{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T07:25:50Z","timestamp":1769585150955,"version":"3.49.0"},"reference-count":28,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T00:00:00Z","timestamp":1700438400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems: Applications in Engineering and Technology"],"published-print":{"date-parts":[[2024,1,10]]},"abstract":"<jats:p>Hybrid tabular-textual question answering (QA) is a crucial task in natural language processing that involves reasoning and locating answers from various information sources, primarily through numerical reasoning and span extraction. Cur-rent techniques in numerical reasoning often rely on autoregressive models to decode program sequences. However, these methods suffer from exposure bias and error propagation, which can significantly decrease the accuracy of program generation as the decoding process unfolds. To address these challenges, this paper proposes a novel multitasking hybrid tabular-textual question answering (MHTTQA) framework. Instead of generating operators and operands step by step, this framework can independently generate entire program tuples in parallel. This innovative approach solves the problem of error propagation and greatly improves the speed of program generation. The effectiveness of the method is demonstrated through experiments using the ConvFinQA and MultiHiertt datasets. Our proposed model outperforms the strong FinQANet baselines by 7% and 7.2% Exe\/Prog Acc and the MT2Net baselines by 20.9% and 9.4% EM\/F1. In addition, the program generation rate of our method far exceeds that of the baseline method. Additionally, our non-autoregressive program generation method exhibits greater resilience to an increasing number of numerical reasoning steps, further highlighting the advantages of our proposed framework in the field of hybrid tabular-textual QA.<\/jats:p>","DOI":"10.3233\/jifs-234719","type":"journal-article","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T11:06:15Z","timestamp":1700564775000},"page":"1059-1068","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Synthetical reasoning for hybrid tabular-textual question answering over multitasking model"],"prefix":"10.1177","volume":"46","author":[{"given":"Tongzheng","family":"Pu","sequence":"first","affiliation":[{"name":"Yunnan University","place":["China"]}]},{"given":"Chongxing","family":"Huang","sequence":"additional","affiliation":[{"name":"University College London","place":["UK"]}]},{"given":"Yifei","family":"Yang","sequence":"additional","affiliation":[{"name":"The Second Standing Force of National Immigration Administration, Kunming, China"}]},{"given":"Jingjing","family":"Yang","sequence":"additional","affiliation":[{"name":"Yunnan University","place":["China"]}]},{"given":"Ming","family":"Huang","sequence":"additional","affiliation":[{"name":"Yunnan University","place":["China"]}]}],"member":"179","published-online":{"date-parts":[[2023,11,20]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"WangD. DouL. CheW. A Survey on Table-and-Text HybridQA: Concepts Methods Challenges and Future Directions 2022 arXiv preprint arXiv:2212.13465."},{"issue":"3","key":"e_1_3_1_3_2","article-title":"FarsNewsQA: A deep learning-based question answering system for the Persian news articles","volume":"26","author":"Kazemi A.","year":"2023","unstructured":"KazemiA., ZojajiZ., MalverdiM. et al., FarsNewsQA: A deep learning-based question answering system for the Persian news articles, Inf Retrieval J 26(3) (2023).","journal-title":"Inf Retrieval J"},{"key":"e_1_3_1_4_2","first-page":"1","article-title":"Malayalam question answering system using deep learning approaches","author":"Reji Rahmath K.","year":"2022","unstructured":"Reji RahmathK., Reghu RajP.C. and RafeequeP.C., Malayalam question answering system using deep learning approaches, IETE Journal of Research (2022), 1\u201313.","journal-title":"IETE