Unstructured Data Fusion for Schema and Data Extraction
Authors: 
Kaiwen Chen, Nick KoudasAuthors Info & Claims
Article No.: 181, Pages 1 - 26
Abstract
Recently, there has been significant interest in extracting actionable insights from the abundance of unstructured textual data. In this paper, we introduce a novel problem, which we term Semistructured Schema and Data Extraction (SDE). This task aims to enhance and complete tables using information discovered from textual repositories, given partial table specifications in the form of queries. To effectively solve SDE, several challenges must be overcome, which involve transforming the partial table specifications into effective queries, retrieving relevant documents, discerning values for partially specified attributes, inferring additional attributes, and constructing an enriched output table while mitigating the influence of false positives from the retrieval.
We propose an end-to-end pipeline for SDE, which consists of a retrieval component and an augmentation component, to address each of the challenges. In the retrieval component, we serialize the partial table specifications into a query and employ a dense passage retrieval algorithm to extract the top-k relevant results from the text repository. Subsequently, the augmentation component ingests the output documents from the retrieval phase and generates an enriched table. We formulate this table enrichment task as a unique sequence-to-sequence task, distinct from traditional approaches, as it operates on multiple documents during generation. Utilizing an interpolation mechanism on the encoder output, our model maintains a nearly constant context length while automatically prioritizing the importance of documents during the generation.
Due to the novelty of SDE, we establish a validation methodology, adapting and expanding existing benchmarks with the use of powerful large language models. Our extensive experiments show that our method achieves high accuracy in enriching query tables through multi-document fusion, while also surpassing baseline methods in both accuracy and computational efficiency.
References
[1]
G Amati and CJ Van Rijsbergen. 2002. Probabilistic models of information retrieval based on measuring the divergence from randomness. ACM Transactions on Information Systems, Vol. 20, 4 (2002), 357--389.
[2]
Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http://arxiv.org/abs/1409.0473
[3]
Alex Bogatu, Alvaro A. A. Fernandes, Norman W. Paton, and Nikolaos Konstantinou. 2020. Dataset Discovery in Data Lakes. In 2020 IEEE 36th International Conference on Data Engineering (ICDE). 709--720. https://doi.org/10.1109/ICDE48307.2020.00067
[4]
Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching word vectors with subword information. Transactions of the association for computational linguistics, Vol. 5 (2017), 135--146.
[5]
Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877--1901. https://proceedings.neurips.cc/paper_files/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf
[6]
Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607.
[7]
Nadiia Chepurko, Ryan Marcus, Emanuel Zgraggen, Raul Castro Fernandez, Tim Kraska, and David Karger. 2020. ARDA: automatic relational data augmentation for machine learning. Proc. VLDB Endow., Vol. 13, 9 (may 2020), 1373--1387. https://doi.org/10.14778/3397230.3397235
[8]
Thomas Davis and Max Kolesnyk. 2023. JSONRESUME-fake. https://github.com/jsonresume/jsonresume-fake Accessed: 2023-09--30.
[9]
Xiang Deng, Huan Sun, Alyssa Lees, You Wu, and Cong Yu. 2020. TURL: table understanding through representation learning. Proceedings of the VLDB Endowment, Vol. 14, 3 (2020), 307--319.
