{"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/the-techqa-dataset","title":"The TechQA Dataset","arxiv_id":"1911.02984","date":"2019-11-08","proceeding":"ACL 2020 6","authors":["Vittorio Castelli","Rishav Chakravarti","Saswati Dana","Anthony Ferritto","Radu Florian","Martin Franz","Dinesh Garg","Dinesh Khandelwal","Scott McCarley","Mike McCawley","Mohamed Nasr","Lin Pan","Cezar Pendus","John Pitrelli","Saurabh Pujar","Salim Roukos","Andrzej Sakrajda","Avirup Sil","Rosario Uceda-Sosa","Todd Ward","Rong Zhang"],"abstract":"We introduce TechQA, a domain-adaptation question answering dataset for the technical support domain. The TechQA corpus highlights two real-world issues from the automated customer support domain. First, it contains actual questions posed by users on a technical forum, rather than questions generated specifically for a competition or a task. Second, it has a real-world size -- 600 training, 310 dev, and 490 evaluation question/answer pairs -- thus reflecting the cost of creating large labeled datasets with actual data. Consequently, TechQA is meant to stimulate research in domain adaptation rather than being a resource to build QA systems from scratch. The dataset was obtained by crawling the IBM Developer and IBM DeveloperWorks forums for questions with accepted answers that appear in a published IBM Technote---a technical document that addresses a specific technical issue. We also release a collection of the 801,998 publicly available Technotes as of April 4, 2019 as a companion resource that might be used for pretraining, to learn representations of the IT domain language.","url_abs":"https://arxiv.org/abs/1911.02984v1","url_pdf":"https://arxiv.org/pdf/1911.02984v1.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":"the-techqa-dataset","repo_url":"https://github.com/ibm/techqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"the-techqa-dataset","repo_url":"https://github.com/yeonsw/vkgdr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[{"slug":"techqa","name":"TechQA","full_name":"The TechQA Dataset"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.02984","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02984"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/yeonsw/vkgdr","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ibm/techqa","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":8},"by_repo_kind":{"listed":{"samples":9,"ran":1,"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":"9df40357afea56cc","entry":"to_list","repo":"ibm/techqa","repo_kind":"listed","path":"techqa_metrics.py","file_url":"https://github.com/ibm/techqa/blob/HEAD/techqa_metrics.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9df40357afea56cc"}},{"code_sha256_prefix":"192f44f7e75dcf94","entry":"compute_f1","repo":"ibm/techqa","repo_kind":"listed","path":"techqa_evaluation.py","file_url":"https://github.com/ibm/techqa/blob/HEAD/techqa_evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"192f44f7e75dcf94"}},{"code_sha256_prefix":"8c33500c4337c1c3","entry":"compute_score_diff_between_span_and_cls","repo":"ibm/techqa","repo_kind":"listed","path":"techqa_metrics.py","file_url":"https://github.com/ibm/techqa/blob/HEAD/techqa_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8c33500c4337c1c3"}},{"code_sha256_prefix":"829b312ef0709a1f","entry":"create_features","repo":"ibm/techqa","repo_kind":"listed","path":"techqa_processor.py","file_url":"https://github.com/ibm/techqa/blob/HEAD/techqa_processor.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"829b312ef0709a1f"}},{"code_sha256_prefix":"8e92c38c62033416","entry":"generate_features_for_example","repo":"ibm/techqa","repo_kind":"listed","path":"techqa_processor.py","file_url":"https://github.com/ibm/techqa/blob/HEAD/techqa_processor.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8e92c38c62033416"}},{"code_sha256_prefix":"c26684b657a9e826","entry":"get_best_indexes","repo":"ibm/techqa","repo_kind":"listed","path":"techqa_metrics.py","file_url":"https://github.com/ibm/techqa/blob/HEAD/techqa_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c26684b657a9e826"}},{"code_sha256_prefix":"524130350eb026cf","entry":"get_raw_scores","repo":"ibm/techqa","repo_kind":"listed","path":"techqa_evaluation.py","file_url":"https://github.com/ibm/techqa/blob/HEAD/techqa_evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"524130350eb026cf"}},{"code_sha256_prefix":"64f34f8784ad0dbd","entry":"load_and_cache_examples","repo":"ibm/techqa","repo_kind":"listed","path":"techqa_processor.py","file_url":"https://github.com/ibm/techqa/blob/HEAD/techqa_processor.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"64f34f8784ad0dbd"}},{"code_sha256_prefix":"b63023126d0278b8","entry":"make_qid_to_has_ans","repo":"ibm/techqa","repo_kind":"listed","path":"techqa_evaluation.py","file_url":"https://github.com/ibm/techqa/blob/HEAD/techqa_evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b63023126d0278b8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}