{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T03:39:19Z","timestamp":1768966759918,"version":"3.49.0"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705328","type":"print"},{"value":"9783031705335","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70533-5_27","type":"book-chapter","created":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:02:25Z","timestamp":1725685345000},"page":"470-487","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["DocTabQA: Answering Questions from\u00a0Long Documents Using Tables"],"prefix":"10.1007","author":[{"given":"Haochen","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangcai","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,8]]},"reference":[{"key":"27_CR1","doi-asserted-by":"publisher","unstructured":"Ahmed, S., Jawade, B., Pandey, S., Setlur, S., Govindaraju, V.: Realcqa: scientific chart question answering as a test-bed for first-order logic. In: ICDAR, pp. 66\u201383. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-41682-8_5","DOI":"10.1007\/978-3-031-41682-8_5"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: ICCV, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Bao, J., et al.: Table-to-text: describing table region with natural language. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11944"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Choi, E., et al.: QUAC: question answering in context. In: EMNLP, pp. 2174\u20132184 (2018)","DOI":"10.18653\/v1\/D18-1241"},{"key":"27_CR5","unstructured":"Dai, Z., et al.: Promptagator: few-shot dense retrieval from 8 examples. In: ICLR (2023)"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Fan, A., Jernite, Y., Perez, E., Grangier, D., Weston, J., Auli, M.: ELI5: long form question answering. In: ACL, pp. 3558\u20133567 (2019)","DOI":"10.18653\/v1\/P19-1346"},{"key":"27_CR7","unstructured":"Gao, Y., et al.: Retrieval-augmented generation for large language models: a survey. arXiv preprint arXiv:2312.10997 (2023)"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"He, Y., Hu, J., Tang, B.: Revisiting event argument extraction: can EAE models learn better when being aware of event co-occurrences? In: ACL, pp. 12542\u201312556 (2023)","DOI":"10.18653\/v1\/2023.acl-long.701"},{"key":"27_CR9","unstructured":"Hu, E.J., et al.: LORA: low-rank adaptation of large language models. In: ICLR (2022)"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Huang, X., Zhang, J., Li, D., Li, P.: Knowledge graph embedding based question answering. In: WSDM, pp. 105\u2013113 (2019)","DOI":"10.1145\/3289600.3290956"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Iyyer, M., Boyd-Graber, J., Claudino, L., Socher, R., Daum\u00e9\u00a0III, H.: A neural network for factoid question answering over paragraphs. In: EMNLP, pp. 633\u2013644 (2014)","DOI":"10.3115\/v1\/D14-1070"},{"key":"27_CR12","doi-asserted-by":"publisher","unstructured":"Jin, N., Siebert, J., Li, D., Chen, Q.: A survey on table question answering: recent advances. In: CCKS, pp. 174\u2013186. Springer (2022). https:\/\/doi.org\/10.1007\/978-981-19-7596-7_14","DOI":"10.1007\/978-981-19-7596-7_14"},{"key":"27_CR13","unstructured":"Khot, T., et al.: Decomposed prompting: a modular approach for solving complex tasks. arXiv preprint arXiv:2210.02406 (2022)"},{"key":"27_CR14","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1162\/tacl_a_00023","volume":"6","author":"T Ko\u010disk\u00fd","year":"2018","unstructured":"Ko\u010disk\u00fd, T., et al.: The NarrativeQA reading comprehension challenge. Trans. Assoc. Comput. Linguist. 