 2010： 33-38. 10.3115/1621969.1621986
21	BAGGA A， BALDWIN B. Entity-based cross-document coreferencing using the vector space model ［C］// Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics， Volume 1. New Brunswick， NJ： ACL， 1998： 79-85. 10.3115/980845.980859
22	ROSENBERG A， HIRSCHBERG J. V-measure： a conditional entropy-based external cluster evaluation measure ［C］// Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Stroudsburg， PA： ACL， 2007： 410-420.
23	HUBERT L， ARABIE P. Comparing partitions［J］. Journal of Classification， 1985， 2（1）： 193-218. 10.1007/bf01908075
24	BLEI D M， NG A Y， JORDAN M I. Latent Dirichlet allocation［J］. Journal of Machine Learning Research， 2003， 3： 993-1022.
25	ZENG D J， LIU K， CHEN Y B， et al. Distant supervision for relation extraction via piecewise convolutional neural networks ［C］// Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg： ACL， 2015： 1753-1762. 10.18653/v1/d15-1203
26	ROMANO S， VINH N X， BAILEY J， et al. Adjusting for chance clustering comparison measures［J］. Journal of Machine Learning Research， 2016， 17： 4635-4666. 10.5715/jnlp.4.3_1

模型	B-cubed			V-measure			ARI
模型	F1	Pre	Rec	F1	Hom	Com	ARI
RelLDA	29.1	24.8	35.2	30.0	26.1	35.1	13.3
SelfORE	41.4	38.5	44.7	40.4	37.8	43.3	35.0
EIORE	43.1	48.4	38.8	42.7	37.7	49.2	34.5
HiURE	45.3	40.2	51.8	45.9	40.0	53.8	38.6
March	37.5	31.1	47.4	38.7	32.6	47.8	27.6
Simon^*	32.5	28.2	38.4	31.5	27.1	37.7	22.2
Simon	39.4	32.2	50.7	38.3	32.2	47.2	33.8
EType^*	41.8	30.1	68.9	38.1	28.3	58.5	30.2
EType	41.9	31.3	59.0	41.3	33.6	53.9	30.5
UREVA	43.1	—	—	42.0	—	—	31.6
PURE	46.4	35.3	61.7	47.1	38.0	62.1	31.9

模型	B-cubed			V-measure			ARI
模型	F1	Pre	Rec	F1	Hom	Com	ARI
RelLDA	29.1	24.8	35.2	30.0	26.1	35.1	13.3
SelfORE	41.4	38.5	44.7	40.4	37.8	43.3	35.0
EIORE	43.1	48.4	38.8	42.7	37.7	49.2	34.5
HiURE	45.3	40.2	51.8	45.9	40.0	53.8	38.6
March	37.5	31.1	47.4	38.7	32.6	47.8	27.6
Simon^*	32.5	28.2	38.4	31.5	27.1	37.7	22.2
Simon	39.4	32.2	50.7	38.3	32.2	47.2	33.8
EType^*	41.8	30.1	68.9	38.1	28.3	58.5	30.2
EType	41.9	31.3	59.0	41.3	33.6	53.9	30.5
UREVA	43.1	—	—	42.0	—	—	31.6
PURE	46.4	35.3	61.7	47.1	38.0	62.1	31.9

模型	B-cubed F1	V-measure F1	ARI
SelfORE^*	14.5	5.1	3.2
Simon^*	18.7	8.6	1.5
Simon	22.3	11.2	9.7
UREVA	24.5	13.8	11.7
PURE	26.6	29.0	13.2

模型	B-cubed F1	V-measure F1	ARI
SelfORE^*	14.5	5.1	3.2
Simon^*	18.7	8.6	1.5
Simon	22.3	11.2	9.7
UREVA	24.5	13.8	11.7
PURE	26.6	29.0	13.2

是否微调PLM	模型	B-cubed F1	V-measure F1	ARI
否	PURE_max	19.5	10.9	6.3
否	PURE_cls	33.3	34.9	20.2
是	PURE_{max_finetune}	35.2	36.5	23.7
是	PURE_{cls_finetune}	42.7	46.2	25.9
否	PURE	46.4	47.1	31.9

