Multi-Paragraph Machine Reading Comprehension with Hybrid Reader over Tables and Text

References

• Campos, D. F., T. Nguyen, M. Rosenberg, X. Song, J. Gao, S. Tiwary, R. Majumder, L. Deng, and B. Mitra. 2016. Ms marco: A human generated machine reading comprehension dataset. arXiv Preprint arXiv:150302531 2.
   Google Scholar
• Chai, Y., M. Chen, H. Wu, and S. Wang. 2023. Fin-EMRC: An efficient machine reading comprehension framework for financial entity-relation extraction. Institute of Electrical and Electronics Engineers Access 11:82685–25. doi:10.1109/ACCESS.2023.3299880.
   Google Scholar
• Chen, Z., W. Chen, C. Smiley, S. Shah, I. Borova, D. Langdon, R. N. Moussa, M. Beane, T. H. Huang, B. Routledge, et al. 2021. FinQA: A dataset of numerical reasoning over financial data. arXiv Preprint arXiv: 150302531 2. https://api.semanticscholar.org/CorpusID:235399966.
   Google Scholar
• Chen, W., M.-W. Chang, E. Schlinger, W. Yang Wang, and W. W. Cohen. 2020. Open question answering over tables and text. arXiv Preprint arXiv: 150302531 2. https://api.semanticscholar.org/CorpusID:224803601.
   Google Scholar
• Devlin, J., M.-W. Chang, K. Lee, and K. Toutanova. 2018. Bert: Pre- training of deep bidirectional transformers for language understanding. arXiv Preprint arXiv:1810.04805.
   Google Scholar
• Ding, J., W. Hu, Q. Xu, and Y. Qu. 2019. Leveraging frequent query substructures to generate formal queries for complex question answering. arXiv Preprint arXiv:150302531 2. https://api.semanticscholar.org/CorpusID:201668424.
   Google Scholar
• Dong, R., X. Wang, L. Dong, and Z. Zhang. 2023. Multi-passage extraction- based machine reading comprehension based on verification sorting. Computers & Electrical Engineering 106:108576. issn: 0045-7906. https://www.sciencedirect.com/science/article/pii/S0045790623000010. doi:10.1016/j.compeleceng.2023.108576.
   Web of Science ®Google Scholar
• Eisenschlos, J. M., M. Gor, T. Müller, and W. W. Cohen. 2021. MATE: Multi-view attention for table transformer efficiency. Conference on Em- pirical Methods in Natural Language Processing, Punta Cana, Dominican Republic.
   Google Scholar
• Eisenschlos, J. M., S. Krichene, and T. Müller. 2020. Understanding tables with intermediate pre-training. arXiv Preprint arXiv: 150302531 2. https://api.semanticscholar.org/CorpusID:222090330.
   Google Scholar
• Herzig, J., P.-L. K. Nowak, T. Müller, F. Piccinno, and J. M. Eisenschlos. 2020. TaPas: Weakly supervised table parsing via pre-training. arXiv Preprint arXiv:2004.02349.
   Google Scholar
• Hochreiter, S., and J. Schmidhuber. 1997. Long short-term memory. Neural Computation 9 (8):1735–80. doi:10.1162/neco.1997.9.8.1735.
   PubMed Web of Science ®Google Scholar
• Joshi, M., E. Choi, D. S. Weld, and L. Zettlemoyer. 2017. Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension. arXiv Preprint arXiv: 1705.03551.
   Google Scholar
• Kim, Y., S. Lim, H. Lee, S. Park, and M. Kim. 2019. KorQuAD 2.0: Korean QA dataset for web document machine comprehension. Annual Conference on Human and Language Technology, Daejeon, South Korea, 97–102, Human and Language Technology.
   Google Scholar
• Kwiatkowski, T., J. Palomaki, O. Redfield, M. Collins, A. Parikh, C. Alberti, D. Epstein, I. Polosukhin, J. Devlin, K. Lee, et al. 2019. Natural questions: A benchmark for question answering research. Transactions of the Association for Computational Linguistics 7:453–66. doi:10.1162/tacl_a_00276.
   Google Scholar
• Lim, S., M. Kim, and J. Lee. 2019. Korquad1. 0: Korean qa dataset for machine reading comprehension. arXiv Preprint arXiv:1909.07005.
   Google Scholar
• Liu, Y., M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, and V. Stoyanov. 2019. Roberta: A robustly optimized Bert pretraining approach. arXiv Preprint arXiv:1907.11692.
   Google Scholar
• Li, C., W. Ye, and Y. Zhao. 2022. FinMath: Injecting a tree-structured solver for question answering over financial reports. International Conference on Language Resources and Evaluation. https://api.semanticscholar.org/CorpusID:252432931.
   Google Scholar
• Nararatwong, R., N. Kertkeidkachorn, and R. Ichise. 2022. Enhancing financial table and text question answering with tabular graph and numerical reasoning. AACL. https://api.semanticscholar.org/CorpusID:253761979.
