CoChat
Sign Up
Cited by 96Topic ModelingAdvanced Graph Neural NetworksMultimodal Machine Learning Applications

Transformers for Tabular Data Representation: A Survey of Models and Applications

Open access
Badaro, Gilbert, Saeed, Mohammed, Papotti, Paolo·2023·Transactions of the Association for Computational Linguistics
DOI 10.1162/tacl_a_00544
Open this paper in CoChat — free accountOpen PDF

Abstract

In the last few years, the natural language processing community has witnessed advances in neural representations of free texts with transformer-based language models (LMs). Given the importance of knowledge available in tabular data, recent research efforts extend LMs by developing neural representations for structured data. In this article, we present a survey that analyzes these efforts. We first abstract the different systems according to a traditional machine learning pipeline in terms of training data, input representation, model training, and supported downstream tasks. For each aspect, we characterize and compare the proposed solutions. Finally, we discuss future work directions.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1162/tacl_a_00544

Cites

16 of 16 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Large language models face fundamental constraints processing relational and structured data including tables, databases, and knowledge graphs due to text-based input requirements and sequential architecture limitations.

    “Large language models face fundamental constraints processing relational and structured data including tables, databases, and knowledge graphs due to text-based input requirements and sequential architecture limitations [495, 47, 1145].”

    From A Survey of Context Engineering for Large Language Models (2025) · cites this paper as [47]

    Section 4, “Input Processing” (page not available), says transformers for tabular data require token-sequence input, face input-size limits, and must convert two-dimensional table structure into one dimension. The “Complex Queries & Rich Tables” section also notes that many models assume a single table and struggle with joins. These passages support constraints for tabular models, but not the broader claim about large language models processing databases and knowledge graphs generally. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 91