Journal of Research"},{"key":"e_1_3_1_5_2","doi-asserted-by":"crossref","unstructured":"HerzigJ. NowakP.K. M\u00fcllerT. PiccinnoF. EisenschlosJ.M. TaPas: Weakly supervised table parsing via pre-training Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics 2020 pp. 4320\u20134333.","DOI":"10.18653\/v1\/2020.acl-main.398"},{"key":"e_1_3_1_6_2","doi-asserted-by":"crossref","unstructured":"YangJ. GuptaA. UpadhyayS. WuL. GoelR. PaulS. Tableformer: Robust transformer modeling for tabletext encoding Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics Volume 1 2022 pp. 528\u2013537.","DOI":"10.18653\/v1\/2022.acl-long.40"},{"key":"e_1_3_1_7_2","doi-asserted-by":"crossref","unstructured":"ChenW. ZhaH. ChenZ. XiongW. WangH. WangW. Hybridqa:Adataset of multi-hop question answering over tabular and textual data Findings of the Association for Computational Linguistics: EMNLP 2020 pp. 1026\u20131036.","DOI":"10.18653\/v1\/2020.findings-emnlp.91"},{"key":"e_1_3_1_8_2","doi-asserted-by":"crossref","unstructured":"ZhuF. LeiW. HuangY. WangC. ZhangS. LvJ. FengF. ChuaT.S. Tatqa: A question answering benchmark on a hybrid of tabular and textual content in finance Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing Volume 1 2021 pp. 3277\u20133287.","DOI":"10.18653\/v1\/2021.acl-long.254"},{"key":"e_1_3_1_9_2","doi-asserted-by":"crossref","unstructured":"ChenZ. ChenW. SmileyC. ShivamS. IrynaB. DavidL. RamiM. MarkB. HuangT. BraxtonR. WangW. Finqa: A dataset of numerical reasoning over financial data Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing 2021 pp. 3697\u20133708.","DOI":"10.18653\/v1\/2021.emnlp-main.300"},{"key":"e_1_3_1_10_2","doi-asserted-by":"crossref","unstructured":"LiM. FengF. ZhangH. HeX. ZhuF. ChuaT.S. Learning to imagine: Integrating counterfactual thinking in neural discrete reasoning Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics Volume 1 2022 pp. 57\u201369.","DOI":"10.18653\/v1\/2022.acl-long.5"},{"key":"e_1_3_1_11_2","doi-asserted-by":"crossref","unstructured":"ChenZ. LiS. SmileyC. MaZ. ShivamS. WangW. Convfinqa: Exploring the chain of numerical reasoning in conversational finance question answering Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing 2022 pp. 6279\u20136292.","DOI":"10.18653\/v1\/2022.emnlp-main.421"},{"key":"e_1_3_1_12_2","doi-asserted-by":"crossref","unstructured":"ZhaoY. LiY. LiC. ZhangR. Multihiertt: Numerical reasoning over multi hierarchical tabular and textual data Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics Volume 1 2022 pp. 6588\u20136600.","DOI":"10.18653\/v1\/2022.acl-long.454"},{"key":"e_1_3_1_13_2","unstructured":"LiuY. OttM. GoyalN. DuJ. JoshiM. ChenD. LevyO. LewisM. ZettlemoyerL. StoyanovV. Roberta:A robustly optimized bert pretraining approach arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_1_14_2","doi-asserted-by":"crossref","unstructured":"ZhangW. FengY. MengF. YouD. LiuQ. Bridging the gap between training and inference for neural machine translation Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics 2019 pp. 4334\u20134343.","DOI":"10.18653\/v1\/P19-1426"},{"key":"e_1_3_1_15_2","doi-asserted-by":"crossref","unstructured":"ZhangS. HuangH. LiuJ. LiH. Spelling error correction with soft-masked bert Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics 2020 pp. 882\u2013890.","DOI":"10.18653\/v1\/2020.acl-main.82"},{"key":"e_1_3_1_16_2","doi-asserted-by":"crossref","unstructured":"ThawaniA. PujaraJ. IlievskiF. SzekelyP. Representing numbers in nlp: A survey and a vision Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 2021 pp. 644\u2013656.","DOI":"10.18653\/v1\/2021.naacl-main.53"},{"key":"e_1_3_1_17_2","unstructured":"K.P. K. BaralC. Investigating numeracy learning ability of a text-to-text transfer model In: Findings of the Association for Computational Linguistics: EMNLP 2021 2021 pp. 3095\u20133101."