   Google Scholar
• Park, C., M. Kim, S. Park, S. Lim, J. Lee, and C. Lee. 2020. Korean TableQA: Structured data question answering based on span prediction style with S3-NET. ETRI Journal 42 (6):899–911. doi:10.4218/etrij.2019-0189.
   Web of Science ®Google Scholar
• Park, S., S. Lim, M. Kim, and J. Lee. 2018. TabQA: Question answering model for table data. https://api.semanticscholar.org/CorpusID:238431804.
   Google Scholar
• Park, S., J. Moon, S. Kim, W. Ik Cho, J. Han, J. Park, C. Song, J. Kim, Y. Song, T. Oh, et al. 2021. Klue: Korean language understanding evaluation. arXiv Preprint arXiv:2105.09680.
   Google Scholar
• Rajpurkar, P., R. Jia, and P. Liang. 2018. Know what you don’t know: Unan- swerable questions for SQuAD. arXiv Preprint arXiv:1806.03822.
   Google Scholar
• Rajpurkar, P., J. Zhang, K. Lopyrev, and P. Liang. 2016a. SQuAD: 100, 000+ questions for machine comprehension of text. CoRR Abs/1606.05250. arXiv: 1606.05250. http://arxiv.org/abs/1606.05250.
   Google Scholar
• Rajpurkar, P., J. Zhang, K. Lopyrev, and P. Liang. 2016b. Squad: 100,000+ questions for machine comprehension of text. arXiv Preprint arXiv: 1606.05250.
   Google Scholar
• Seo, M., A. Kembhavi, A. Farhadi, and H. Hajishirzi. 2016. Bidirectional attention flow for machine comprehension. arXiv Preprint arXiv: 1611.01603.
   Google Scholar
• Wang, R., D. Tang, N. Duan, Z. Wei, X. Huang, G. Cao, D. Jiang, M. Zhou. 2020. K-adapter: Infusing knowledge into pre-trained models with adapters. arXiv Preprint arXiv:2002.01808.
   Google Scholar
• Yang, Y., M. C. S. Uy, and A. Huang. 2020. FinBERT: A pretrained language model for financial communications. CoRR Abs/2006.08097 arXiv: 2006.08097. https://arxiv.org/abs/2006.08097.
   Google Scholar
• Yin, P., G. Neubig, W.-T. Yih, and S. Riedel. 2020. TaBERT: Pretraining for joint understanding of textual and tabular data. arXiv Preprint arXiv:2005.08314.
   Google Scholar
• Yu, A. W., D. Dohan, M.-T. Luong, R. Zhao, K. Chen, M. Norouzi, and Q. V. Le. 2018. Qanet: Combining local convolution with global self-attention for reading comprehension. arXiv Preprint arXiv:1804.09541.
   Google Scholar
• Yu, T., C.-S. Wu, X. V. Lin, B. Wang, Y. C. Tan, X. Yang, D. Radev, R. Socher, and C. Xiong. 2020. GraPPa: Grammar-augmented pre-training for table semantic parsing. arXiv Preprint arXiv:2009.13845.
   Google Scholar
• Zaheer, M., G. Guruganesh, K. A. Dubey, J. Ainslie, C. Alberti, S. Ontañón, P. Pham, A. Ravula, Q. Wang, L. Yang, et al. 2020. Big Bird: Transformers for longer sequences. arXiv Preprint arXiv:150302531 2.
   Google Scholar
• Zhang, Z., J. Yang, and H. Zhao. 2021. Retrospective reader for machine reading comprehension. Proceedings of the AAAI Conference on Artificial Intelligence 35 (16):14506–14. doi:10.1609/aaai.v35i16.17705.
   Google Scholar
• Zhang, Y., and H. Zhang. 2022. FinBERT–MRC: Financial named entity recognition using BERT under the machine reading comprehension paradigm. Neural Processing Letters 55 (6):7393–413. https://api.semanticscholar.org/CorpusID:249210021.
   Web of Science ®Google Scholar
• Zhong, V., C. Xiong, and R. Socher. 2017. Seq2SQL: Generating structured queries from natural language using reinforcement learning. CoRR Abs/1709.00103. arXiv: 1709.00103. http://arxiv.org/abs/1709.00103.
   Google Scholar
• Zhou, Y., J. Bao, C. Duan, Y. Wu, X. He, and T. Zhao. 2022. UniRPG: Unified discrete reasoning over table and text as program generation. arXiv Preprint arXiv:150302531 2 Abs/2210.08249. https://api.semanticscholar.org/CorpusID:252918014.
   Google Scholar
• Zhu, F., W. Lei, Y. Huang, C. Wang, S. Zhang, J. Lv, F. Feng, and T.-S. Chua. 2021. TAT-QA: A question answering benchmark on a hybrid of tabular and textual content in finance. arXiv Preprint arXiv:150302531 2 Abs/2105.07624. https://api.semanticscholar.org/CorpusID:234741852.
   Google Scholar