Leveraging Pretrained Language Models for Enhanced Entity Matching: : A Comprehensive Study of Fine-Tuning and Prompt Learning Paradigms
Authors: 
Yu Wang, Luyao Zhou, Yuan Wang, Zhenwan Peng Academic Editor: Surya PrakashAuthors Info & Claims
Yu Wang, Luyao Zhou, Yuan Wang, Zhenwan Peng Academic Editor: Surya PrakashAuthors Info & ClaimsAbstract
Pretrained Language Models (PLMs) acquire rich prior semantic knowledge during the pretraining phase and utilize it to enhance downstream Natural Language Processing (NLP) tasks. Entity Matching (EM), a fundamental NLP task, aims to determine whether two entity records from different knowledge bases refer to the same real-world entity. This study, for the first time, explores the potential of using a PLM to boost the EM task through two transfer learning techniques, namely, fine-tuning and prompt learning. Our work also represents the first application of the soft prompt in an EM task. Experimental results across eleven EM datasets show that the soft prompt consistently outperforms other methods in terms of F1 scores across all datasets. Additionally, this study also investigates the capability of prompt learning in few-shot learning and observes that the hard prompt achieves the highest F1 scores in both zero-shot and one-shot context. These findings underscore the effectiveness of prompt learning paradigms in tackling challenging EM tasks.
References
[1]
D. Van Assche, T. Delva, G. Haesendonck, P. Heyvaert, B. De Meester, and A. Dimou, “Declarative RDF graph generation from heterogeneous (semi-) structured data: a systematic literature review,” Journal of Web Semantics, vol. 75, 2023.
[2]
L. Asprino, E. Daga, A. Gangemi, and P. Mulholland, “Knowledge Graph Construction with a façade: a unified method to access heterogeneous data sources on the Web,” ACM Transactions on Internet Technology, vol. 23, pp. 1–31, 2023.
[3]
B. Hui, L. Zhang, X. Zhou, X. Wen, and Y. Nian, “Personalized recommendation system based on knowledge embedding and historical behavior,” Applied Intelligence, vol. 13, 2023.
[4]
F. Zhao, Y. Li, J. Hou, and L. Bai, “Improving question answering over incomplete knowledge graphs with relation prediction,” Neural Computing & Applications, vol. 18, 2022.
[5]
Q. Guo, S. Cao, and Z. Yi, “A medical question answering system using large language models and knowledge graphs,” International Journal of Intelligent Systems, vol. 37, no. 11, pp. 8548–8564, 2022.
[6]
Y. Li, J. Li, Y. Suhara, J. Wang, W. Hirota, and W. C. Tan, “Deep entity matching: challenges and opportunities,” Journal of Data and Information Quality, vol. 13, pp. 1–17, 2021.
[7]
S. N. Minton, C. Nanjo, C. A. Knoblock, M. Michalowski, and M. Michelson, “A heterogeneous field matching method for record linkage,” in Proceedings of Fifth IEEE International Conference on Data Mining (ICDM’05), pp. 226–233, Washington, DC, USA, November 2005.
[8]
N. Barlaug and J. A. Gulla, “Neural networks for entity matching: a survey,” ACM Transactions on Knowledge Discovery from Data, vol. 15, no. 3, pp. 1–37, 2021.
[9]
C. Fu, X. Han, J. He, and L. Sun, “Hierarchical matching network for heterogeneous entity resolution,” in Proceedings of the International Conference on International Joint Conferences on Artificial Intelligence, pp. 3665–3671, Yokohama, Japan, January 2021.
[10]
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” in Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA, June 2017.
[11]
J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, “BERT: pre-training of deep bidirectional transformers for language understanding,” in Proceedings of the North American Chapter of the Association for Computational Linguistics, pp. 4171–4186, Minneapolis, MI, USA, June 2019.
[12]
Y. Sun, S. Wang, Y. Li, S. Feng, X. Chen, H. Zhang, X. Tian, D. Zhu, H. Tian, and H. Wu, “ERNIE: enhanced representation through knowledge integration,” in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 1441–1451, Florence, Italy, July 2019.
[13]
C. Jia, Y. Shi, Q. Yang, and Y. Zhang, “Entity enhanced BERT pre-training for Chinese NER,” in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6384–6396, Online, November 2020.
[14]
S. Chatterjee and D. Laura, “BERT-ER: query-specific BERT entity representations for entity ranking,” in Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1466–1477, Madrid, Spain, July 2022.
