{"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/open-question-answering-over-tables-and-text-1","title":"Open Question Answering over Tables and Text","arxiv_id":"2010.10439","date":"2020-10-20","proceeding":"ICLR 2021 1","authors":["Wenhu Chen","Ming-Wei Chang","Eva Schlinger","William Wang","William W. Cohen"],"abstract":"In open question answering (QA), the answer to a question is produced by retrieving and then analyzing documents that might contain answers to the question. Most open QA systems have considered only retrieving information from unstructured text. Here we consider for the first time open QA over both tabular and textual data and present a new large-scale dataset Open Table-and-Text Question Answering (OTT-QA) to evaluate performance on this task. Most questions in OTT-QA require multi-hop inference across tabular data and unstructured text, and the evidence required to answer a question can be distributed in different ways over these two types of input, making evidence retrieval challenging -- our baseline model using an iterative retriever and BERT-based reader achieves an exact match score less than 10%. We then propose two novel techniques to address the challenge of retrieving and aggregating evidence for OTT-QA. The first technique is to use \"early fusion\" to group multiple highly relevant tabular and textual units into a fused block, which provides more context for the retriever to search for. The second technique is to use a cross-block reader to model the cross-dependency between multiple retrieved evidence with global-local sparse attention. Combining these two techniques improves the score significantly, to above 27%.","url_abs":"https://arxiv.org/abs/2010.10439v2","url_pdf":"https://arxiv.org/pdf/2010.10439v2.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":"open-question-answering-over-tables-and-text-1","repo_url":"https://github.com/wenhuchen/OTT-QA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"open-question","task_name":"Open-Ended Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[{"slug":"ott-qa","name":"OTT-QA","full_name":null}],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-ott-qa","task":"Question Answering","dataset":"OTT-QA","model":"Fusion Retriever+ETC","rank_in_archive_order":1,"of":3,"metrics":{"ANS-EM":"27.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.10439","atlas_url":"https://app.syntology.ai/?focus=2010.10439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.10439"}},"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/wenhuchen/OTT-QA","reach":null}],"summary":{"ran_draft_wrong":3,"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"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":3,"samples":[{"code_sha256_prefix":"badaaa9e1524f612","entry":"get_contents","repo":"wenhuchen/OTT-QA","repo_kind":"official","path":"retriever/build_tfidf.py","file_url":"https://github.com/wenhuchen/OTT-QA/blob/HEAD/retriever/build_tfidf.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"badaaa9e1524f612"}},{"code_sha256_prefix":"fa92eeafd62c6e49","entry":"import_module","repo":"wenhuchen/OTT-QA","repo_kind":"official","path":"retriever/build_tfidf.py","file_url":"https://github.com/wenhuchen/OTT-QA/blob/HEAD/retriever/build_tfidf.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fa92eeafd62c6e49"}},{"code_sha256_prefix":"86df5eac4985fe0e","entry":"isNaN","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"86df5eac4985fe0e"}},{"code_sha256_prefix":"38c3f4fa8e089762","entry":"url2text","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"38c3f4fa8e089762"}},{"code_sha256_prefix":"33c6fb2a636e2a0b","entry":"fetch_text","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"33c6fb2a636e2a0b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}