[10]
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In 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). Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186. https://doi.org/10.18653/v1/N19--1423
[11]
Xinya Du, Alexander Rush, and Claire Cardie. 2021. GRIT: Generative Role-filler Transformers for Document-level Event Entity Extraction. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. Association for Computational Linguistics, Online, 634--644. https://doi.org/10.18653/v1/2021.eacl-main.52
[12]
Mohamed Y. Eltabakh, Mayuresh Kunjir, Ahmed K. Elmagarmid, and Mohammad Shahmeer Ahmad. 2023. Cross Modal Data Discovery over Structured and Unstructured Data Lakes. Proc. VLDB Endow., Vol. 16, 11 (aug 2023), 3377--3390. https://doi.org/10.14778/3611479.3611533
[13]
Grace Fan, Jin Wang, Yuliang Li, and Renée J. Miller. 2023. Table Discovery in Data Lakes: State-of-the-Art and Future Directions. In Companion of the 2023 International Conference on Management of Data (Seattle, WA, USA) (SIGMOD '23). Association for Computing Machinery, New York, NY, USA, 69--75. https://doi.org/10.1145/3555041.3589409
[14]
Raul Castro Fernandez, Ziawasch Abedjan, Famien Koko, Gina Yuan, Samuel Madden, and Michael Stonebraker. 2018. Aurum: A Data Discovery System. In 34th IEEE International Conference on Data Engineering, ICDE 2018, Paris, France, April 16--19, 2018. IEEE Computer Society, 1001--1012. https://doi.org/10.1109/ICDE.2018.00094
[15]
Javier de Jesús Flores Herrera, Sergi Nadal Francesch, and Óscar Romero Moral. 2021. Effective and scalable data discovery with NextiaJD. In Advances in Database Technology: EDBT 2021, 24th International Conference on Extending Database Technology: Nicosia, Cyprus, March 23--26, 2021: proceedings. OpenProceedings, 690--693.
[16]
Michael Glass, Xueqing Wu, Ankita Rajaram Naik, Gaetano Rossiello, and Alfio Gliozzo. 2023. Retrieval-Based Transformer for Table Augmentation. In Findings of the Association for Computational Linguistics: ACL 2023. Association for Computational Linguistics, Toronto, Canada, 5635--5648. https://doi.org/10.18653/v1/2023.findings-acl.348
[17]
Tatsunori Hashimoto. 2021. Model Performance Scaling with Multiple Data Sources. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 4107--4116. https://proceedings.mlr.press/v139/hashimoto21a.html
[18]
Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. arxiv: 2106.09685 [cs.CL]
[19]
Ihab F. Ilyas, Theodoros Rekatsinas, Vishnu Konda, Jeffrey Pound, Xiaoguang Qi, and Mohamed Soliman. 2022. Saga: A Platform for Continuous Construction and Serving of Knowledge at Scale. In Proceedings of the 2022 International Conference on Management of Data (SIGMOD/PODS '22). ACM. https://doi.org/10.1145/3514221.3526049
[20]
Vladimir Karpukhin, Barlas Oug uz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020).
[21]
Aamod Khatiwada, Grace Fan, Roee Shraga, Zixuan Chen, Wolfgang Gatterbauer, Renée J. Miller, and Mirek Riedewald. 2023. SANTOS: Relationship-Based Semantic Table Union Search. Proc. ACM Manag. Data, Vol. 1, 1, Article 9 (may 2023), bibinfonumpages25 pages. https://doi.org/10.1145/3588689
[22]
Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Advances in neural information processing systems, Vol. 33 (2020), 18661--18673.
[23]
Rémi Lebret, David Grangier, and Michael Auli. 2016. Neural Text Generation from Structured Data with Application to the Biography Domain. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Austin, Texas, 1203--1213. https://doi.org/10.18653/v1/D16--1128
[24]
Martin Josifoski Sebastian Riedel Ledell Wu, Fabio Petroni and Luke Zettlemoyer. 2020. Zero-shot Entity Linking with Dense Entity Retrieval. In EMNLP.