  1. Rami Aly, Zhijiang Guo, Michael Sejr Schlichtkrull, James Thorne, Andreas Vla- chos, Christos Christodoulopoulos, Oana Cocarascu, and Arpit Mittal. 2021. FEVER- OUS: Fact extraction and VERification over unstructured and structured information. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1).
  2. Wissam Antoun, Fady Baly, and Hazem Hajj. 2020. AraBERT: Transformer-based model for arabic language understanding. In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 9-15.
  3. Gilbert Badaro, Ramy Baly, Hazem Hajj, Wassim El-Hajj, Khaled Bashir Shaban, Nizar Habash, Ahmad Al-Sallab, and Ali Hamdi. 2019. A sur- vey of opinion mining in arabic: A compre- hensive system perspective covering challenges and advances in tools, resources, models, appli- cations, and visualizations. ACM Transactions on Asian and Low-Resource Language Informa- tion Processing (TALLIP), 18(3):1-52.
  4. Gilbert Badaro, Ramy Baly, Hazem Hajj, Nizar Habash, and Wassim El-Hajj. 2014. A large scale arabic sentiment lexicon for arabic opin- ion mining. In Proceedings of the EMNLP 2014 workshop on arabic natural language process- ing (ANLP), pages 165-173.
  5. Gilbert Badaro, Obeida El Jundi, Alaa Khaddaj, Alaa Maarouf, Raslan Kain, Hazem Hajj, and Wassim El-Hajj. 2018a. EMA at SemEval- 2018 task 1: Emotion mining for arabic. In Pro- ceedings of The 12th International Workshop on Semantic Evaluation, pages 236-244.
  6. Gilbert Badaro, Hazem Hajj, and Nizar Habash. 2020. A link prediction approach for accurately mapping a large-scale arabic lexical resource to english wordnet. ACM Transactions on Asian and Low-Resource Language Information Pro- cessing (TALLIP), 19(6):1-38.
  7. Gilbert Badaro, Hussein Jundi, Hazem Hajj, and Wassim El-Hajj. 2018b. EmoWordNet: Auto- matic expansion of emotion lexicon using en- glish wordnet. In Proceedings of the seventh joint conference on lexical and computational semantics, pages 86-93.
  8. Gilbert Badaro and Paolo Papotti. 2022. Trans- formers for tabular data representation: a tuto- rial on models and applications. Proceedings of the VLDB Endowment, 15(12):3746-3749.
  9. Amir Bakarov. 2018. A survey of word em- beddings evaluation methods. arXiv preprint arXiv:1801.09536v1. · arXiv
  10. Jonathan Berant and Percy Liang. 2014. Seman- tic parsing via paraphrasing. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pa- pers), pages 1415-1425.
  11. Chandra Sekhar Bhagavatula, Thanapon Noraset, and Doug Downey. 2015. TabEL: Entity link- ing in web tables. In International Semantic Web Conference, pages 425-441. Springer.
  12. Shikha Bordia and Samuel R Bowman. 2019. Identifying and reducing gender bias in word- level language models. In 2019 Conference of the North American Chapter of the Associ- ation for Computational Linguistics: Human Language Technologies, NAACL HLT 2019- Student Research Workshop, SRW 2019, pages 7-15. Association for Computational Linguis- tics (ACL).
  13. Vadim Borisov, Tobias Leemann, Kathrin Seßler, Johannes Haug, Martin Pawelczyk, and Gjergji Kasneci. 2021. Deep neural networks and tabular data: A survey. arXiv preprint arXiv:2110.01889v3. · arXiv
  14. Tom B. Brown, Benjamin Mann, Nick Ry- der, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agar- wal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Win- ter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCan- dlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. CoRR, abs/2005.14165. · arXiv
  15. Riccardo Cappuzzo, Paolo Papotti, and Saravanan Thirumuruganathan. 2020. Creating embed- dings of heterogeneous relational datasets for data integration tasks. In Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, SIGMOD '20, page 1335-1349, New York, NY, USA. Association for Computing Machinery. · DOI
  16. Yoan Chabot, Pierre Monnin, Frédéric Deuzé, Viet-Phi Huynh, Thomas Labbé, Jixiong Liu, and Raphaël Troncy. 2021. A framework for automatically interpreting tabular data at or- ange. In Proceedings of the 20th International Semantic Web Conference.
  17. Wei-Cheng Chang, Felix X. Yu, Yin-Wen Chang, Yiming Yang, and Sanjiv Kumar. 2020. Pre- training tasks for embedding-based large-scale retrieval. In International Conference on Learning Representations.
  18. Wenhu Chen, Ming-Wei Chang, Eva Schlinger, William Yang Wang, and William W. Cohen. 2021. Open question answering over tables and text. In International Conference on Learning Representations.
  19. Wenhu Chen, Jianshu Chen, Yu Su, Zhiyu Chen, and William Yang Wang. 2020a. Logical nat- ural language generation from open-domain ta- bles. In Proceedings of the 58th Annual Meet- ing of the Association for Computational Lin- guistics, pages 7929-7942.
