{"url":"/task/cloze-test","name":"Cloze Test","slug":"cloze-test","description_markdown":"The cloze task refers to infilling individual words.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":71,"papers_with_code":28,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/cloze-test-on-codexglue-ct-all","slug":"cloze-test-on-codexglue-ct-all","dataset":"CodeXGLUE - CT-all","dataset_url":"/dataset/codexglue","rows_in_archive":1,"metrics":["Go","JS","Java","PHP","Python","Ruby"],"first_row_in_archive_order":{"model":"CodeBERT(MLM)","paper_title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","paper_url":"/paper/codexglue-a-machine-learning-benchmark","paper_date":"2021-02-09","arxiv_id":"2102.04664","code_links":[{"title":"microsoft/CodeXGLUE","url":"https://github.com/microsoft/CodeXGLUE"},{"title":"facebookresearch/CodeGen","url":"https://github.com/facebookresearch/CodeGen"},{"title":"sberbank-ai/fusion_brain_aij2021","url":"https://github.com/sberbank-ai/fusion_brain_aij2021"},{"title":"kilimanj4r0/code-summarization-beyond-function-level","url":"https://github.com/kilimanj4r0/code-summarization-beyond-function-level"},{"title":"yueyuel/programgen-lms-reliability","url":"https://github.com/yueyuel/programgen-lms-reliability"},{"title":"Avmb/semantic_neq_game","url":"https://github.com/Avmb/semantic_neq_game"},{"title":"deeplearnxmu/unigencoder","url":"https://github.com/deeplearnxmu/unigencoder"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/cloze-test-on-codexglue-ct-maxmin","slug":"cloze-test-on-codexglue-ct-maxmin","dataset":"CodeXGLUE - CT-maxmin","dataset_url":"/dataset/codexglue","rows_in_archive":1,"metrics":["Go","JS","Java","PHP","Python","Ruby"],"first_row_in_archive_order":{"model":"CodeBERT(MLM)","paper_title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","paper_url":"/paper/codexglue-a-machine-learning-benchmark","paper_date":"2021-02-09","arxiv_id":"2102.04664","code_links":[{"title":"microsoft/CodeXGLUE","url":"https://github.com/microsoft/CodeXGLUE"},{"title":"facebookresearch/CodeGen","url":"https://github.com/facebookresearch/CodeGen"},{"title":"sberbank-ai/fusion_brain_aij2021","url":"https://github.com/sberbank-ai/fusion_brain_aij2021"},{"title":"kilimanj4r0/code-summarization-beyond-function-level","url":"https://github.com/kilimanj4r0/code-summarization-beyond-function-level"},{"title":"yueyuel/programgen-lms-reliability","url":"https://github.com/yueyuel/programgen-lms-reliability"},{"title":"Avmb/semantic_neq_game","url":"https://github.com/Avmb/semantic_neq_game"},{"title":"deeplearnxmu/unigencoder","url":"https://github.com/deeplearnxmu/unigencoder"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/codexglue","name":"CodeXGLUE","full_name":"","num_papers_in_archive":205},{"url":"/dataset/completion-norms-for-3085-english-sentence","name":"Completion norms for 3085 English sentence contexts","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":28,"of":28,"tagged_in_all":71,"items":[{"url":"/paper/bidirectional-attention-flow-for-machine","title":"Bidirectional Attention Flow for Machine Comprehension","date":"2016-11-05","arxiv_id":"1611.01603","repositories_listed":27,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":7}},{"url":"/paper/ernie-enhanced-representation-through","title":"ERNIE: Enhanced Representation through Knowledge Integration","date":"2019-04-19","arxiv_id":"1904.09223","repositories_listed":19,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/improving-language-understanding-by","title":"Improving Language Understanding by Generative Pre-Training","date":"2018-06-11","arxiv_id":null,"repositories_listed":13,"syntology":null},{"url":"/paper/cpm-a-large-scale-generative-chinese-pre","title":"CPM: A Large-scale Generative Chinese Pre-trained Language Model","date":"2020-12-01","arxiv_id":"2012.00413","repositories_listed":10,"syntology":null},{"url":"/paper/codexglue-a-machine-learning-benchmark","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","date":"2021-02-09","arxiv_id":"2102.04664","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/cdgp-automatic-cloze-distractor-generation","title":"CDGP: Automatic Cloze Distractor Generation based on Pre-trained Language Model","date":"2024-03-15","arxiv_id":"2403.10326","repositories_listed":1,"syntology":null},{"url":"/paper/contextual-object-detection-with-multimodal","title":"Contextual Object Detection with Multimodal Large Language Models","date":"2023-05-29","arxiv_id":"2305.18279","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/are-pretrained-multilingual-models-equally-1","title":"Are