{"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/caire-in-dialdoc21-data-augmentation-for","title":"CAiRE in DialDoc21: Data Augmentation for Information-Seeking Dialogue System","arxiv_id":"2106.03530","date":"2021-06-07","proceeding":null,"authors":["Etsuko Ishii","Yan Xu","Genta Indra Winata","Zhaojiang Lin","Andrea Madotto","Zihan Liu","Peng Xu","Pascale Fung"],"abstract":"Information-seeking dialogue systems, including knowledge identification and response generation, aim to respond to users with fluent, coherent, and informative responses based on users' needs, which. To tackle this challenge, we utilize data augmentation methods and several training techniques with the pre-trained language models to learn a general pattern of the task and thus achieve promising performance. In DialDoc21 competition, our system achieved 74.95 F1 score and 60.74 Exact Match score in subtask 1, and 37.72 SacreBLEU score in subtask 2. Empirical analysis is provided to explain the effectiveness of our approaches.","url_abs":"https://arxiv.org/abs/2106.03530v2","url_pdf":"https://arxiv.org/pdf/2106.03530v2.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":"caire-in-dialdoc21-data-augmentation-for","repo_url":"https://github.com/HLTCHKUST/CAiRE_in_DialDoc21","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"response-generation","task_name":"Response Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.03530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03530"}},"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/HLTCHKUST/CAiRE_in_DialDoc21","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"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":"e2ad8489a367a513","entry":"btag","repo":"HLTCHKUST/CAiRE_in_DialDoc21","repo_kind":"official","path":"task2/seq2seq_utils.py","file_url":"https://github.com/HLTCHKUST/CAiRE_in_DialDoc21/blob/HEAD/task2/seq2seq_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":"e2ad8489a367a513"}},{"code_sha256_prefix":"df675544dd207659","entry":"filter_save","repo":"HLTCHKUST/CAiRE_in_DialDoc21","repo_kind":"official","path":"task1/postprocess_prediction.py","file_url":"https://github.com/HLTCHKUST/CAiRE_in_DialDoc21/blob/HEAD/task1/postprocess_prediction.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":"df675544dd207659"}},{"code_sha256_prefix":"4cc91bb2f3ff1629","entry":"getDataLoader","repo":"HLTCHKUST/CAiRE_in_DialDoc21","repo_kind":"official","path":"task2/wow_reader.py","file_url":"https://github.com/HLTCHKUST/CAiRE_in_DialDoc21/blob/HEAD/task2/wow_reader.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":"4cc91bb2f3ff1629"}},{"code_sha256_prefix":"0e48d1e095a13e53","entry":"get_data_from_batch","repo":"HLTCHKUST/CAiRE_in_DialDoc21","repo_kind":"official","path":"task2/wow_reader.py","file_url":"https://github.com/HLTCHKUST/CAiRE_in_DialDoc21/blob/HEAD/task2/wow_reader.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":"0e48d1e095a13e53"}},{"code_sha256_prefix":"65190e80584fade5","entry":"insert_missing_spans","repo":"HLTCHKUST/CAiRE_in_DialDoc21","repo_kind":"official","path":"task1/postprocess_prediction.py","file_url":"https://github.com/HLTCHKUST/CAiRE_in_DialDoc21/blob/HEAD/task1/postprocess_prediction.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":"65190e80584fade5"}},{"code_sha256_prefix":"0ce9a974b3175422","entry":"postprocess_qa_predictions","repo":"HLTCHKUST/CAiRE_in_DialDoc21","repo_kind":"official","path":"task1/utils_qa.py","file_url":"https://github.com/HLTCHKUST/CAiRE_in_DialDoc21/blob/HEAD/task1/utils_qa.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":"0ce9a974b3175422"}},{"code_sha256_prefix":"a2b329a6b17f8924","entry":"postprocess_qa_predictions_with_beam_search","repo":"HLTCHKUST/CAiRE_in_DialDoc21","repo_kind":"official","path":"task1/utils_qa.py","file_url":"https://github.com/HLTCHKUST/CAiRE_in_DialDoc21/blob/HEAD/task1/utils_qa.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":"a2b329a6b17f8924"}},{"code_sha256_prefix":"02f3fb4bf22031fa","entry":"prepare_doc_info_from_doc_datasets","repo":"HLTCHKUST/CAiRE_in_DialDoc21","repo_kind":"official","path":"task1/postprocess_prediction.py","file_url":"https://github.com/HLTCHKUST/CAiRE_in_DialDoc21/blob/HEAD/task1/postprocess_prediction.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":"02f3fb4bf22031fa"}},{"code_sha256_prefix":"80f9ffaa5f9b37c2","entry":"text2line","repo":"HLTCHKUST/CAiRE_in_DialDoc21","repo_kind":"official","path":"task2/seq2seq_utils.py","file_url":"https://github.com/HLTCHKUST/CAiRE_in_DialDoc21/blob/HEAD/task2/seq2seq_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":"80f9ffaa5f9b37c2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}