{"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/towards-more-realistic-generation-of","title":"Generating Information-Seeking Conversations from Unlabeled Documents","arxiv_id":"2205.12609","date":"2022-05-25","proceeding":null,"authors":["Gangwoo Kim","Sungdong Kim","Kang Min Yoo","Jaewoo Kang"],"abstract":"In this paper, we introduce a novel framework, SIMSEEK, (Simulating information-Seeking conversation from unlabeled documents), and compare its two variants. In our baseline SIMSEEK-SYM, a questioner generates follow-up questions upon the predetermined answer by an answerer. On the contrary, SIMSEEK-ASYM first generates the question and then finds its corresponding answer under the conversational context. Our experiments show that they can synthesize effective training resources for CQA and conversational search tasks. As a result, conversations from SIMSEEK-ASYM not only make more improvements in our experiments but also are favorably reviewed in a human evaluation. We finally release a large-scale resource of synthetic conversations, WIKI-SIMSEEK, containing 2 million CQA pairs built upon Wikipedia documents. With the dataset, our CQA model achieves state-of-the-art performance on a recent CQA benchmark, QuAC.","url_abs":"https://arxiv.org/abs/2205.12609v2","url_pdf":"https://arxiv.org/pdf/2205.12609v2.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":"towards-more-realistic-generation-of","repo_url":"https://github.com/naver-ai/simseek","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"conversational-search","task_name":"Conversational Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2205.12609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.12609"}},"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":"deterministic:regex_extraction","url":"https://github.com/prdwb/orconvqa-release","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/facebookresearch/KILT","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/naverai/simseek","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran_draft_wrong":1,"unverified":11},"by_repo_kind":{"found_in_text":{"samples":12,"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":12,"samples":[{"code_sha256_prefix":"e7e75981cb464788","entry":"normalize_answer","repo":"facebookresearch/KILT","repo_kind":"found_in_text","path":"kilt/eval_downstream.py","file_url":"https://github.com/facebookresearch/KILT/blob/HEAD/kilt/eval_downstream.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"e7e75981cb464788"}},{"code_sha256_prefix":"5818cfb84ff0a3eb","entry":"convert_to_KILT_format","repo":"facebookresearch/KILT","repo_kind":"found_in_text","path":"kilt/datasets/entity_linking.py","file_url":"https://github.com/facebookresearch/KILT/blob/HEAD/kilt/datasets/entity_linking.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":false,"mcp_get_code":{"code_sha256":"5818cfb84ff0a3eb"}},{"code_sha256_prefix":"fb44e7c3365b1055","entry":"generate_output_file","repo":"facebookresearch/KILT","repo_kind":"found_in_text","path":"kilt/retrieval.py","file_url":"https://github.com/facebookresearch/KILT/blob/HEAD/kilt/retrieval.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":false,"mcp_get_code":{"code_sha256":"fb44e7c3365b1055"}},{"code_sha256_prefix":"1822840bf1a15385","entry":"get_gold_answers","repo":"facebookresearch/KILT","repo_kind":"found_in_text","path":"kilt/eval_downstream.py","file_url":"https://github.com/facebookresearch/KILT/blob/HEAD/kilt/eval_downstream.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":false,"mcp_get_code":{"code_sha256":"1822840bf1a15385"}},{"code_sha256_prefix":"e7e608263bcd02c2","entry":"get_gold_titles","repo":"facebookresearch/KILT","repo_kind":"found_in_text","path":"kilt/eval_downstream.py","file_url":"https://github.com/facebookresearch/KILT/blob/HEAD/kilt/eval_downstream.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":false,"mcp_get_code":{"code_sha256":"e7e608263bcd02c2"}},{"code_sha256_prefix":"6a9bcdcb79e942e6","entry":"get_rank","repo":"facebookresearch/KILT","repo_kind":"found_in_text","path":"kilt/eval_retrieval.py","file_url":"https://github.com/facebookresearch/KILT/blob/HEAD/kilt/eval_retrieval.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":false,"mcp_get_code":{"code_sha256":"6a9bcdcb79e942e6"}},{"code_sha256_prefix":"67865292b6695b67","entry":"load_data","repo":"facebookresearch/KILT","repo_kind":"found_in_text","path":"kilt/kilt_utils.py","file_url":"https://github.com/facebookresearch/KILT/blob/HEAD/kilt/kilt_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":false,"mcp_get_code":{"code_sha256":"67865292b6695b67"}},{"code_sha256_prefix":"527517ab30580dfd","entry":"normalize_answer","repo":"facebookresearch/KILT","repo_kind":"found_in_text","path":"kilt/kilt_utils.py","file_url":"https://github.com/facebookresearch/KILT/blob/HEAD/kilt/kilt_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":false,"mcp_get_code":{"code_sha256":"527517ab30580dfd"}},{"code_sha256_prefix":"8127c3fe61cc2993","entry":"rprecision","repo":"facebookresearch/KILT","repo_kind":"found_in_text","path":"kilt/eval_retrieval.py","file_url":"https://github.com/facebookresearch/KILT/blob/HEAD/kilt/eval_retrieval.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":false,"mcp_get_code":{"code_sha256":"8127c3fe61cc2993"}},{"code_sha256_prefix":"1a66d75f4a44d89f","entry":"run_thread","repo":"facebookresearch/KILT","repo_kind":"found_in_text","path":"kilt/dataset_mapper.py","file_url":"https://github.com/facebookresearch/KILT/blob/HEAD/kilt/dataset_mapper.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":false,"mcp_get_code":{"code_sha256":"1a66d75f4a44d89f"}},{"code_sha256_prefix":"6b32309ff7cc3ada","entry":"run_thread","repo":"facebookresearch/KILT","repo_kind":"found_in_text","path":"kilt/datasets/hotpotqa_ks.py","file_url":"https://github.com/facebookresearch/KILT/blob/HEAD/kilt/datasets/hotpotqa_ks.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":false,"mcp_get_code":{"code_sha256":"6b32309ff7cc3ada"}},{"code_sha256_prefix":"c55902d3b0300f91","entry":"validate_datapoint","repo":"facebookresearch/KILT","repo_kind":"found_in_text","path":"kilt/kilt_utils.py","file_url":"https://github.com/facebookresearch/KILT/blob/HEAD/kilt/kilt_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":false,"mcp_get_code":{"code_sha256":"c55902d3b0300f91"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}