{"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/language-modeling/papers/48","list_of":"/task/language-modeling","task":"Language Modeling","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":48,"pages_in_order":142,"rows_per_page":100,"rows":[4701,4800],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"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"},"first_page":"/task/language-modeling","prev":"/task/language-modeling/papers/47","next":"/task/language-modeling/papers/49","papers":[{"url":"/paper/prix-lm-pretraining-for-multilingual","slug":"prix-lm-pretraining-for-multilingual","title":"Prix-LM: Pretraining for Multilingual Knowledge Base Construction","date":"2021-10-16","arxiv_id":"2110.08443","repositories_listed":1,"syntology":null},{"url":"/paper/transformer-with-a-mixture-of-gaussian-keys-1","slug":"transformer-with-a-mixture-of-gaussian-keys-1","title":"Improving Transformers with Probabilistic Attention Keys","date":"2021-10-16","arxiv_id":"2110.08678","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transformer-with-a-mixture-of-gaussian-keys-1#ran","syntology_url":"https://syntology.ai/paper/2110.08678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08678"}},"official":{"repos":["minhtannguyen/transformer-mgk"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/boosting-coherence-of-language-models","slug":"boosting-coherence-of-language-models","title":"Coherence boosting: When your pretrained language model is not paying enough attention","date":"2021-10-15","arxiv_id":"2110.08294","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/boosting-coherence-of-language-models#ran","syntology_url":"https://syntology.ai/paper/2110.08294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08294"}},"official":{"repos":["zhenwang9102/coherence-boosting"],"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":["official"]}}},{"url":"/paper/ds-tod-efficient-domain-specialization-for","slug":"ds-tod-efficient-domain-specialization-for","title":"DS-TOD: Efficient Domain Specialization for Task Oriented Dialog","date":"2021-10-15","arxiv_id":"2110.08395","repositories_listed":1,"syntology":null},{"url":"/paper/generated-knowledge-prompting-for-commonsense","slug":"generated-knowledge-prompting-for-commonsense","title":"Generated Knowledge Prompting for Commonsense Reasoning","date":"2021-10-15","arxiv_id":"2110.08387","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generated-knowledge-prompting-for-commonsense#ran","syntology_url":"https://syntology.ai/paper/2110.08387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08387"}},"official":{"repos":["liujch1998/gkp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/meta-learning-via-language-model-in-context","slug":"meta-learning-via-language-model-in-context","title":"Meta-learning via Language Model In-context Tuning","date":"2021-10-15","arxiv_id":"2110.07814","repositories_listed":1,"syntology":null},{"url":"/paper/the-world-of-an-octopus-how-reporting-bias","slug":"the-world-of-an-octopus-how-reporting-bias","title":"The World of an Octopus: How Reporting Bias Influences a Language Model's Perception of Color","date":"2021-10-15","arxiv_id":"2110.08182","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-world-of-an-octopus-how-reporting-bias#ran","syntology_url":"https://syntology.ai/paper/2110.08182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08182"}},"official":{"repos":["nala-cub/coda"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tracing-origins-coref-aware-machine-reading","slug":"tracing-origins-coref-aware-machine-reading","title":"Tracing Origins: Coreference-aware Machine Reading Comprehension","date":"2021-10-15","arxiv_id":"2110.07961","repositories_listed":1,"syntology":null},{"url":"/paper/spoken-objectnet-a-bias-controlled-spoken","slug":"spoken-objectnet-a-bias-controlled-spoken","title":"Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset","date":"2021-10-14","arxiv_id":"2110.07575","repositories_listed":1,"syntology":null},{"url":"/paper/symbolic-knowledge-distillation-from-general","slug":"symbolic-knowledge-distillation-from-general","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","date":"2021-10-14","arxiv_id":"2110.07178","repositories_listed":1,"syntology":null},{"url":"/paper/unipelt-a-unified-framework-for-parameter","slug":"unipelt-a-unified-framework-for-parameter","title":"UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning","date":"2021-10-14","arxiv_id":"2110.07577","repositories_listed":1,"syntology":null},{"url":"/paper/dict-bert-enhancing-language-model-pre-1","slug":"dict-bert-enhancing-language-model-pre-1","title":"Dict-BERT: