{"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/generating-diverse-and-consistent-qa-pairs","title":"Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs","arxiv_id":"2005.13837","date":"2020-05-28","proceeding":"ACL 2020 6","authors":["Dong Bok Lee","Seanie Lee","Woo Tae Jeong","Donghwan Kim","Sung Ju Hwang"],"abstract":"One of the most crucial challenges in question answering (QA) is the scarcity of labeled data, since it is costly to obtain question-answer (QA) pairs for a target text domain with human annotation. An alternative approach to tackle the problem is to use automatically generated QA pairs from either the problem context or from large amount of unstructured texts (e.g. Wikipedia). In this work, we propose a hierarchical conditional variational autoencoder (HCVAE) for generating QA pairs given unstructured texts as contexts, while maximizing the mutual information between generated QA pairs to ensure their consistency. We validate our Information Maximizing Hierarchical Conditional Variational AutoEncoder (Info-HCVAE) on several benchmark datasets by evaluating the performance of the QA model (BERT-base) using only the generated QA pairs (QA-based evaluation) or by using both the generated and human-labeled pairs (semi-supervised learning) for training, against state-of-the-art baseline models. The results show that our model obtains impressive performance gains over all baselines on both tasks, using only a fraction of data for training.","url_abs":"https://arxiv.org/abs/2005.13837v5","url_pdf":"https://arxiv.org/pdf/2005.13837v5.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":"generating-diverse-and-consistent-qa-pairs","repo_url":"https://github.com/seanie12/Info-HCVAE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"question-generation","task_name":"Question Generation"},{"task_slug":"question-answer-generation","task_name":"Question-Answer-Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-generation-on-natural-questions","task":"Question Generation","dataset":"Natural Questions","model":"Info-HCVAE","rank_in_archive_order":1,"of":2,"metrics":{"QAE":"37.18","R-QAE":"29.39"},"uses_additional_data":false},{"leaderboard":"/sota/question-generation-on-natural-questions","task":"Question Generation","dataset":"Natural Questions","model":"HCVAE","rank_in_archive_order":2,"of":2,"metrics":{"QAE":"31.45","R-QAE":"32.78"},"uses_additional_data":false},{"leaderboard":"/sota/question-generation-on-squad","task":"Question Generation","dataset":"SQuAD","model":"Info-HCVAE","rank_in_archive_order":1,"of":2,"metrics":{"QAE":"71.18","R-QAE":"38.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-generation-on-squad","task":"Question Generation","dataset":"SQuAD","model":"HCVAE","rank_in_archive_order":2,"of":2,"metrics":{"QAE":"69.46","R-QAE":"37.57"},"uses_additional_data":false},{"leaderboard":"/sota/question-generation-on-triviaqa","task":"Question Generation","dataset":"TriviaQA","model":"Info-HCVAE","rank_in_archive_order":1,"of":2,"metrics":{"QAE":"35.45","R-QAE":"21.65"},"uses_additional_data":false},{"leaderboard":"/sota/question-generation-on-triviaqa","task":"Question Generation","dataset":"TriviaQA","model":"HCVAE","rank_in_archive_order":2,"of":2,"metrics":{"QAE":"30.2","R-QAE":"34.41"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.13837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.13837"}},"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/seanie12/Info-HCVAE","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":16},"by_repo_kind":{"official":{"samples":16,"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":"7cef89edf29127bc","entry":"batch_to_device","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"vae/utils.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/vae/utils.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":"7cef89edf29127bc"}},{"code_sha256_prefix":"1f734017a6f68175","entry":"cal_attn","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"vae/models.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/vae/models.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":"1f734017a6f68175"}},{"code_sha256_prefix":"72c5000d831f12e0","entry":"convert_examples_to_features","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"qa-eval/squad_utils.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/qa-eval/squad_utils.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":"72c5000d831f12e0"}},{"code_sha256_prefix":"1e2aae97388cfe6e","entry":"convert_examples_to_features_answer_id","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"qa-eval/squad_utils.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/qa-eval/squad_utils.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":"1e2aae97388cfe6e"}},{"code_sha256_prefix":"4481bd2f1ff50f5b","entry":"convert_examples_to_harv_features","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"qa-eval/squad_utils.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/qa-eval/squad_utils.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":"4481bd2f1ff50f5b"}},{"code_sha256_prefix":"5172aba957a32d9e","entry":"cook_refs","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"vae/qgevalcap/cider/cider_scorer.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/vae/qgevalcap/cider/cider_scorer.py","link_basis":"plan_row","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":"5172aba957a32d9e"}},{"code_sha256_prefix":"90a4bcbf05586ff3","entry":"cook_test","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"vae/qgevalcap/cider/cider_scorer.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/vae/qgevalcap/cider/cider_scorer.py","link_basis":"plan_row","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":"90a4bcbf05586ff3"}},{"code_sha256_prefix":"a3c458ae06a14711","entry":"get_linear_schedule_with_warmup","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"qa-eval/trainer.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/qa-eval/trainer.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":"a3c458ae06a14711"}},{"code_sha256_prefix":"7b8c9c000eba3141","entry":"gumbel_softmax","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"vae/models.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/vae/models.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":"7b8c9c000eba3141"}},{"code_sha256_prefix":"845c524066f993b4","entry":"post_process","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"vae/translate.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/vae/translate.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":"845c524066f993b4"}},{"code_sha256_prefix":"422c41f5b22cf9c3","entry":"precook","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"vae/qgevalcap/cider/cider_scorer.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/vae/qgevalcap/cider/cider_scorer.py","link_basis":"plan_row","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":"422c41f5b22cf9c3"}},{"code_sha256_prefix":"58fb608bcfbbdffe","entry":"progress_bar","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"qa-eval/utils.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/qa-eval/utils.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":"58fb608bcfbbdffe"}},{"code_sha256_prefix":"b058372cf5b99e2b","entry":"return_mask_lengths","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"vae/models.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/vae/models.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":"b058372cf5b99e2b"}},{"code_sha256_prefix":"c058fcfe8ca35ccf","entry":"return_mask_lengths","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"vae/translate.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/vae/translate.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":"c058fcfe8ca35ccf"}},{"code_sha256_prefix":"3d69d712283cfd10","entry":"time_since","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"qa-eval/utils.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/qa-eval/utils.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":"3d69d712283cfd10"}},{"code_sha256_prefix":"0a7669f48a1dc3a1","entry":"user_friendly_time","repo":"seanie12/Info-HCVAE","repo_kind":"official","path":"qa-eval/utils.py","file_url":"https://github.com/seanie12/Info-HCVAE/blob/HEAD/qa-eval/utils.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":"0a7669f48a1dc3a1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}