Abstract
In the era of rising AI, ChatGPT has become the most well-known chatbot, utilizing Large Language Models (LLMs), specifically GPT versions 3.5 or 4. It has been employed in various tasks, including text generation and text summarization. Entity Matching is one such task that requires the comparison of information in the records of interest. Traditionally, this work has relied on rule-based similarity measurements. However, in recent years, novel methods have emerged to combat this problem, including the use of word vectors, neural networks, and language models. In this paper, we will compare the results of the Entity Matching task by using ChatGPT and other language models, such as sentence-BERT and RoBERTa. Additionally, we will compare the results from zero-shot capable models like RoBERTa, DistilBERT, and BART. For the Blocking phase, we will use benchmark datasets that are available in ready-to-use formats, in conjunction with other novel blocking methods, if available.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Brown, T.B., Mann, B., Ryder, N., et al.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)
Christen, P.: Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection. Springer, Cham (2012). https://doi.org/10.1007/978-3-642-31164-2
Davison, J.: BART-large-mnli-yahoo-answers. https://huggingface.co/joeddav/bart-large-mnli-yahoo-answers. Accessed 27 aug 2023
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2019)
Elmagarmid, A.K., Ipeirotis, P.G., Verykios, V.S.: Duplicate record detection: a survey. IEEE Trans. Knowl. Data Eng. 19(1), 1–16 (2007)
Larochelle, H., Erhan, D., Bengio, Y.: Zero-data learning of new tasks. In: Proceedings of the National Conference on Artificial Intelligence, vol. 21 (2008)
Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv:1910.13461 (2020)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)
Nuntachit, N., Sugunnasil, P.: Do we need a specific corpus and multiple high-performance GPUs for training the BERT model? An experiment on COVID-19 dataset. Mach. Learn. Knowl. Extract. 4(3), 641–664 (2022). https://doi.org/10.3390/make4030030
OpenAi: GPT-3.5. https://platform.openai.com/docs/models/gpt-3-5. Accessed 27 Aug 2023
OpenAi: GPT-completion-API. https://platform.openai.com/docs/guides/gpt/chat-completions-api. Accessed 27 Aug 2023
OpenAi: OpenAI pricing. https://openai.com/pricing. Accessed 27 Aug 2023
Palatucci, M., Pomerleau, D., Hinton, G.E., Mitchell, T.M.: Zero-shot learning with semantic output codes. In: Advances in Neural Information Processing Systems, pp. 1410–1418 (2009)
Papadakis, G.: Datasets for supervised matching in clean-clean entity resolution (2022). https://doi.org/10.5281/zenodo.8164151
Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)
Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (2019). https://arxiv.org/abs/1908.10084
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Williams, A., Nangia, N., Bowman, S.: A broad-coverage challenge corpus for sentence understanding through inference. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 1112–1122. Association for Computational Linguistics (2018). http://aclweb.org/anthology/N18-1101
Acknowledgements
This work was supported by Erawan HPC Project, Information Technology Service Center (ITSC), Chiang Mai University, Chiang Mai, Thailand. The authors would like to thank Faculty of Engineering and ITSC staff for supporting us in this study. Additionally, we extend our sincere appreciation to the Chiang Mai University Presidential Scholarship for their financial support, which greatly contributed to the successful completion of this study.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
The environment setup for this experiment was provided by ERAWAN HPC Project. The virtual desktop infrastructure that we used were
-
CPU Intel Xeon Gold 6254 (64 virtual CPU cores) with 3.10 GHz
-
Memory 64 GB
-
Storage Virtual SCSI disk 40.0 TB
-
GPU Nvidia GRID V100D-8Q
-
OS Windows 10 Education Version 22H2
-
Python version 3.8.8
-
Jupyter Notebook version 6.3.0
-
CUDA version 11.4
-
Transformers version 4.23.1
-
Pytorch version 1.10.0
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Nuntachit, N., Sugannasil, P. (2024). Can ChatGPT Outperform Other Language Models? An Experiment on Using ChatGPT for Entity Matching Versus Other Language Models. In: Barolli, L. (eds) Advances on P2P, Parallel, Grid, Cloud and Internet Computing . 3PGCIC 2023. Lecture Notes on Data Engineering and Communications Technologies, vol 189. Springer, Cham. https://doi.org/10.1007/978-3-031-46970-1_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-46970-1_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46969-5
Online ISBN: 978-3-031-46970-1
eBook Packages: EngineeringEngineering (R0)