{"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/ask-what-s-missing-and-what-s-useful","title":"Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge","arxiv_id":"2104.06828","date":"2021-04-14","proceeding":"NAACL 2021 4","authors":["Bodhisattwa Prasad Majumder","Sudha Rao","Michel Galley","Julian McAuley"],"abstract":"The ability to generate clarification questions i.e., questions that identify useful missing information in a given context, is important in reducing ambiguity. Humans use previous experience with similar contexts to form a global view and compare it to the given context to ascertain what is missing and what is useful in the context. Inspired by this, we propose a model for clarification question generation where we first identify what is missing by taking a difference between the global and the local view and then train a model to identify what is useful and generate a question about it. Our model outperforms several baselines as judged by both automatic metrics and humans.","url_abs":"https://arxiv.org/abs/2104.06828v1","url_pdf":"https://arxiv.org/pdf/2104.06828v1.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":"ask-what-s-missing-and-what-s-useful","repo_url":"https://github.com/microsoft/clarification-qgen-globalinfo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"question-generation","task_name":"Question Generation"},{"task_slug":"question-generation","task_name":"Question-Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.06828","atlas_url":"https://app.syntology.ai/?focus=2104.06828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06828"}},"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/microsoft/clarification-qgen-globalinfo","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":14},"by_repo_kind":{"official":{"samples":14,"ran":0,"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":"1922d68fd519cffa","entry":"build_schema","repo":"microsoft/clarification-qgen-globalinfo","repo_kind":"official","path":"amazon/get_schema.py","file_url":"https://github.com/microsoft/clarification-qgen-globalinfo/blob/HEAD/amazon/get_schema.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":"1922d68fd519cffa"}},{"code_sha256_prefix":"305f91dc9ae7c818","entry":"build_schema_from_desc","repo":"microsoft/clarification-qgen-globalinfo","repo_kind":"official","path":"amazon/get_schema.py","file_url":"https://github.com/microsoft/clarification-qgen-globalinfo/blob/HEAD/amazon/get_schema.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":"305f91dc9ae7c818"}},{"code_sha256_prefix":"6ded62d9787204e8","entry":"build_schema_from_table","repo":"microsoft/clarification-qgen-globalinfo","repo_kind":"official","path":"amazon/get_schema.py","file_url":"https://github.com/microsoft/clarification-qgen-globalinfo/blob/HEAD/amazon/get_schema.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":"6ded62d9787204e8"}},{"code_sha256_prefix":"50991f7e06d740d2","entry":"clean_html","repo":"microsoft/clarification-qgen-globalinfo","repo_kind":"official","path":"amazon/baselines/create_seq2seq_data.py","file_url":"https://github.com/microsoft/clarification-qgen-globalinfo/blob/HEAD/amazon/baselines/create_seq2seq_data.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":"50991f7e06d740d2"}},{"code_sha256_prefix":"ceae444d11bd25e4","entry":"clf_predict","repo":"microsoft/clarification-qgen-globalinfo","repo_kind":"official","path":"amazon/predict_usefulness_score.py","file_url":"https://github.com/microsoft/clarification-qgen-globalinfo/blob/HEAD/amazon/predict_usefulness_score.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":"ceae444d11bd25e4"}},{"code_sha256_prefix":"8fa821a1e0e2be65","entry":"create_keyword_embs","repo":"microsoft/clarification-qgen-globalinfo","repo_kind":"official","path":"amazon/global_schema_utils.py","file_url":"https://github.com/microsoft/clarification-qgen-globalinfo/blob/HEAD/amazon/global_schema_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":"8fa821a1e0e2be65"}},{"code_sha256_prefix":"1840a84c3d80a3fa","entry":"feedfoward_regr_model","repo":"microsoft/clarification-qgen-globalinfo","repo_kind":"official","path":"amazon/question_ranker.py","file_url":"https://github.com/microsoft/clarification-qgen-globalinfo/blob/HEAD/amazon/question_ranker.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":"1840a84c3d80a3fa"}},{"code_sha256_prefix":"ccc731d1ce007e01","entry":"getDF","repo":"microsoft/clarification-qgen-globalinfo","repo_kind":"official","path":"amazon/create_split.py","file_url":"https://github.com/microsoft/clarification-qgen-globalinfo/blob/HEAD/amazon/create_split.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":"ccc731d1ce007e01"}},{"code_sha256_prefix":"82bd4d8fb1a2c5b5","entry":"get_glove_vector","repo":"microsoft/clarification-qgen-globalinfo","repo_kind":"official","path":"amazon/predict_usefulness_score.py","file_url":"https://github.com/microsoft/clarification-qgen-globalinfo/blob/HEAD/amazon/predict_usefulness_score.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":"82bd4d8fb1a2c5b5"}},{"code_sha256_prefix":"139874e879dde9b0","entry":"get_glove_vector","repo":"microsoft/clarification-qgen-globalinfo","repo_kind":"official","path":"amazon/global_schema_utils.py","file_url":"https://github.com/microsoft/clarification-qgen-globalinfo/blob/HEAD/amazon/global_schema_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":"139874e879dde9b0"}},{"code_sha256_prefix":"a38422b38b0a22c7","entry":"load_glove_vectors","repo":"microsoft/clarification-qgen-globalinfo","repo_kind":"official","path":"amazon/global_schema_utils.py","file_url":"https://github.com/microsoft/clarification-qgen-globalinfo/blob/HEAD/amazon/global_schema_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":"a38422b38b0a22c7"}},{"code_sha256_prefix":"78054b6fc43b80d3","entry":"svc_model","repo":"microsoft/clarification-qgen-globalinfo","repo_kind":"official","path":"amazon/question_ranker.py","file_url":"https://github.com/microsoft/clarification-qgen-globalinfo/blob/HEAD/amazon/question_ranker.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":"78054b6fc43b80d3"}},{"code_sha256_prefix":"0091bc81c2e128ca","entry":"svc_model_predict","repo":"microsoft/clarification-qgen-globalinfo","repo_kind":"official","path":"amazon/predict_usefulness_score.py","file_url":"https://github.com/microsoft/clarification-qgen-globalinfo/blob/HEAD/amazon/predict_usefulness_score.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":"0091bc81c2e128ca"}},{"code_sha256_prefix":"bb028603164d4abd","entry":"svr_model","repo":"microsoft/clarification-qgen-globalinfo","repo_kind":"official","path":"amazon/question_ranker.py","file_url":"https://github.com/microsoft/clarification-qgen-globalinfo/blob/HEAD/amazon/question_ranker.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":"bb028603164d4abd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}