[25]
Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 7871--7880. https://doi.org/10.18653/v1/2020.acl-main.703
[26]
Tong Li, Zhihao Wang, Liangying Shao, Xuling Zheng, Xiaoli Wang, and Jinsong Su. 2023. A Sequence-to-Sequence&Set Model for Text-to-Table Generation. In Findings of the Association for Computational Linguistics: ACL 2023. Association for Computational Linguistics, Toronto, Canada, 5358--5370. https://doi.org/10.18653/v1/2023.findings-acl.330
[27]
Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2023 b. Pre-Train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing. ACM Comput. Surv., Vol. 55, 9, Article 195 (jan 2023), bibinfonumpages35 pages. https://doi.org/10.1145/3560815
[28]
Yiheng Liu, Tianle Han, Siyuan Ma, Jiayue Zhang, Yuanyuan Yang, Jiaming Tian, Hao He, Antong Li, Mengshen He, Zhengliang Liu, Zihao Wu, Lin Zhao, Dajiang Zhu, Xiang Li, Ning Qiang, Dingang Shen, Tianming Liu, and Bao Ge. 2023 a. Summary of ChatGPT-Related research and perspective towards the future of large language models. Meta-Radiology, Vol. 1, 2 (sep 2023), 100017. https://doi.org/10.1016/j.metrad.2023.100017
[29]
Evan Mayo-Wilson, Tianjing Li, Nicole Fusco, Kay Dickersin, and MUDS investigators. 2017. Practical guidance for using multiple data sources in systematic reviews and meta-analyses (with examples from the MUDS study). Res Synth Methods, Vol. 9, 1 (Dec. 2017), 2--12.
[30]
Bhaskar Mitra and Nick Craswell. 2017. Neural models for information retrieval. arXiv preprint arXiv:1705.01509 (2017).
[31]
Marius Mosbach, Tiago Pimentel, Shauli Ravfogel, Dietrich Klakow, and Yanai Elazar. 2023. Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation. arxiv: 2305.16938 [cs.CL]
[32]
Avanika Narayan, Ines Chami, Laurel Orr, and Christopher Ré. 2022. Can Foundation Models Wrangle Your Data? Proceedings of the VLDB Endowment, Vol. 16, 4 (2022), 738--746.
[33]
Jekaterina Novikova, Ondvr ej Duvs ek, and Verena Rieser. 2017. The E2E Dataset: New Challenges For End-to-End Generation. In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue. Association for Computational Linguistics, Saarbrücken, Germany, 201--206. https://doi.org/10.18653/v1/W17--5525
[34]
OpenAI. 2023. GPT-4 Technical Report. arxiv: 2303.08774 [cs.CL]
[35]
Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. arxiv: 2203.02155 [cs.CL]
[36]
Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu, Jingfang Xu, and Xueqi Cheng. 2017. Deeprank: A new deep architecture for relevance ranking in information retrieval. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. 257--266.
[37]
Michał Pietruszka, Michał Turski, Łukasz Borchmann, Tomasz Dwojak, Gabriela Pałka, Karolina Szyndler, Dawid Jurkiewicz, and Łukasz Garncarek. 2022. STable: Table Generation Framework for Encoder-Decoder Models. arXiv preprint arXiv:2206.04045 (2022).
[38]
Maja Popović. 2015. chrF: character n-gram F-score for automatic MT evaluation. In Proceedings of the Tenth Workshop on Statistical Machine Translation. Association for Computational Linguistics, Lisbon, Portugal, 392--395. https://doi.org/10.18653/v1/W15--3049
[39]
Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. J. Mach. Learn. Res., Vol. 21, 1, Article 140 (jan 2020), bibinfonumpages67 pages.
[40]
Stephen Robertson, Hugo Zaragoza, et al. 2009. The probabilistic relevance framework: BM25 and beyond. Foundations and Trends® in Information Retrieval, Vol. 3, 4 (2009), 333--389.
[41]
Hinrich Schütze, Christopher D Manning, and Prabhakar Raghavan. 2008. Introduction to information retrieval. Vol. 39. Cambridge University Press Cambridge.
[42]
Hongjin Su, Weijia Shi, Jungo Kasai, Yizhong Wang, Yushi Hu, Mari Ostendorf, Wen-tau Yih, Noah A. Smith, Luke Zettlemoyer, and Tao Yu. 2023. One Embedder, Any Task: Instruction-Finetuned Text Embeddings. In Findings of the Association for Computational Linguistics: ACL 2023. Association for Computational Linguistics, Toronto, Canada, 1102--1121. https://doi.org/10.18653/v1/2023.findings-acl.71
[43]
Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. Advances in neural information processing systems, Vol. 27 (2014).