  20. Wenhu Chen, Hanwen Zha, Zhiyu Chen, Wen- han Xiong, Hong Wang, and William Yang Wang. 2020c. HybridQA: A dataset of multi- hop question answering over tabular and textual data. In Findings of the Association for Com- putational Linguistics: EMNLP 2020, pages 1026-1036, Online. Association for Computa- tional Linguistics. · DOI
  21. Zhiyu Chen, Wenhu Chen, Hanwen Zha, Xiyou Zhou, Yunkai Zhang, Sairam Sundaresan, and William Yang Wang. 2020d. Logic2Text: High-fidelity natural language generation from logical forms. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2096-2111.
  22. Zhiyu Chen, Harini Eavani, Wenhu Chen, Yinyin Liu, and William Yang Wang. 2020e. Few-shot nlg with pre-trained language model. In Pro- ceedings of the 58th Annual Meeting of the As- sociation for Computational Linguistics, pages 183-190.
  23. Zhoujun Cheng, Haoyu Dong, Ran Jia, Pengfei Wu, Shi Han, Fan Cheng, and Dongmei Zhang. 2022. FORTAP: Using formulas for numerical- reasoning-aware table pretraining. In Proceed- ings of the 60th Annual Meeting of the Associ- ation for Computational Linguistics (Volume 1: Long Papers), pages 1150-1166.
  24. Radostin Cholakov and Todor Kolev. 2021. Trans- formers predicting the future. Applying atten- tion in next-frame and time series forecasting. arXiv preprint arXiv:2108.08224v1. · arXiv
  25. Krzysztof Choromanski, Valerii Likhosherstov, David Dohan, Xingyou Song, Andreea Gane, Tamas Sarlos, Peter Hawkins, Jared Davis, David Belanger, Lucy Colwell, et al. 2020. Masked language modeling for proteins via lin- early scalable long-context transformers. arXiv preprint arXiv:2006.03555v3. · arXiv
  26. Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning. 2020. ELEC- TRA: pre-training text encoders as discrimina- tors rather than generators. In 8th Interna- tional Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26- 30, 2020. OpenReview.net.
  27. Sabyasachi Dash, Sushil Kumar Shakyawar, Mo- hit Sharma, and Sandeep Kaushik. 2019. Big data in healthcare: management, analysis and future prospects. Journal of Big Data, 6(1):1- 25.
  28. Xiang Deng, Huan Sun, Alyssa Lees, You Wu, and Cong Yu. 2020. TURL: Table understanding through representation learning. Proceedings of the VLDB Endowment, 14(3):307-319.
  29. Ning Ding, Yujia Qin, Guang Yang, Fuchao Wei, Zonghan Yang, Yusheng Su, Shengding Hu, Yulin Chen, Chi-Min Chan, Weize Chen, et al. 2022. Delta tuning: A comprehen- sive study of parameter efficient methods for pre-trained language models. arXiv preprint arXiv:2203.06904v2. · arXiv
  30. Haoyu Dong, Zhoujun Cheng, Xinyi He, Mengyu Zhou, Anda Zhou, Fan Zhou, Ao Liu, Shi Han, and Dongmei Zhang. 2022. Table pre-training: A survey on model architectures, pre-training objectives, and downstream tasks. In Pro- ceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pages 5426-5435. International Joint Confer- ences on Artificial Intelligence Organization. Survey Track. · DOI
  31. Haoyu Dong, Shijie Liu, Zhouyu Fu, Shi Han, and Dongmei Zhang. 2019. Semantic structure ex- traction for spreadsheet tables with a multi-task learning architecture. In Workshop on Docu- ment Intelligence at NeurIPS 2019.
  32. Yihe Dong, Jean-Baptiste Cordonnier, and An- dreas Loukas. 2021. Attention is not all you need: Pure attention loses rank doubly expo- nentially with depth. In International Confer- ence on Machine Learning, pages 2793-2803.
  33. PMLR.
  34. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations.
  35. Lun Du, Fei Gao, Xu Chen, Ran Jia, Junshan Wang, Jiang Zhang, Shi Han, and Dongmei Zhang. 2021. TabularNet: A neural network ar- chitecture for understanding semantic structures of tabular data. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pages 322-331.
  36. Julian Eisenschlos, Maharshi Gor, Thomas Mueller, and William Cohen. 2021. MATE: Multi-view attention for table transformer ef- ficiency. In Proceedings of the 2021 Confer- ence on Empirical Methods in Natural Lan- guage Processing, pages 7606-7619.
  37. Majid Ghasemi-Gol and Pedro A. Szekely. 2018. TabVec: Table vectors for classification of web tables. CoRR, abs/1802.06290. · arXiv
  38. Michael Glass, Mustafa Canim, Alfio Gliozzo, Saneem Chemmengath, Vishwajeet Kumar, Rishav Chakravarti, Avirup Sil, Feifei Pan, Samarth Bharadwaj, and Nicolas Rodolfo Fauceglia. 2021. Capturing row and column se- mantics in transformer based question answer- ing over tables. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1212- 1224.