Enhancing Language Model Pre-training with Dictionary","date":"2021-10-13","arxiv_id":"2110.06490","repositories_listed":1,"syntology":null},{"url":"/paper/learning-compact-metrics-for-mt","slug":"learning-compact-metrics-for-mt","title":"Learning Compact Metrics for MT","date":"2021-10-12","arxiv_id":"2110.06341","repositories_listed":1,"syntology":null},{"url":"/paper/long-expressive-memory-for-sequence-modeling-1","slug":"long-expressive-memory-for-sequence-modeling-1","title":"Long Expressive Memory for Sequence Modeling","date":"2021-10-10","arxiv_id":"2110.04744","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":1,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/long-expressive-memory-for-sequence-modeling-1#ran","syntology_url":"https://syntology.ai/paper/2110.04744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04744"}},"official":{"repos":["tk-rusch/lem"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/yuan-1-0-large-scale-pre-trained-language","slug":"yuan-1-0-large-scale-pre-trained-language","title":"Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning","date":"2021-10-10","arxiv_id":"2110.04725","repositories_listed":1,"syntology":null},{"url":"/paper/improving-multi-party-dialogue-discourse","slug":"improving-multi-party-dialogue-discourse","title":"Improving Multi-Party Dialogue Discourse Parsing via Domain Integration","date":"2021-10-09","arxiv_id":"2110.04526","repositories_listed":1,"syntology":null},{"url":"/paper/global-explainability-of-bert-based","slug":"global-explainability-of-bert-based","title":"Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors","date":"2021-10-08","arxiv_id":"2110.04399","repositories_listed":1,"syntology":null},{"url":"/paper/layer-wise-pruning-of-transformer-attention","slug":"layer-wise-pruning-of-transformer-attention","title":"Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling","date":"2021-10-07","arxiv_id":"2110.03252","repositories_listed":1,"syntology":null},{"url":"/paper/mixer-tts-non-autoregressive-fast-and-compact","slug":"mixer-tts-non-autoregressive-fast-and-compact","title":"Mixer-TTS: non-autoregressive, fast and compact text-to-speech model conditioned on language model embeddings","date":"2021-10-07","arxiv_id":"2110.03584","repositories_listed":1,"syntology":null},{"url":"/paper/a-novel-metric-for-evaluating-semantics","slug":"a-novel-metric-for-evaluating-semantics","title":"Contextualized Semantic Distance between Highly Overlapped Texts","date":"2021-10-04","arxiv_id":"2110.01176","repositories_listed":1,"syntology":null},{"url":"/paper/juribert-a-masked-language-model-adaptation","slug":"juribert-a-masked-language-model-adaptation","title":"JuriBERT: A Masked-Language Model Adaptation for French Legal Text","date":"2021-10-04","arxiv_id":"2110.01485","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-self-training-for-few-shot","slug":"revisiting-self-training-for-few-shot","title":"Revisiting Self-Training for Few-Shot Learning of Language Model","date":"2021-10-04","arxiv_id":"2110.01256","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/revisiting-self-training-for-few-shot#ran","syntology_url":"https://syntology.ai/paper/2110.01256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01256"}},"official":{"repos":["matthewcym/sflm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/bert-got-a-date-introducing-transformers-to","slug":"bert-got-a-date-introducing-transformers-to","title":"BERT got a Date: Introducing Transformers to Temporal Tagging","date":"2021-09-30","arxiv_id":"2109.14927","repositories_listed":1,"syntology":null},{"url":"/paper/matscibert-a-materials-domain-language-model","slug":"matscibert-a-materials-domain-language-model","title":"MatSciBERT: A Materials Domain Language Model for Text Mining and Information Extraction","date":"2021-09-30","arxiv_id":"2109.15290","repositories_listed":1,"syntology":null},{"url":"/paper/slovakbert-slovak-masked-language-model","slug":"slovakbert-slovak-masked-language-model","title":"SlovakBERT: Slovak Masked Language Model","date":"2021-09-30","arxiv_id":"2109.15254","repositories_listed":1,"syntology":null},{"url":"/paper/effective-use-of-graph-convolution-network","slug":"effective-use-of-graph-convolution-network","title":"Effective Use of Graph Convolution Network and Contextual Sub-Tree forCommodity News Event