{"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/addressing-semantic-drift-in-question","title":"Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering","arxiv_id":"1909.06356","date":"2019-09-13","proceeding":"IJCNLP 2019 11","authors":["Shiyue Zhang","Mohit Bansal"],"abstract":"Text-based Question Generation (QG) aims at generating natural and relevant questions that can be answered by a given answer in some context. Existing QG models suffer from a \"semantic drift\" problem, i.e., the semantics of the model-generated question drifts away from the given context and answer. In this paper, we first propose two semantics-enhanced rewards obtained from downstream question paraphrasing and question answering tasks to regularize the QG model to generate semantically valid questions. Second, since the traditional evaluation metrics (e.g., BLEU) often fall short in evaluating the quality of generated questions, we propose a QA-based evaluation method which measures the QG model's ability to mimic human annotators in generating QA training data. Experiments show that our method achieves the new state-of-the-art performance w.r.t. traditional metrics, and also performs best on our QA-based evaluation metrics. Further, we investigate how to use our QG model to augment QA datasets and enable semi-supervised QA. We propose two ways to generate synthetic QA pairs: generate new questions from existing articles or collect QA pairs from new articles. We also propose two empirically effective strategies, a data filter and mixing mini-batch training, to properly use the QG-generated data for QA. Experiments show that our method improves over both BiDAF and BERT QA baselines, even without introducing new articles.","url_abs":"https://arxiv.org/abs/1909.06356v1","url_pdf":"https://arxiv.org/pdf/1909.06356v1.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":"addressing-semantic-drift-in-question","repo_url":"https://github.com/ZhangShiyue/QGforQA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"addressing-semantic-drift-in-question","repo_url":"https://github.com/CLUEbenchmark/LGEB","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"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":null,"task_name":"valid"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.06356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.06356"}},"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/CLUEbenchmark/LGEB","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZhangShiyue/QGforQA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"ran_honours":2,"ran_draft_wrong":2,"unverified":14},"by_repo_kind":{"official":{"samples":19,"ran":5,"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":"f6c275d6a18330a9","entry":"exact_match_score","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/EVAL/evaluate.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/EVAL/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6c275d6a18330a9"}},{"code_sha256_prefix":"2112c433b9c6d343","entry":"f1_score","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/EVAL/evaluate.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/EVAL/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2112c433b9c6d343"}},{"code_sha256_prefix":"d08f324f950148de","entry":"gelu","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/bert/modeling.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/bert/modeling.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"code_sha256_prefix":"5842ee67106321d6","entry":"get_activation","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/bert/modeling.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/bert/modeling.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5842ee67106321d6"}},{"code_sha256_prefix":"c6a80c065d2e4851","entry":"normalize_answer","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/EVAL/evaluate.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/EVAL/evaluate.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":true,"mcp_get_code":{"code_sha256":"c6a80c065d2e4851"}},{"code_sha256_prefix":"9212e9aaf973fc1a","entry":"compute_bleu","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/EVAL/bleu.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/EVAL/bleu.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":"9212e9aaf973fc1a"}},{"code_sha256_prefix":"30f594e125b54470","entry":"compute_rouge_L","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/EVAL/rouge.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/EVAL/rouge.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":"30f594e125b54470"}},{"code_sha256_prefix":"b24b3b9c700da839","entry":"create_float_feature","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/bert/create_pretraining_data.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/bert/create_pretraining_data.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":true,"mcp_get_code":{"code_sha256":"b24b3b9c700da839"}},{"code_sha256_prefix":"dd3ef48a15aec0cd","entry":"create_int_feature","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/bert/create_pretraining_data.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/bert/create_pretraining_data.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":true,"mcp_get_code":{"code_sha256":"dd3ef48a15aec0cd"}},{"code_sha256_prefix":"51e2ecf02135f000","entry":"diverse_bleu","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/EVAL/bleu.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/EVAL/bleu.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":"51e2ecf02135f000"}},{"code_sha256_prefix":"1b46c9ce24fc6db3","entry":"file_based_input_fn_builder","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/bert/run_classifier.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/bert/run_classifier.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":true,"mcp_get_code":{"code_sha256":"1b46c9ce24fc6db3"}},{"code_sha256_prefix":"50958618b65e514e","entry":"get_assignment_map_from_checkpoint","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/bert/modeling.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/bert/modeling.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":true,"mcp_get_code":{"code_sha256":"50958618b65e514e"}},{"code_sha256_prefix":"a92cc5798a065cd8","entry":"get_batch_dataset","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/utils.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/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":"a92cc5798a065cd8"}},{"code_sha256_prefix":"d542375d94644b96","entry":"get_dataset","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/utils.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/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":"d542375d94644b96"}},{"code_sha256_prefix":"f9afe5c09ca7b577","entry":"glu","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/layers.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/layers.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":"f9afe5c09ca7b577"}},{"code_sha256_prefix":"47a3c792cebb6603","entry":"input_fn_builder","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/bert/extract_features.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/bert/extract_features.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":true,"mcp_get_code":{"code_sha256":"47a3c792cebb6603"}},{"code_sha256_prefix":"df5f1c26bcb94d35","entry":"layer_norm_compute_python","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/layers.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/layers.py","link_basis":"plan_row","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":"df5f1c26bcb94d35"}},{"code_sha256_prefix":"16b3541623c0f60b","entry":"my_lcs","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/EVAL/rouge.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/EVAL/rouge.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":"16b3541623c0f60b"}},{"code_sha256_prefix":"15b2eb813c7ac34f","entry":"noam_norm","repo":"ZhangShiyue/QGforQA","repo_kind":"official","path":"LIB/layers.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/layers.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":"15b2eb813c7ac34f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}