  39. Heng Gong, Yawei Sun, Xiaocheng Feng, Bing Qin, Wei Bi, Xiaojiang Liu, and Ting Liu. 2020. TableGPT: Few-shot table-to-text generation with table structure reconstruction and content matching. In Proceedings of the 28th Interna- tional Conference on Computational Linguis- tics, pages 1978-1988.
  40. Yury Gorishniy, Ivan Rubachev, Valentin Khrulkov, and Artem Babenko. 2021. Revis- iting deep learning models for tabular data. Advances in Neural Information Processing Systems, 34:18932-18943.
  41. Poonam Gupta and Vishal Gupta. 2012. A survey of text question answering techniques. Interna- tional Journal of Computer Applications, 53(4).
  42. Jonathan Herzig, Thomas Mueller, Syrine Krich- ene, and Julian Eisenschlos. 2021. Open do- main question answering over tables via dense retrieval. In Proceedings of the 2021 Confer- ence of the North American Chapter of the As- sociation for Computational Linguistics: Hu- man Language Technologies, pages 512-519.
  43. Jonathan Herzig, Pawel Krzysztof Nowak, Thomas Mueller, Francesco Piccinno, and Julian Eisenschlos. 2020. TaPas: Weakly supervised table parsing via pre-training. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4320-4333.
  44. Kevin Hu, Snehalkumar'Neil'S Gaikwad, Made- lon Hulsebos, Michiel A Bakker, Emanuel Zgraggen, César Hidalgo, Tim Kraska, Guo- liang Li, Arvind Satyanarayan, and Çagatay Demiralp. 2019. VizNet: Towards a large-scale visualization learning and benchmarking repos- itory. In Proceedings of the 2019 CHI Confer- ence on Human Factors in Computing Systems, pages 1-12.
  45. Kexin Huang, Jaan Altosaar, and Rajesh Ran- ganath. 2019. ClinicalBERT: Modeling clini- cal notes and predicting hospital readmission. arXiv preprint arXiv:1904.05342v3. · arXiv
  46. Hiroshi Iida, Dung Thai, Varun Manjunatha, and Mohit Iyyer. 2021. TABBIE: Pretrained repre- sentations of tabular data. In Proceedings of the 2021 Conference of the North American Chap- ter of the Association for Computational Lin- guistics: Human Language Technologies, pages 3446-3456.
  47. Sujay Kumar Jauhar, Peter Turney, and Eduard Hovy. 2016. TabMCQ: A dataset of general knowledge tables and multiple-choice ques- tions. arXiv preprint arXiv:1602.03960v1. · arXiv
  48. Georgios Karagiannis, Mohammed Saeed, Paolo Papotti, and Immanuel Trummer. 2020. Scru- tinizer: A mixed-initiative approach to large- scale, data-driven claim verification. Proc. VLDB Endow., 13(11):2508-2521.
  49. Marcin Kaszkiel and Justin Zobel. 1997. Passage retrieval revisited. In SIGIR, pages 178-185. ACM. · DOI
  50. PMLR.
  51. George Katsogiannis-Meimarakis and Georgia Koutrika. 2021. A deep dive into deep learning approaches for text-to-SQL systems. In Pro- ceedings of the 2021 International Conference on Management of Data, pages 2846-2851.
  52. Salman Khan, Muzammal Naseer, Munawar Hayat, Syed Waqas Zamir, Fahad Shahbaz Khan, and Mubarak Shah. 2021. Transform- ers in vision: A survey. arXiv preprint arXiv:2101.01169. · arXiv
  53. Nikita Kitaev, Lukasz Kaiser, and Anselm Lev- skaya. 2020. Reformer: The efficient trans- former. In International Conference on Learn- ing Representations.
  54. Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, Mirella Lapata, and Hannaneh Hajishirzi. 2019. Text generation from knowledge graphs with graph transformers. In Proceedings of the 2019 Conference of the North American Chap- ter of the Association for Computational Lin- guistics: Human Language Technologies, Vol- ume 1 (Long and Short Papers), pages 2284- 2293.
  55. Daniel Z Korman, Eric Mack, Jacob Jett, and Allen H Renear. 2018. Defining textual entail- ment. Journal of the Association for Informa- tion Science and Technology, 69(6):763-772.
  56. Bogdan Kostić, Julian Risch, and Timo Möller. 2021. Multi-modal retrieval of tables and texts using tri-encoder models. In Proceedings of the 3rd Workshop on Machine Reading for Ques- tion Answering, pages 82-91, Punta Cana, Do- minican Republic. Association for Computa- tional Linguistics.
  57. Zhenzhong Lan, Mingda Chen, Sebastian Good- man, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: A lite BERT for self-supervised learning of language representa- tions. In International Conference on Learning Representations.
  58. Oliver Lehmberg, Dominique Ritze, Robert Meusel, and Christian Bizer. 2016. A large pub- lic corpus of web tables containing time and context metadata. In Proceedings of the 25th International Conference Companion on World Wide Web, pages 75-76.
