{"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/template-based-question-generation-from","title":"Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering","arxiv_id":"2004.11892","date":"2020-04-24","proceeding":"ACL 2020 6","authors":["Alexander R. Fabbri","Patrick Ng","Zhiguo Wang","Ramesh Nallapati","Bing Xiang"],"abstract":"Question Answering (QA) is in increasing demand as the amount of information available online and the desire for quick access to this content grows. A common approach to QA has been to fine-tune a pretrained language model on a task-specific labeled dataset. This paradigm, however, relies on scarce, and costly to obtain, large-scale human-labeled data. We propose an unsupervised approach to training QA models with generated pseudo-training data. We show that generating questions for QA training by applying a simple template on a related, retrieved sentence rather than the original context sentence improves downstream QA performance by allowing the model to learn more complex context-question relationships. Training a QA model on this data gives a relative improvement over a previous unsupervised model in F1 score on the SQuAD dataset by about 14%, and 20% when the answer is a named entity, achieving state-of-the-art performance on SQuAD for unsupervised QA.","url_abs":"https://arxiv.org/abs/2004.11892v1","url_pdf":"https://arxiv.org/pdf/2004.11892v1.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":"template-based-question-generation-from","repo_url":"https://github.com/awslabs/unsupervised-qa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"question-generation","task_name":"Question Generation"},{"task_slug":"question-generation","task_name":"Question-Generation"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.11892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.11892"}},"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/awslabs/unsupervised-qa","reach":null}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"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":"20db2098dee11bfd","entry":"QuestionGenerator","repo":"awslabs/unsupervised-qa","repo_kind":"official","path":"distant_supervision/question_generator.py","file_url":"https://github.com/awslabs/unsupervised-qa/blob/HEAD/distant_supervision/question_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20db2098dee11bfd"}},{"code_sha256_prefix":"f2b2036212c8c959","entry":"QuestionGeneratorError","repo":"awslabs/unsupervised-qa","repo_kind":"official","path":"distant_supervision/question_generator.py","file_url":"https://github.com/awslabs/unsupervised-qa/blob/HEAD/distant_supervision/question_generator.py","link_basis":"first_harvest_node","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":"f2b2036212c8c959"}},{"code_sha256_prefix":"eb76e9e3b3f42d34","entry":"QuestionStyle","repo":"awslabs/unsupervised-qa","repo_kind":"official","path":"distant_supervision/question_generator.py","file_url":"https://github.com/awslabs/unsupervised-qa/blob/HEAD/distant_supervision/question_generator.py","link_basis":"first_harvest_node","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":"eb76e9e3b3f42d34"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}