{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/codexglue-a-machine-learning-benchmark#ran","syntology_url":"https://syntology.ai/paper/2102.04664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.04664"}},"official":{"repos":["microsoft/CodeXGLUE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/codexglue-a-machine-learning-benchmark#ran","syntology_url":"https://syntology.ai/paper/2102.04664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.04664"}},"official":{"repos":["microsoft/CodeXGLUE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}}],"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":71,"of":71,"of_with_code":28,"tagged_in_all":71,"counts":{"archive_papers_tagged":71,"with_a_code_link":28,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":71,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/bidirectional-attention-flow-for-machine","slug":"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":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":7,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bidirectional-attention-flow-for-machine#ran","syntology_url":"https://syntology.ai/paper/1611.01603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01603"}},"official":{"repos":["allenai/bi-att-flow"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/ernie-enhanced-representation-through","slug":"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":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ernie-enhanced-representation-through#ran","syntology_url":"https://syntology.ai/paper/1904.09223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09223"}},"official":{"repos":["PaddlePaddle/PaddleNLP"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/improving-language-understanding-by","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/codexglue-a-machine-learning-benchmark#ran","syntology_url":"https://syntology.ai/paper/2102.04664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.04664"}},"official":{"repos":["microsoft/CodeXGLUE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cdgp-automatic-cloze-distractor-generation","slug":"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","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/contextual-object-detection-with-multimodal#ran","syntology_url":"https://syntology.ai/paper/2305.18279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18279"}},"official":{"repos":["yuhangzang/contextdet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/are-pretrained-multilingual-models-equally-1","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mc-bert-efficient-language-pre-training-via-a#ran","syntology_url":"https://syntology.ai/paper/2006.05744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.05744"}},"official":{"repos":["MC-BERT/MC-BERT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-robustness-of-language-encoders","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-the-robustness-of-language-encoders#ran","syntology_url":"https://syntology.ai/paper/2005.05683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05683"}},"official":{"repos":["uclanlp/ProbeGrammarRobustness"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledge-graph-augmented-abstractive","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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},{"url":null,"slug":"nlp-and-education-using-semantic-similarity","title":"NLP and Education: using semantic similarity to evaluate filled gaps in a large-scale Cloze test in the classroom","date":"2024-11-02","arxiv_id":"2411.01280","repositories_listed":0,"syntology":null},{"url":null,"slug":"listen-again-and-choose-the-right-answer-a","title":"Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models","date":"2024-05-16","arxiv_id":"2405.10025","repositories_listed":0,"syntology":null},{"url":null,"slug":"emojinize-enriching-any-text-with-emoji","title":"Emojinize: Enriching Any Text with Emoji Translations","date":"2024-03-06","arxiv_id":"2403.03857","repositories_listed":0,"syntology":null},{"url":null,"slug":"controlling-cloze-test-question-item","title":"Controlling Cloze-test Question Item Difficulty with PLM-based Surrogate Models for IRT Assessment","date":"2024-03-03","arxiv_id":"2403.01456","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-contextual-target-attributes-for","title":"Exploiting Contextual Target Attributes for Target Sentiment Classification","date":"2023-12-21","arxiv_id":"2312.13766","repositories_listed":0,"syntology":null},{"url":null,"slug":"turead-an-eye-movement-dataset-of-turkish","title":"TURead: An eye movement dataset of Turkish reading","date":"2023-12-02","arxiv_id":"2312.01114","repositories_listed":0,"syntology":null},{"url":null,"slug":"storyfier-exploring-vocabulary-learning","title":"Storyfier: Exploring Vocabulary Learning Support with Text Generation Models","date":"2023-08-07","arxiv_id":"2308.03864","repositories_listed":0,"syntology":null},{"url":null,"slug":"index-indonesian-idiom-and-expression-dataset","title":"InDEX: Indonesian Idiom and Expression Dataset for Cloze Test","date":"2022-11-24","arxiv_id":"2211.13376","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenging-america-modeling-language-in-1","title":"Challenging America: Modeling language in longer time scales","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-corpus-for-commonsense-inference-in-story","title":"A Corpus for Commonsense Inference in Story Cloze Test","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-the-impact-of-syntactic-distance-and","title":"Modeling the Impact of Syntactic Distance and Surprisal on Cross-Slavic Text Comprehension","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"decorate-the-examples-a-simple-method-of","title":"Decorate the Examples: A Simple Method of Prompt Design for Biomedical Relation Extraction","date":"2022-04-21","arxiv_id":"2204.10360","repositories_listed":0,"syntology":null},{"url":null,"slug":"pretraining-without-wordpieces-learning-over","title":"Pretraining without Wordpieces: Learning Over a Vocabulary of Millions of Words","date":"2022-02-24","arxiv_id":"2202.12142","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-pretrained-multilingual-models-equally","title":"Are