{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/tat-qa-a-question-answering-benchmark-on-a","title":"TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance","arxiv_id":"2105.07624","date":"2021-05-17","proceeding":"ACL 2021 5","authors":["Fengbin Zhu","Wenqiang Lei","Youcheng Huang","Chao Wang","Shuo Zhang","Jiancheng Lv","Fuli Feng","Tat-Seng Chua"],"abstract":"Hybrid data combining both tabular and textual content (e.g., financial reports) are quite pervasive in the real world. However, Question Answering (QA) over such hybrid data is largely neglected in existing research. In this work, we extract samples from real financial reports to build a new large-scale QA dataset containing both Tabular And Textual data, named TAT-QA, where numerical reasoning is usually required to infer the answer, such as addition, subtraction, multiplication, division, counting, comparison/sorting, and the compositions. We further propose a novel QA model termed TAGOP, which is capable of reasoning over both tables and text. It adopts sequence tagging to extract relevant cells from the table along with relevant spans from the text to infer their semantics, and then applies symbolic reasoning over them with a set of aggregation operators to arrive at the final answer. TAGOPachieves 58.0% inF1, which is an 11.1% absolute increase over the previous best baseline model, according to our experiments on TAT-QA. But this result still lags far behind performance of expert human, i.e.90.8% in F1. It is demonstrated that our TAT-QA is very challenging and can serve as a benchmark for training and testing powerful QA models that address hybrid form data.","url_abs":"https://arxiv.org/abs/2105.07624v2","url_pdf":"https://arxiv.org/pdf/2105.07624v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tat-qa-a-question-answering-benchmark-on-a","repo_url":"https://github.com/NExTplusplus/TAT-QA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[{"slug":"tat-qa","name":"TAT-QA","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-tat-qa","task":"Question Answering","dataset":"TAT-QA","model":"TagOp","rank_in_archive_order":1,"of":1,"metrics":{"Exact Match (EM)":"50.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.07624","atlas_url":"https://app.syntology.ai/?focus=2105.07624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.07624"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NExTplusplus/TAT-QA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"unverified":10},"by_repo_kind":{"official":{"samples":12,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"e7d542062316094a","entry":"warmup_constant","repo":"NExTplusplus/TAT-QA","repo_kind":"official","path":"tag_op/tagop/optimizer.py","file_url":"https://github.com/NExTplusplus/TAT-QA/blob/HEAD/tag_op/tagop/optimizer.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7d542062316094a"}},{"code_sha256_prefix":"c58d57224530d17e","entry":"warmup_linear","repo":"NExTplusplus/TAT-QA","repo_kind":"official","path":"tag_op/tagop/optimizer.py","file_url":"https://github.com/NExTplusplus/TAT-QA/blob/HEAD/tag_op/tagop/optimizer.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c58d57224530d17e"}},{"code_sha256_prefix":"ea74b65463265ba2","entry":"create_logger","repo":"NExTplusplus/TAT-QA","repo_kind":"official","path":"tag_op/tagop/util.py","file_url":"https://github.com/NExTplusplus/TAT-QA/blob/HEAD/tag_op/tagop/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea74b65463265ba2"}},{"code_sha256_prefix":"2be876d386453689","entry":"extract_gold_answers","repo":"NExTplusplus/TAT-QA","repo_kind":"official","path":"tatqa_metric.py","file_url":"https://github.com/NExTplusplus/TAT-QA/blob/HEAD/tatqa_metric.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2be876d386453689"}},{"code_sha256_prefix":"b591a51b9d4dd3bb","entry":"extract_one_num_from_str","repo":"NExTplusplus/TAT-QA","repo_kind":"official","path":"tatqa_utils.py","file_url":"https://github.com/NExTplusplus/TAT-QA/blob/HEAD/tatqa_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b591a51b9d4dd3bb"}},{"code_sha256_prefix":"f39958953701ff98","entry":"get_continuous_tag_slots","repo":"NExTplusplus/TAT-QA","repo_kind":"official","path":"tag_op/tagop/modeling_tagop.py","file_url":"https://github.com/NExTplusplus/TAT-QA/blob/HEAD/tag_op/tagop/modeling_tagop.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f39958953701ff98"}},{"code_sha256_prefix":"43ec29e1df123bda","entry":"get_span_tokens_from_paragraph","repo":"NExTplusplus/TAT-QA","repo_kind":"official","path":"tag_op/tagop/modeling_tagop.py","file_url":"https://github.com/NExTplusplus/TAT-QA/blob/HEAD/tag_op/tagop/modeling_tagop.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"43ec29e1df123bda"}},{"code_sha256_prefix":"275419aee12c926d","entry":"get_span_tokens_from_table","repo":"NExTplusplus/TAT-QA","repo_kind":"official","path":"tag_op/tagop/modeling_tagop.py","file_url":"https://github.com/NExTplusplus/TAT-QA/blob/HEAD/tag_op/tagop/modeling_tagop.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"275419aee12c926d"}},{"code_sha256_prefix":"1a0411f2ec690e26","entry":"is_number","repo":"NExTplusplus/TAT-QA","repo_kind":"official","path":"tatqa_utils.py","file_url":"https://github.com/NExTplusplus/TAT-QA/blob/HEAD/tatqa_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a0411f2ec690e26"}},{"code_sha256_prefix":"03692148eacb9928","entry":"metric_max_over_ground_truths","repo":"NExTplusplus/TAT-QA","repo_kind":"official","path":"tatqa_metric.py","file_url":"https://github.com/NExTplusplus/TAT-QA/blob/HEAD/tatqa_metric.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"03692148eacb9928"}},{"code_sha256_prefix":"71b0d5b420628a19","entry":"scale_to_num","repo":"NExTplusplus/TAT-QA","repo_kind":"official","path":"tatqa_utils.py","file_url":"https://github.com/NExTplusplus/TAT-QA/blob/HEAD/tatqa_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"71b0d5b420628a19"}},{"code_sha256_prefix":"35f7cddf90dd05d4","entry":"warmup_cosine","repo":"NExTplusplus/TAT-QA","repo_kind":"official","path":"tag_op/tagop/optimizer.py","file_url":"https://github.com/NExTplusplus/TAT-QA/blob/HEAD/tag_op/tagop/optimizer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"35f7cddf90dd05d4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}