},{"key":"e_1_3_1_18_2","doi-asserted-by":"crossref","unstructured":"YuS. et al. PLM-PGHC:Anovel de-biasing framework for robust question answering Journal of Intelligent & Fuzzy Systems (2023) 1\u201312.","DOI":"10.3233\/JIFS-233029"},{"key":"e_1_3_1_19_2","doi-asserted-by":"crossref","unstructured":"ZhangQ. WangL. YuS. WangS. WangY. JiangJ. LimE.P. Noahqa: Numerical reasoning with interpretable graph question answering dataset Findings of the Association for Computational Linguistics (2021) 4147\u20134161.","DOI":"10.18653\/v1\/2021.findings-emnlp.350"},{"key":"e_1_3_1_20_2","doi-asserted-by":"crossref","unstructured":"LiX. SunY. ChengG. Tsqa: Tabular scenario based question answering Proceedings of the AAAI Conference on Artificial Intelligence vol. 35 2021 pp. 13297\u201313305.","DOI":"10.1609\/aaai.v35i15.17570"},{"key":"e_1_3_1_21_2","doi-asserted-by":"crossref","unstructured":"DengY. LeiW. ZhangW. LamW. ChuaT.S. Pacific: Towards proactive conversational question answering over tabular and textual data in finance Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing 2022 pp. 6970\u20136984.","DOI":"10.18653\/v1\/2022.emnlp-main.469"},{"key":"e_1_3_1_22_2","doi-asserted-by":"crossref","unstructured":"GevaM. GuptaA. BerantJ. Injecting numerical reasoning skills into language models Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics 2020 pp. 946\u2013958.","DOI":"10.18653\/v1\/2020.acl-main.89"},{"key":"e_1_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Berg-KirkpatrickT. SpokoynyD. An empirical investigation of contextualized number prediction Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020 pp. 4754\u20134764.","DOI":"10.18653\/v1\/2020.emnlp-main.385"},{"key":"e_1_3_1_24_2","unstructured":"PiX. LiuQ. ChenB. ZiyadiM. LinZ. FuQ. ChenW. Reasoning like program executors arXiv preprint arXiv:2201.11473 (2022)."},{"key":"e_1_3_1_25_2","doi-asserted-by":"crossref","unstructured":"FanC. et al. Span prompt dense passage retrieval for Chinese open domain question answering Journal of Intelligent & Fuzzy Systems (2023) 1\u201311.","DOI":"10.3233\/JIFS-231328"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105426"},{"issue":"8","key":"e_1_3_1_27_2","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford A.","year":"2019","unstructured":"RadfordA., WuJ., ChildR., LuanD., AmodeiD. and SutskeverI., Language models are unsupervised multitask learners, OpenAI Blog 1(8) (2019), 9.","journal-title":"OpenAI Blog"},{"issue":"1","key":"e_1_3_1_28_2","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel C.","year":"2020","unstructured":"RaffelC., ShazeerN., RobertsA., LeeK., NarangS., MatenaM., ZhouY., LiW. and LiuP.J., Exploring the limits of transfer learning with a unified text-to-text transformer, The Journal of Machine Learning Research 21(1) (2020), 5485\u20135551.","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_1_29_2","first-page":"03462","article-title":"Napg: Non-autoregressive program generation for hybrid tabular-textual question answering","volume":"2211","author":"Zhang T.","year":"2022","unstructured":"ZhangT., XuH., van GenabithJ., XiongD. and ZanH., Napg: Non-autoregressive program generation for hybrid tabular-textual question answering, arXiv preprint arXiv 2211 (2022), 03462.","journal-title":"arXiv preprint arXiv"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems: Applications in Engineering and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-234719","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-234719","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-234719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T17:55:05Z","timestamp":1769536505000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-234719"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,20]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1,10]]}},"alternative-id":["10.3233\/JIFS-234719"],"URL":"https:\/\/doi.org\/10.3233\/jifs-234719","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,20]]}}}