[44]
Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller, Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez, Madian Khabsa, Isabel Kloumann, Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov, Pushkar Mishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith, Ranjan Subramanian, Xiaoqing Ellen Tan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu, Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan, Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arxiv: 2307.09288 [cs.CL]
[45]
Katrina M Turner, John Percival, David Kessler, and Jenny L Donovan. 2018. Synthesizing Qualitative Data Sets to Improve the Design of Trials and Complex Health Interventions: A Worked Example. Qual Health Res, Vol. 29, 5 (Oct. 2018), 693--699.
[46]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
[47]
Sam Wiseman, Stuart Shieber, and Alexander Rush. 2017. Challenges in Data-to-Document Generation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Copenhagen, Denmark, 2253--2263. https://doi.org/10.18653/v1/D17--1239
[48]
Xueqing Wu, Jiacheng Zhang, and Hang Li. 2022. Text-to-Table: A New Way of Information Extraction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Dublin, Ireland, 2518--2533. https://doi.org/10.18653/v1/2022.acl-long.180
[49]
Hang Yan, Tao Gui, Junqi Dai, Qipeng Guo, Zheng Zhang, and Xipeng Qiu. 2021. A Unified Generative Framework for Various NER Subtasks. In 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), Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli (Eds.). Association for Computational Linguistics, Online, 5808--5822. https://doi.org/10.18653/v1/2021.acl-long.451
[50]
Hongbin Ye, Ningyu Zhang, Hui Chen, and Huajun Chen. 2022. Generative Knowledge Graph Construction: A Review. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang (Eds.). Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, 1--17. https://doi.org/10.18653/v1/2022.emnlp-main.1
[51]
Tianyi Zhang*, Varsha Kishore*, Felix Wu*, Kilian Q. Weinberger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations. https://openreview.net/forum?id=SkeHuCVFDr
[52]
Zixuan Zhao and Raul Castro Fernandez. 2022. Leva: Boosting Machine Learning Performance with Relational Embedding Data Augmentation. In Proceedings of the 2022 International Conference on Management of Data (Philadelphia, PA, USA) (SIGMOD '22). Association for Computing Machinery, New York, NY, USA, 1504--1517. https://doi.org/10.1145/3514221.3517891
[53]
Zexuan Zhong and Danqi Chen. 2021. A Frustratingly Easy Approach for Entity and Relation Extraction. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, and Yichao Zhou (Eds.). Association for Computational Linguistics, Online, 50--61. https://doi.org/10.18653/v1/2021.naacl-main.5
Index Terms
- Unstructured Data Fusion for Schema and Data Extraction
Recommendations
Schema Extraction and Integration of Heterogeneous XML Document Collections
MEDI 2013: Proceedings of the Third International Conference on Model and Data Engineering - Volume 8216The availability of vast amounts of heterogeneous XML web data motivates finding efficient methods to search, integrate, query, and present this data. The structure of XML documents is useful for achieving these tasks; however, not every XML document on ...
Fusion of visual representations for multimodal information extraction from unstructured transactional documents
AbstractThe importance of automated document understanding in terms of today’s businesses’ speed, efficiency, and cost reduction is indisputable. Although structured and semi-structured business documents have been studied intensively within the ...
XML schema and data summarization
ICAISC'10: Proceedings of the 10th international conference on Artifical intelligence and soft computing: Part IIAs XML repositories are becoming more and more complex there is a need to develop methods and tools to facilitate the understanding and exploring schemas and contents of these repositories. A solution can be provided by a proper summarization of XML ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
June 2024
1953 pages
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 30 May 2024
Published in PACMMOD Volume 2, Issue 3
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 324Total Downloads
- Downloads (Last 12 months)324
- Downloads (Last 6 weeks)45
Reflects downloads up to 08 Feb 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in