[15]
K. Xue, Y. Zhou, Z. Ma, T. Ruan, H. Zhang, and P. He, “Fine-tuning BERT for joint entity and relation extraction in Chinese medical text,” in Proceedings of the IEEE international conference on bioinformatics and biomedicine (BIBM), pp. 892–897, San Diego, CA, USA, August 2019.
[16]
L. Fichtel, J. C. Kalo, and W. T. Balke, “Prompt tuning or fine-tuning-investigating relational knowledge in pre-trained language models,” in Proceedings of the Conference on Automated Knowledge Base Construction, Irvine, IR, USA, October 2021.
[17]
W. Jin, B. Zhao, Y. Zhang, J. Huang, and H. Yu, “WordTransABSA: enhancing Aspect-based Sentiment Analysis with masked language modeling for affective token prediction,” Expert Systems with Applications, vol. 238, 2024.
[18]
P. Liu, W. Yuan, J. Fu, Z. Jiang, H. Hayashi, and G. Neubig, “Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing,” ACM Computing Surveys, vol. 55, no. 9, pp. 1–35, 2023.
[19]
L. Li, Y. Zhang, and L. Chen, “Personalized prompt learning for explainable recommendation,” ACM Transactions on Information Systems, vol. 41, no. 4, pp. 1–26, 2023.
[20]
G. Jiang, S. Liu, Y. Zhao, Y. Sun, and M. Zhang, “Fake news detection via knowledgeable prompt learning,” Information Processing & Management, vol. 59, 2022.
[21]
X. Wang, K. Zhou, J. R. Wen, and W. X. Zhao, “Towards unified conversational recommender systems via knowledge-enhanced prompt learning,” in Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 1929–1937, Washington, DC, USA, August 2022.
[22]
B. Zhao, W. Jin, Y. Zhang, S. Huang, and G. Yang, “Prompt learning for metonymy resolution: enhancing performance with internal prior knowledge of pre-trained language models,” Knowledge-Based Systems, vol. 279, 2023.
[23]
T. Schick and H. Schütze, “Few-shot text generation with pattern-exploiting training,” in Proceedings of the Empirical Methods in Natural Language Processing (EMNLP), pp. 390–402, Abu Dhabi, UAE, December 2020.
[24]
B. Lester, R. Al-Rfou, and N. Constant, “The power of scale for parameter-efficient prompt tuning,” in Proceedings of the Empirical Methods in Natural Language Processing (EMNLP), pp. 3045-–3059, Abu Dhabi, UAE, December 2020.
[25]
A. E. Monge and E. Charles, “The field matching problem: algorithms and applications,” Proceedings of the ACM SIGKDD international conference on Knowledge discovery and data mining, vol. 2, pp. 267–270, 1996.
[26]
M. Bilenko, R. Mooney, W. Cohen, P. Ravikumar, and S. Fienberg, “Adaptive name matching in information integration,” IEEE Intelligent Systems, vol. 18, no. 5, pp. 16–23, 2003.
[27]
M. Bilenko and R. J. Mooney, “Adaptive duplicate detection using learnable string similarity measures,” in Proceedings of the ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 39–48, Washington, DC, USA, July 2003.
[28]
V. Di Cicco, D. Firmani, N. Koudas, P. Merialdo, and D. Srivastava, “Interpreting deep learning models for entity resolution: an experience report using LIME,” in Proceedings of the International Workshop on Exploiting Artificial Intelligence Techniques for Data Management, pp. 1–4, Amsterdam, Netherlands, June 2019.
[29]
H. Nie, X. Han, B. He, L. Sun, B. Chen, W. Zhang, S. Wu, and H. Kong, “Deep sequence-to-sequence entity matching for heterogeneous entity resolution,” in Proceedings of the ACM International Conference on Information and Knowledge Management, pp. 629–638, Beijing, China, October 2019.
[30]
N. Kooli, R. Allesiardo, and E. Pigneul, “Deep learning based approach for entity resolution in databases,” in Proceedings of the Asian conference on intelligent information and database systems, pp. 3–12, Dong Hoi City, Vietnam, February 2018.
[31]
R. D. Gottapu, C. Dagli, and B. Ali, “Entity resolution using convolutional neural network,” Procedia Computer Science, vol. 95, pp. 153–158, 2016.
[32]
J. Kasai, K. Qian, S. Gurajada, Y. Li, and L. Popa, “Low-resource deep entity resolution with transfer and active learning,” in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 5851–5861, Florence, Italy, August 2019.