  59. Junyi Li, Tianyi Tang, Wayne Xin Zhao, Zhicheng Wei, Nicholas Jing Yuan, and Ji-Rong Wen. 2021. Few-shot knowledge graph-to-text gener- ation with pretrained language models. In Find- ings of the Association for Computational Lin- guistics: ACL-IJCNLP 2021, pages 1558-1568.
  60. Yuliang Li, Jinfeng Li, Yoshihiko Suhara, AnHai Doan, and Wang-Chiew Tan. 2020. Deep en- tity matching with pre-trained language models. Proc. VLDB Endow., 14(1):50-60. · DOI
  61. Qian Liu, Bei Chen, Jiaqi Guo, Zeqi Lin, and Jian-guang Lou. 2021a. TAPEX: Table pre- training via learning a neural SQL executor. arXiv preprint arXiv:2107.07653v3. · arXiv
  62. Ruibo Liu, Chenyan Jia, Jason Wei, Guangx- uan Xu, Lili Wang, and Soroush Vosoughi. 2021b. Mitigating political bias in language models through reinforced calibration. In Thirty-Fifth AAAI Conference on Artificial In- telligence, AAAI, pages 14857-14866. AAAI Press.
  63. Preslav Nakov, David Corney, Maram Hasanain, Firoj Alam, Tamer Elsayed, Alberto Barrón- Cedeño, Paolo Papotti, Shaden Shaar, and Gio- vanni Da San Martino. 2021. Automated fact- checking for assisting human fact-checkers. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, pages 4551-4558. International Joint Confer- ences on Artificial Intelligence Organization. Survey Track. · DOI
  64. J. Neeraja, Vivek Gupta, and Vivek Srikumar. 2021. Incorporating external knowledge to en- hance tabular reasoning. In Proceedings of the 2021 Conference of the North American Chap- ter of the Association for Computational Lin- guistics, pages 2799-2809, Online. Association for Computational Linguistics. · DOI
  65. Feifei Pan, Mustafa Canim, Michael Glass, Alfio Gliozzo, and Peter Fox. 2021. CLTR: An end- to-end, transformer-based system for cell-level table retrieval and table question answering. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Nat- ural Language Processing: System Demonstra- tions, pages 202-209, Online. Association for Computational Linguistics. · DOI
  66. Ankur Parikh, Xuezhi Wang, Sebastian Gehrmann, Manaal Faruqui, Bhuwan Dhingra, Diyi Yang, and Dipanjan Das. 2020. ToTTo: A controlled table-to-text generation dataset. In Proceedings of the 2020 Conference on Empir- ical Methods in Natural Language Processing (EMNLP), pages 1173-1186.
  67. Panupong Pasupat and Percy Liang. 2015. Com- positional semantic parsing on semi-structured tables. In Proceedings of the 53rd Annual Meet- ing of the Association for Computational Lin- guistics and the 7th International Joint Confer- ence on Natural Language Processing (Volume 1: Long Papers), pages 1470-1480, Beijing, China. Association for Computational Linguis- tics. · DOI · Paper page
  68. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. 2019. Language models are unsupervised mul- titask learners. OpenAI blog, 1(8):9.
  69. Roy Schwartz, Jesse Dodge, Noah A Smith, and Oren Etzioni. 2020. Green AI. Communica- tions of the ACM, 63(12):54-63.
  70. Ravid Shwartz-Ziv and Amitai Armon. 2021. Tabular data: Deep learning is not all you need. In 8th ICML Workshop on Automated Machine Learning (AutoML).
  71. Gowthami Somepalli, Micah Goldblum, Avi Schwarzschild, C Bayan Bruss, and Tom Goldstein. 2021. SAINT: Improved neural networks for tabular data via row attention and contrastive pre-training. arXiv preprint arXiv:2106.01342v1. · arXiv
  72. Yoshihiko Suhara, Jinfeng Li, Yuliang Li, Dan Zhang, Çagatay Demiralp, Chen Chen, and Wang-Chiew Tan. 2022. Annotating columns with pre-trained language models. In Proceed- ings of the 2022 International Conference on Management of Data, pages 1493-1503.
  73. Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neu- ral networks. In Proceedings of the 27th In- ternational Conference on Neural Information Processing Systems -Volume 2, NIPS'14, page 3104-3112, Cambridge, MA, USA. MIT Press.
  74. Nan Tang, Ju Fan, Fangyi Li, Jianhong Tu, Xi- aoyong Du, Guoliang Li, Samuel Madden, and Mourad Ouzzani. 2021. RPT: Relational pre- trained transformer is almost all you need to- wards democratizing data preparation. Proc. VLDB Endow., 14(8):1254-1261.
  75. Yi Tay, Mostafa Dehghani, Dara Bahri, and Don- ald Metzler. 2020. Efficient transformers: A survey. CoRR, abs/2009.06732. · arXiv
  76. James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. FEVER: a large-scale dataset for fact extraction and verification. In Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT, pages 809-819. · DOI · Paper page
  77. ACL.
  78. James Thorne, Majid Yazdani, Marzieh Saeidi, Fabrizio Silvestri, Sebastian Riedel, and Alon Halevy. 2021. Database reasoning over text. 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), pages 3091-3104, Online. Association for Computational Linguistics. · DOI