Extraction","date":"2021-09-27","arxiv_id":"2109.12781","repositories_listed":1,"syntology":null},{"url":"/paper/factorized-neural-transducer-for-efficient","slug":"factorized-neural-transducer-for-efficient","title":"Factorized Neural Transducer for Efficient Language Model Adaptation","date":"2021-09-27","arxiv_id":"2110.01500","repositories_listed":1,"syntology":null},{"url":"/paper/extracting-and-inferring-personal-attributes","slug":"extracting-and-inferring-personal-attributes","title":"Extracting and Inferring Personal Attributes from Dialogue","date":"2021-09-26","arxiv_id":"2109.12702","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-information-extraction-as-a-unified","slug":"zero-shot-information-extraction-as-a-unified","title":"Zero-Shot Information Extraction as a Unified Text-to-Triple Translation","date":"2021-09-23","arxiv_id":"2109.11171","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-relation-embeddings-from-pre","slug":"distilling-relation-embeddings-from-pre","title":"Distilling Relation Embeddings from Pre-trained Language Models","date":"2021-09-21","arxiv_id":"2110.15705","repositories_listed":1,"syntology":null},{"url":"/paper/jobbert-understanding-job-titles-through","slug":"jobbert-understanding-job-titles-through","title":"JobBERT: Understanding Job Titles through Skills","date":"2021-09-20","arxiv_id":"2109.09605","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-linguistic-context-for-language","slug":"distilling-linguistic-context-for-language","title":"Distilling Linguistic Context for Language Model Compression","date":"2021-09-17","arxiv_id":"2109.08359","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/distilling-linguistic-context-for-language#ran","syntology_url":"https://syntology.ai/paper/2109.08359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08359"}},"official":{"repos":["geondopark/ckd"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/does-commonsense-help-in-detecting-sarcasm","slug":"does-commonsense-help-in-detecting-sarcasm","title":"Does Commonsense help in detecting Sarcasm?","date":"2021-09-17","arxiv_id":"2109.08588","repositories_listed":1,"syntology":null},{"url":"/paper/knowman-weakly-supervised-multinomial","slug":"knowman-weakly-supervised-multinomial","title":"KnowMAN: Weakly Supervised Multinomial Adversarial Networks","date":"2021-09-16","arxiv_id":"2109.07994","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/knowman-weakly-supervised-multinomial#ran","syntology_url":"https://syntology.ai/paper/2109.07994","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.07994"}},"official":{"repos":["luisamaerz/knowman"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/melt-message-level-transformer-with-masked","slug":"melt-message-level-transformer-with-masked","title":"MeLT: Message-Level Transformer with Masked Document Representations as Pre-Training for Stance Detection","date":"2021-09-16","arxiv_id":"2109.08113","repositories_listed":1,"syntology":null},{"url":"/paper/comparing-text-representations-a-theory","slug":"comparing-text-representations-a-theory","title":"Comparing Text Representations: A Theory-Driven Approach","date":"2021-09-15","arxiv_id":"2109.07458","repositories_listed":1,"syntology":null},{"url":"/paper/dialogue-state-tracking-with-a-language-model","slug":"dialogue-state-tracking-with-a-language-model","title":"Dialogue State Tracking with a Language Model using Schema-Driven Prompting","date":"2021-09-15","arxiv_id":"2109.07506","repositories_listed":1,"syntology":null},{"url":"/paper/it-doesn-t-look-good-for-a-date-transforming","slug":"it-doesn-t-look-good-for-a-date-transforming","title":"\"It doesn't look good for a date\": Transforming Critiques into Preferences for Conversational Recommendation Systems","date":"2021-09-15","arxiv_id":"2109.07576","repositories_listed":1,"syntology":null},{"url":"/paper/supcl-seq-supervised-contrastive-learning-for","slug":"supcl-seq-supervised-contrastive-learning-for","title":"SupCL-Seq: Supervised Contrastive Learning for Downstream Optimized Sequence Representations","date":"2021-09-15","arxiv_id":"2109.07424","repositories_listed":1,"syntology":null},{"url":"/paper/mdapt-multilingual-domain-adaptive","slug":"mdapt-multilingual-domain-adaptive","title":"MDAPT: Multilingual Domain Adaptive Pretraining in a Single Model","date":"2021-09-14","arxiv_id":"2109.06605","repositories_listed":1,"syntology":null},{"url":"/paper/types-of-out-of-distribution-texts-and-how-to","slug":"types-of-out-of-distribution-texts-and-how-to","title":"Types of Out-of-Distribution Texts and How to Detect