6, 317\u2013328 (2018)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Kwok, C.C., Etzioni, O., Weld, D.S.: Scaling question answering to the web. In: WWW, pp. 150\u2013161 (2001)","DOI":"10.1145\/371920.371973"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Lebret, R., Grangier, D., Auli, M.: Neural text generation from structured data with application to the biography domain. In: EMNLP, pp. 1203\u20131213 (2016)","DOI":"10.18653\/v1\/D16-1128"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Lelkes, A.D., Tran, V.Q., Yu, C.: Quiz-style question generation for news stories. In: WWW, pp. 2501\u20132511 (2021)","DOI":"10.1145\/3442381.3449892"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: ACL, pp. 7871\u20137880 (2020)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"27_CR19","unstructured":"Lewis, P., et\u00a0al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: NeurIPS, pp. 9459\u20139474 (2020)"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Li, T., Wang, Z., Shao, L., Zheng, X., Wang, X., Su, J.: A sequence-to-sequence &set model for text-to-table generation. In: ACL-Findings, pp. 5358\u20135370 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.330"},{"key":"27_CR21","unstructured":"Li, X., Li, J.: Angle-optimized text embeddings. arXiv preprint arXiv:2309.12871 (2023)"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Liu, T., Wang, K., Sha, L., Chang, B., Sui, Z.: Table-to-text generation by structure-aware seq2seq learning. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11925"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Ma, X., Gong, Y., He, P., Zhao, H., Duan, N.: Query rewriting for retrieval-augmented large language models. In: EMNLP, pp. 5303\u20135315 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.322"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: DOCVQA: a dataset for VQA on document images. In: WACV, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Nayak, T., Ng, H.T.: Effective modeling of encoder-decoder architecture for joint entity and relation extraction. In: AAAI, pp. 8528\u20138535 (2020)","DOI":"10.1609\/aaai.v34i05.6374"},{"key":"27_CR26","unstructured":"Ni, X., Li, P.: Unified text structuralization with instruction-tuned language models. arXiv preprint arXiv:2303.14956 (2023)"},{"key":"27_CR27","unstructured":"OpenAI: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Pandya, H.A., Bhatt, B.S.: Question answering survey: Directions, challenges, datasets, evaluation matrices. arXiv preprint arXiv:2112.03572 (2021)","DOI":"10.20944\/preprints202112.0136.v1"},{"key":"27_CR29","unstructured":"Pietruszka, M., et al.: Stable: Table generation framework for encoder-decoder models. arXiv preprint arXiv:2206.04045 (2022)"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Popovi\u0107, M.: CHRF: character n-gram F-score for automatic MT evaluation. In: WMT, pp. 392\u2013395 (2015)","DOI":"10.18653\/v1\/W15-3049"},{"issue":"8","key":"27_CR31","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"27_CR32","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1) (2020)"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Jia, R., Liang, P.: Know what you don\u2019t know: unanswerable questions for SQuAD. In: ACL, pp. 784\u2013789 (2018)","DOI":"10.18653\/v1\/P18-2124"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: EMNLP-IJCNLP, pp. 3982\u20133992 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Rossiello, G., Chowdhury, M.F.M., Mihindukulasooriya, N., Cornec, O., Gliozzo, A.M.: Knowgl: knowledge generation and linking from text. In: AAAI, pp. 16476\u201316478 (2023)","DOI":"10.1609\/aaai.v37i13.27084"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: CVPR, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"27_CR37","unstructured":"Song, K., Tan, X., Qin, T., Lu, J., Liu, T.Y.: MPNET: masked and permuted pre-training for language understanding. In: NeurIPS, pp. 16857\u201316867 (2020)"},{"key":"27_CR38","unstructured":"Sun, G., Liang, L., Li, T., Yu, B., Wu, M., Zhang, B.: Video question answering: a survey of models and datasets. Mob. Netw. Appl. 1\u201334 (2021)"},{"key":"27_CR39","doi-asserted-by":"crossref","unstructured":"Tang, X., Zong, Y., Zhao, Y., Cohan, A., Gerstein, M.: Struc-bench: Are large language models really good at generating complex structured data? arXiv preprint arXiv:2309.08963 (2023)","DOI":"10.18653\/v1\/2024.naacl-short.2"},{"key":"27_CR40","unstructured":"Touvron, H., et\u00a0al.: Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Wang, L., Yang, N., Wei, F.: Query2doc: query expansion with large language models. In: EMNLP, pp. 9414\u20139423 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.585"},{"key":"27_CR42","unstructured":"Wang, W., Wei, F., Dong, L., Bao, H., Yang, N., Zhou, M.: Minilm: deep self-attention distillation for task-agnostic compression of pre-trained transformers. In: NeurIPS, pp. 5776\u20135788 (2020)"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: TUTA: tree-based transformers for generally structured table pre-training. In: KDD, pp. 1780\u20131790 (2021)","DOI":"10.1145\/3447548.3467434"},{"key":"27_CR44","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: NeurIPS, pp. 24824\u201324837 (2022)"},{"key":"27_CR45","doi-asserted-by":"crossref","unstructured":"Whitehouse, C., Vania, C., Aji, A.F., Christodoulopoulos, C., Pierleoni, A.: WebIE: faithful and robust information extraction on the web. In: ACL, pp. 7734\u20137755 (2023)","DOI":"10.18653\/v1\/2023.acl-long.428"},{"key":"27_CR46","doi-asserted-by":"crossref","unstructured":"Wiseman, S., Shieber, S., Rush, A.: Challenges in data-to-document generation. In: EMNLP, pp. 2253\u20132263 (2017)","DOI":"10.18653\/v1\/D17-1239"},{"key":"27_CR47","doi-asserted-by":"crossref","unstructured":"Wu, X., Zhang, J., Li, H.: Text-to-table: a new way of information extraction. In: ACL, pp. 2518\u20132533 (2022)","DOI":"10.18653\/v1\/2022.acl-long.180"},{"issue":"7","key":"27_CR48","doi-asserted-by":"publisher","first-page":"271","DOI":"10.3390\/info12070271","volume":"12","author":"M Yani","year":"2021","unstructured":"Yani, M., Krisnadhi, A.A.: Challenges, techniques, and trends of simple knowledge graph question answering: a survey. Information 12(7), 271 (2021)","journal-title":"Information"},{"key":"27_CR49","doi-asserted-by":"crossref","unstructured":"Yu, Z., Xiong, C., Yu, S., Liu, Z.: Augmentation-adapted retriever improves generalization of language models as generic plug-in. In: ACL, pp. 2421\u20132436 (2023)","DOI":"10.18653\/v1\/2023.acl-long.136"},{"key":"27_CR50","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: evaluating text generation with BERT. In: ICLR (2020)"},{"key":"27_CR51","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Ji, W., Xiao, J., Li, Y., Deng, W., Chua, T.S.: Video question answering: datasets, algorithms and challenges. In: EMNLP, pp. 6439\u20136455 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.432"},{"key":"27_CR52","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Chen, D.: A frustratingly easy approach for entity and relation extraction. In: NAACL, pp. 50\u201361 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.5"},{"key":"27_CR53","unstructured":"Zhou, D., et\u00a0al.: Least-to-most prompting enables complex reasoning in large language models. arXiv preprint arXiv:2205.10625 (2022)"},{"key":"27_CR54","doi-asserted-by":"crossref","unstructured":"Zhu, F., Lei, W., Huang, Y., Wang, C., Zhang, S., Lv, J., Feng, F., Chua, T.S.: TAT-QA: a question answering benchmark on a hybrid of tabular and textual content in finance. In: ACL-IJCNLP, pp. 3277\u20133287 (2021)","DOI":"10.18653\/v1\/2021.acl-long.254"},{"key":"27_CR55","doi-asserted-by":"crossref","unstructured":"Zou, Y., Xie, Q.: A survey on VQA: datasets and approaches. In: CIT, pp. 289\u2013297. IEEE (2020)","DOI":"10.1109\/ITCA52113.2020.00069"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70533-5_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:09:59Z","timestamp":1725685799000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70533-5_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705328","9783031705335"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70533-5_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"8 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}