Pretrained Multilingual Models Equally Fair Across Languages?","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"challenging-america-modeling-language-in","title":"Challenging America: Modeling language in longer time scales","date":"2021-12-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cloze-evaluation-for-deeper-understanding-of","title":"Cloze Evaluation for Deeper Understanding of Commonsense Stories in Indonesian","date":"2021-12-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"eventbert-a-pre-trained-model-for-event","title":"EventBERT: A Pre-Trained Model for Event Correlation Reasoning","date":"2021-10-13","arxiv_id":"2110.06533","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmsoc-an-approach-for-socially-sensitive-1","title":"LMSOC: An approach for socially sensitive pretraining","date":"2021-05-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"correcting-the-misuse-a-method-for-the","title":"Correcting the Misuse: A Method for the Chinese Idiom Cloze Test","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-restoring-for-narrative-machine-reading","title":"Scene Restoring for Narrative Machine Reading Comprehension","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"script-induction-as-association-rule-mining","title":"Script Induction as Association Rule Mining","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-sentence-modeling-for-story","title":"Discriminative Sentence Modeling for Story Ending Prediction","date":"2019-12-19","arxiv_id":"1912.09008","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowsemlm-a-knowledge-infused-semantic","title":"KnowSemLM: A Knowledge Infused Semantic Language Model","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"demn-distilled-exposition-enhanced-matching","title":"DEMN: Distilled-Exposition Enhanced Matching Network for Story Comprehension","date":"2019-01-08","arxiv_id":"1901.02252","repositories_listed":0,"syntology":null},{"url":null,"slug":"find-a-reasonable-ending-for-stories-does","title":"Find a Reasonable Ending for Stories: Does Logic Relation Help the Story Cloze Test?","date":"2018-12-13","arxiv_id":"1812.05411","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-perspective-context-aggregation-for","title":"Multi-Perspective Context Aggregation for Semi-supervised Cloze-style Reading Comprehension","date":"2018-08-20","arxiv_id":"1808.06289","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-reasonable-and-diversified-story","title":"Generating Reasonable and Diversified Story Ending Using Sequence to Sequence Model with Adversarial Training","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tackling-the-story-ending-biases-in-the-story","title":"Tackling the Story Ending Biases in The Story Cloze Test","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/a-simple-and-effective-approach-to-the-story","slug":"a-simple-and-effective-approach-to-the-story","title":"A Simple and Effective Approach to the Story Cloze Test","date":"2018-03-15","arxiv_id":"1803.05547","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-cloze-test-dataset-designed-by","title":"Large-scale Cloze Test Dataset Designed by Teachers","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/large-scale-cloze-test-dataset-created-by","slug":"large-scale-cloze-test-dataset-created-by","title":"Large-scale Cloze Test Dataset Created by Teachers","date":"2017-11-09","arxiv_id":"1711.03225","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-joint-model-for-semantic-sequences-frames","title":"A Joint Model for Semantic Sequences: Frames, Entities, Sentiments","date":"2017-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-rnn-based-binary-classifier-for-the-story","title":"An RNN-based Binary Classifier for the Story Cloze Test","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"behind-the-scenes-of-an-evolving-event-cloze","title":"Behind the Scenes of an Evolving Event Cloze Test","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"iit-bhu-system-description-for-lsdsem17","title":"IIT (BHU): System Description for LSDSem'17 Shared Task","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lsdsem-2017-shared-task-the-story-cloze-test","title":"LSDSem 2017 Shared Task: The Story Cloze Test","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"resource-lean-modeling-of-coherence-in","title":"Resource-Lean Modeling of Coherence in Commonsense Stories","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"story-cloze-ending-selection-baselines-and","title":"Story Cloze Ending Selection Baselines and Data Examination","date":"2017-03-13","arxiv_id":"1703.04330","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-discourse-driven-language-models-for","title":"Two Discourse Driven Language Models for Semantics","date":"2016-06-17","arxiv_id":"1606.05679","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-rule-based-shallow-transfer-machine","title":"A Rule-based Shallow-transfer Machine Translation System for Scots and English","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/a-corpus-and-evaluation-framework-for-deeper","slug":"a-corpus-and-evaluation-framework-for-deeper","title":"A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories","date":"2016-04-06","arxiv_id":"1604.01696","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-cloze-test-performance-of-language","title":"Improving Cloze Test Performance of Language Learners Using Web N-Grams","date":"2014-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-system-for-generating-cloze-test-items-from","title":"A System for Generating Cloze Test Items from Russian-Language Text","date":"2013-09-01","arxiv_id":null,"repositories_listed":0,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":6,"papers_where_code_ran_first_page":"/task/cloze-test/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/cloze-test/papers/ran/1","json":"/task/cloze-test/papers/ran/1.json","rows":6}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"a22a845cd91e681c9aab3914dd7d5df029c2ad774fcb8cf516dae969d9ed38c4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}