  79. Roger PG Van Gompel and Martin J Pickering. 2007. Syntactic parsing. The Oxford handbook of psycholinguistics, pages 289-307.
  80. Enzo Veltri, Gilbert Badaro, Mohammed Saeed, and Paolo Papotti. 2023. Data ambiguity pro- filing for the generation of training examples. In 39th IEEE International Conference on Data Engineering, ICDE 2023, Anaheim, California, USA, April 3-7, 2023. IEEE.
  81. Enzo Veltri, Donatello Santoro, Gilbert Badaro, Mohammed Saeed, and Paolo Papotti. 2022. Pythia: Unsupervised generation of ambiguous textual claims from relational data. In Pro- ceedings of the 2022 International Conference on Management of Data, SIGMOD '22, page 2409-2412, New York, NY, USA. Association for Computing Machinery. · DOI
  82. Jesse Vig, Sebastian Gehrmann, Yonatan Be- linkov, Sharon Qian, Daniel Nevo, Yaron Singer, and Stuart Shieber. 2020. Investigat- ing gender bias in language models using causal mediation analysis. Advances in Neural Infor- mation Processing Systems, 33:12388-12401.
  83. Fei Wang, Kexuan Sun, Muhao Chen, Jay Pujara, and Pedro Szekely. 2021a. Retrieving complex tables with multi-granular graph representation learning. In Proceedings of the 44th Interna- tional ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR '21, page 1472-1482, New York, NY, USA. As- sociation for Computing Machinery. · DOI
  84. Zhiruo Wang, Haoyu Dong, Ran Jia, Jia Li, Zhiyi Fu, Shi Han, and Dongmei Zhang. 2021b. TUTA: Tree-based transformers for generally structured table pre-training. In Proceedings of the 27th ACM SIGKDD Conference on Knowl- edge Discovery & Data Mining, pages 1780- 1790.
  85. Zhiruo Wang, Zhengbao Jiang, Eric Nyberg, and Graham Neubig. 2022. Table retrieval may not necessitate table-specific model design. arXiv preprint arXiv:2205.09843v1. · arXiv
  86. Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I Wang, et al. 2022. UnifiedSKG: Uni- fying and multi-tasking structured knowledge grounding with text-to-text language models. arXiv preprint arXiv:2201.05966v3. · arXiv
  87. Xiaoyu Yang and Xiaodan Zhu. 2021. Exploring decomposition for table-based fact verification. In EMNLP, pages 1045-1052, Punta Cana, Do- minican Republic. Association for Computa- tional Linguistics.
  88. Tao Yu, Chien-Sheng Wu, Xi Victoria Lin, bailin wang, Yi Chern Tan, Xinyi Yang, Dragomir Radev, richard socher, and Caiming Xiong. 2021. GraPPa: Grammar-augmented pre- training for table semantic parsing. In Interna- tional Conference on Learning Representations.
  89. Tao Yu, Rui Zhang, Kai Yang, Michihiro Ya- sunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, Zilin Zhang, and Dragomir Radev. 2018. Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to- SQL task. In Proceedings of the 2018 Con- ference on Empirical Methods in Natural Lan- guage Processing, pages 3911-3921, Brussels, Belgium. Association for Computational Lin- guistics. · DOI · Paper page
  90. Shuo Zhang and Krisztian Balog. 2017. EntiTa- bles: Smart assistance for entity-focused tables. In Proceedings of the 40th International ACM SIGIR Conference on Research and Develop- ment in Information Retrieval, pages 255-264. ACM. · DOI
  91. Victor Zhong, Caiming Xiong, and Richard Socher. 2017. Seq2SQL: Generating struc- tured queries from natural language using reinforcement learning. arXiv preprint arXiv:1709.00103v7. · arXiv

Cited by

Sorted by citations

Authors
Badaro, G., Saeed, M., & Papotti, P.
Affiliations
EURECOM (FR)
Corresponding author
  • Badaro, Gilbert
  • Saeed, Mohammed
  • Papotti, Paolo
ORCID
Venue
Transactions of the Association for Computational Linguistics
Publisher
MIT Press
Published
2023
Volume
11
Pages
227-249
ISSN
2307-387X (ISSN-L)
DOI
10.1162/tacl_a_00544
OpenAlex
W4310390625
Cited by
96
References
16
Citations by year
2026: 32 · 2025: 38 · 2024: 18 · 2023: 6 · 2022: 2
FWCI
8.11
Type
journal article
Language
en
Open access
Licence
Locations
  • Transactions of the Association for Computational Linguistics (publishedVersion, cc-by)
  • HAL (submittedVersion, other-oa)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Agence Nationale de la Recherche (ANR-21-CE23-0037)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
Keywords
transformer models, structured data, neural representations, language models, tabular data classification, tabular data generation, training data, input representation, downstream tasks

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review