Pretrained Multilingual Models Equally Fair Across Languages?","date":"2022-10-11","arxiv_id":"2210.05457","repositories_listed":1,"syntology":null},{"url":"/paper/contextual-embedding-and-model-weighting-by","title":"Contextual embedding and model weighting by fusing domain knowledge on Biomedical Question Answering","date":"2022-06-26","arxiv_id":"2206.12866","repositories_listed":1,"syntology":null},{"url":"/paper/cloze-evaluation-for-deeper-understanding-of-1","title":"Cloze Evaluation for Deeper Understanding of Commonsense Stories in Indonesian","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/on-the-cross-modal-transfer-from-natural","title":"On The Cross-Modal Transfer from Natural Language to Code through Adapter Modules","date":"2022-04-19","arxiv_id":"2204.08653","repositories_listed":1,"syntology":null},{"url":"/paper/lmsoc-an-approach-for-socially-sensitive","title":"LMSOC: An Approach for Socially Sensitive Pretraining","date":"2021-10-20","arxiv_id":"2110.10319","repositories_listed":1,"syntology":null},{"url":"/paper/video-abnormal-event-detection-by-learning-to","title":"Video Abnormal Event Detection by Learning to Complete Visual Cloze Tests","date":"2021-08-05","arxiv_id":"2108.02356","repositories_listed":1,"syntology":null},{"url":"/paper/probing-for-bridging-inference-in-transformer","title":"Probing for Bridging Inference in Transformer Language Models","date":"2021-04-19","arxiv_id":"2104.09400","repositories_listed":1,"syntology":null},{"url":"/paper/braid-weaving-symbolic-and-statistical","title":"Braid: Weaving Symbolic and Neural Knowledge into Coherent Logical Explanations","date":"2020-11-26","arxiv_id":"2011.13354","repositories_listed":1,"syntology":null},{"url":"/paper/a-bert-based-dual-embedding-model-for-chinese","title":"A BERT-based Dual Embedding Model for Chinese Idiom Prediction","date":"2020-11-04","arxiv_id":"2011.02378","repositories_listed":1,"syntology":null},{"url":"/paper/reasoning-about-goals-steps-and-temporal","title":"Reasoning about Goals, Steps, and Temporal Ordering with WikiHow","date":"2020-09-16","arxiv_id":"2009.07690","repositories_listed":1,"syntology":null},{"url":"/paper/cloze-test-helps-effective-video-anomaly","title":"Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Events","date":"2020-08-27","arxiv_id":"2008.11988","repositories_listed":1,"syntology":null},{"url":"/paper/explainable-inference-on-sequential-data-via","title":"Explainable Inference on Sequential Data via Memory-Tracking","date":"2020-07-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mc-bert-efficient-language-pre-training-via-a","title":"MC-BERT: Efficient Language Pre-Training via a Meta Controller","date":"2020-06-10","arxiv_id":"2006.05744","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":4}},{"url":"/paper/on-the-robustness-of-language-encoders","title":"On the Robustness of Language Encoders against Grammatical Errors","date":"2020-05-12","arxiv_id":"2005.05683","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/knowledge-graph-augmented-abstractive","title":"Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward","date":"2020-05-03","arxiv_id":"2005.01159","repositories_listed":1,"syntology":null},{"url":"/paper/sibert-enhanced-chinese-pre-trained-language","title":"SiBert: Enhanced Chinese Pre-trained Language Model with Sentence Insertion","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/chid-a-large-scale-chinese-idiom-dataset-for","title":"ChID: A Large-scale Chinese IDiom Dataset for Cloze Test","date":"2019-06-04","arxiv_id":"1906.01265","repositories_listed":1,"syntology":null},{"url":"/paper/asking-the-right-question-inferring-advice","title":"Asking the Right Question: Inferring Advice-Seeking Intentions from Personal Narratives","date":"2019-04-02","arxiv_id":"1904.01587","repositories_listed":1,"syntology":null},{"url":"/paper/chengyu-cloze-test","title":"Chengyu Cloze Test","date":"2018-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/narrative-modeling-with-memory-chains-and","title":"Narrative Modeling with Memory Chains and Semantic Supervision","date":"2018-05-16","arxiv_id":"1805.06122","repositories_listed":1,"syntology":null},{"url":"/paper/lsdsem-2017-exploring-data-generation-methods","title":"LSDSem 2017: Exploring Data Generation Methods for the Story Cloze Test","date":"2017-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":6,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}