[33]
C. Zhao and H. Yeye, “Auto-em: end-to-end fuzzy entity-matching using pre-trained deep models and transfer learning,” in Proceedings of the World Wide Web Conference, pp. 2413–2424, San Francisco, CA, USA, April 2019.
[34]
M. Akbarian, K. Ehsan, and R. Davood, “Probing the robustness of Pre-trained Language Models for entity matching,” in Proceedings of the ACM International Conference on Information and Knowledge Management, pp. 3786–3790, Atlanta, GA, USA, October 2022.
[35]
T. Schick and H. Schütze, “It’s not just size that matters: small language models are also few-shot learners,” in Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL), pp. 2339–2352, Washington, DC, USA, July 2020.
[36]
T. Shin, Y. Razeghi, R. L. Logan IV, E. Wallace, and S. Singh, “Autoprompt: eliciting knowledge from language models with automatically generated prompts,” in Proceedings of the Empirical Methods in Natural Language Processing (EMNLP), pp. 4222–4235, Abu Dhabi, UAE, December 2020.
[37]
S. Mudgal, H. Li, T. Rekatsinas, A. Doan, Y. Park, G. Krishnan, R. Deep, E. Arcaute, and V. Raghavendra, “Deep learning for entity matching: a design space exploration,” in Proceedings of the International Conference on Management of Data, pp. 19–34, Houston, HL, USA, June 2018.
[38]
M. Ebraheem, S. Thirumuruganathan, S. Joty, M. Ouzzani, and N. Tang, “Distributed representations of tuples for entity resolution,” Proceedings of the VLDB Endowment, vol. 11, pp. 1454–1467, 2018.
[39]
P. Jeffrey, S. Richard, and M. Christopher, “GloVe: global vectors for word representation,” in Proceedings of the Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543, Doha, Qatar, UAE, December 2014.
[40]
P. Konda, S. Das, P. Suganthan G C, A. Doan, A. Ardalan, J. Ballard, H. Li, F. Panahi, H. Zhang, J. Naughton, S. Prasad, G. Krishnan, R. Deep, and V. Raghavendra, “Magellan: toward building entity matching management systems,” Proceedings of the VLDB Endowment, vol. 9, no. 12, pp. 1197–1208, 2016.
[41]
D. Zhang, Y. Nie, S. Wu, Y. Shen, and K. L. Tan, “Multi-context attention for entity matching,” in Proceedings of the Web Conference (WWW), pp. 2634–2640, Taipei, Taiwan, April 2020.
[42]
B. Zhao, W. Jin, J. Del Ser, and G. Yang, “ChatAgri: exploring potentials of ChatGPT on cross-linguistic agricultural text classification,” Neurocomputing, vol. 557, 2023.
[43]
W. Cohen, “Data integration using similarity joins and a word-based information representation language,” ACM Transactions on Information Systems, vol. 18, no. 3, pp. 288–321, 2000.
[44]
S. Sarawagi and A. Bhamidipaty, “Interactive deduplication using active learning,” in Proceedings of the ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 269–278, New York, NY, USA, July 2002.
[45]
P. Ravikumar and W. Cohen, “A hierarchical graphical model for record linkage,” in Proceedings of the Conference on Uncertainty in Artificial Intelligence, Banff, Canada, August 2004.
Recommendations
Deep Sequence-to-Sequence Entity Matching for Heterogeneous Entity Resolution
CIKM '19: Proceedings of the 28th ACM International Conference on Information and Knowledge ManagementEntity Resolution (ER) identifies records from different data sources that refer to the same real-world entity. Conventional ER approaches usually employ a structure matching mechanism, where attributes are aligned, compared and aggregated for ER ...
Expanding Language-Image Pretrained Models for General Video Recognition
Computer Vision – ECCV 2022AbstractContrastive language-image pretraining has shown great success in learning visual-textual joint representation from web-scale data, demonstrating remarkable “zero-shot” generalization ability for various image tasks. However, how to effectively ...
Schema-Agnostic Entity Matching using Pre-trained Language Models
CIKM '20: Proceedings of the 29th ACM International Conference on Information & Knowledge ManagementEntity matching (EM) is the process of linking records from different data sources. While extensive research has been done in various aspects of EM, many of these studies generally assume EM tasks as schema-specific, which attempt to match record pairs ...
Comments
Information & Contributors
Information
Published In
Copyright © 2024 Yu Wang et al.
This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Publisher
John Wiley and Sons Ltd.
United Kingdom
Publication History
Published: 15 April 2024
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 11 Sep 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in