Prompt learning based unsupervised relation extraction model

基于Prompt学习的无监督关系抽取模型

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 26

Related Articles 15

Recommended Articles

Metrics

关系1	关系8	关系10
/business/person/company	/people/person/place_lived	/location/location/containedby
/business/shareholder/major_shareholder_of	/people/person/place_of_death	/location/neighborhood/neighborhood_of
/business/advisor/companies_advised	/people/person/place_of_birt	/location/hud_county_place/county
/book/author/works_written	/location/location/containedby	/book/book_edition/place_of_publication
/organization/founder/organizations_founded	/book/edition/place_of_publication	/transportation/road/major_cities
/music/artist/label	/music/artist/origin	/geography/river/cities
/visual/artist/associated_periods_or_movements	/location/hud_county_place/county	/book/written_work/subjects

[1]	Jieru JIA, Jianchao YANG, Shuorui ZHANG, Tao YAN, Bin CHEN. Unsupervised person re-identification based on self-distilled vision Transformer [J]. Journal of Computer Applications, 2024, 44(9): 2893-2902.
[2]	Xindong YOU, Yingzi WEN, Xinpeng SHE, Xueqiang LYU. Triplet extraction method for mine electromechanical equipment field [J]. Journal of Computer Applications, 2024, 44(7): 2026-2033.
[3]	Junfeng SHEN, Xingchen ZHOU, Can TANG. Dual-channel sentiment analysis model based on improved prompt learning method [J]. Journal of Computer Applications, 2024, 44(6): 1796-1806.
[4]	Chao WEI, Yanping CHEN, Kai WANG, Yongbin QIN, Ruizhang HUANG. Relation extraction method based on mask prompt and gated memory network calibration [J]. Journal of Computer Applications, 2024, 44(6): 1713-1719.
[5]	Xinyan YU, Cheng ZENG, Qian WANG, Peng HE, Xiaoyu DING. Few-shot news topic classification method based on knowledge enhancement and prompt learning [J]. Journal of Computer Applications, 2024, 44(6): 1767-1774.
[6]	Xiawuji, Heming HUANG, Gengzangcuomao, Yutao FAN. Survey of extractive text summarization based on unsupervised learning and supervised learning [J]. Journal of Computer Applications, 2024, 44(4): 1035-1048.
[7]	Rui JIANG, Wei LIU, Cheng CHEN, Tao LU. Asymmetric unsupervised end-to-end image deraining network [J]. Journal of Computer Applications, 2024, 44(3): 922-930.
[8]	Yingjie GAO, Min LIN, Siriguleng, Bin LI, Shujun ZHANG. Prompt learning method for ancient text sentence segmentation and punctuation based on span-extracted prototypical network [J]. Journal of Computer Applications, 2024, 44(12): 3815-3822.
[9]	Nengbing HU, Biao CAI, Xu LI, Danhua CAO. Graph classification method based on graph pooling contrast learning [J]. Journal of Computer Applications, 2024, 44(11): 3327-3334.
[10]	Pei ZHAO, Yan QIAO, Rongyao HU, Xinyu YUAN, Minyue LI, Benchu ZHANG. Multivariate time series anomaly detection based on multi-domain feature extraction [J]. Journal of Computer Applications, 2024, 44(11): 3419-3426.
[11]	Bihui YU, Xingye CAI, Jingxuan WEI. Few-shot text classification method based on prompt learning [J]. Journal of Computer Applications, 2023, 43(9): 2735-2740.
[12]	Zhe XU, Zhihong WANG, Cunyu SHAN, Yaru SUN, Ying YANG. Unsupervised face forgery video detection based on reconstruction error [J]. Journal of Computer Applications, 2023, 43(5): 1571-1577.
[13]	Mengting GE, Minghua WAN. Feature extraction model based on neighbor supervised locally invariant robust principal component analysis [J]. Journal of Computer Applications, 2023, 43(4): 1013-1020.
[14]	Wenbo LI, Bo LIU, Lingling TAO, Fen LUO, Hang ZHANG. Deep spectral clustering algorithm with L1 regularization [J]. Journal of Computer Applications, 2023, 43(12): 3662-3667.
[15]	Yiyang GUO, Jiong YU, Xusheng DU, Shaozhi YANG, Ming CAO. Outlier detection algorithm based on autoencoder and ensemble learning [J]. Journal of Computer Applications, 2022, 42(7): 2078-2087.