Them","date":"2021-09-14","arxiv_id":"2109.06827","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/types-of-out-of-distribution-texts-and-how-to#ran","syntology_url":"https://syntology.ai/paper/2109.06827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.06827"}},"official":{"repos":["uditarora/ood-text-emnlp"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cpt-a-pre-trained-unbalanced-transformerfor","slug":"cpt-a-pre-trained-unbalanced-transformerfor","title":"CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation","date":"2021-09-13","arxiv_id":"2109.05729","repositories_listed":1,"syntology":null},{"url":"/paper/old-bert-new-tricks-artificial-language","slug":"old-bert-new-tricks-artificial-language","title":"Connecting degree and polarity: An artificial language learning study","date":"2021-09-13","arxiv_id":"2109.06333","repositories_listed":1,"syntology":null},{"url":"/paper/virtual-data-augmentation-a-robust-and","slug":"virtual-data-augmentation-a-robust-and","title":"Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models","date":"2021-09-13","arxiv_id":"2109.05793","repositories_listed":1,"syntology":null},{"url":"/paper/xgqa-cross-lingual-visual-question-answering","slug":"xgqa-cross-lingual-visual-question-answering","title":"xGQA: Cross-Lingual Visual Question Answering","date":"2021-09-13","arxiv_id":"2109.06082","repositories_listed":1,"syntology":null},{"url":"/paper/teasel-a-transformer-based-speech-prefixed","slug":"teasel-a-transformer-based-speech-prefixed","title":"TEASEL: A Transformer-Based Speech-Prefixed Language Model","date":"2021-09-12","arxiv_id":"2109.05522","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/teasel-a-transformer-based-speech-prefixed#ran","syntology_url":"https://syntology.ai/paper/2109.05522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05522"}},"official":null}},{"url":"/paper/distantly-supervised-named-entity-recognition-1","slug":"distantly-supervised-named-entity-recognition-1","title":"Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training","date":"2021-09-10","arxiv_id":"2109.05003","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/distantly-supervised-named-entity-recognition-1#ran","syntology_url":"https://syntology.ai/paper/2109.05003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05003"}},"official":{"repos":["yumeng5/roster"],"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":["official"]}}},{"url":"/paper/euphemistic-phrase-detection-by-masked","slug":"euphemistic-phrase-detection-by-masked","title":"Euphemistic Phrase Detection by Masked Language Model","date":"2021-09-10","arxiv_id":"2109.04666","repositories_listed":1,"syntology":null},{"url":"/paper/indobertweet-a-pretrained-language-model-for","slug":"indobertweet-a-pretrained-language-model-for","title":"IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary Initialization","date":"2021-09-10","arxiv_id":"2109.04607","repositories_listed":1,"syntology":null},{"url":"/paper/studying-word-order-through-iterative","slug":"studying-word-order-through-iterative","title":"Studying word order through iterative shuffling","date":"2021-09-10","arxiv_id":"2109.04867","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/studying-word-order-through-iterative#ran","syntology_url":"https://syntology.ai/paper/2109.04867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04867"}},"official":{"repos":["malkin1729/ibis"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-zero-shot-commonsense-reasoning-with","slug":"towards-zero-shot-commonsense-reasoning-with","title":"Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language Models","date":"2021-09-10","arxiv_id":"2109.05105","repositories_listed":1,"syntology":null},{"url":"/paper/astitchinlanguagemodels-dataset-and-methods","slug":"astitchinlanguagemodels-dataset-and-methods","title":"AStitchInLanguageModels: Dataset and Methods for the Exploration of Idiomaticity in Pre-Trained Language Models","date":"2021-09-09","arxiv_id":"2109.04413","repositories_listed":1,"syntology":null},{"url":"/paper/avoiding-inference-heuristics-in-few-shot","slug":"avoiding-inference-heuristics-in-few-shot","title":"Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning","date":"2021-09-09","arxiv_id":"2109.04144","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-entailment-patterns-for-lexical","slug":"continuous-entailment-patterns-for-lexical","title":"Continuous Entailment Patterns for Lexical Inference in Context","date":"2021-09-08","arxiv_id":"2109.03695","repositories_listed":1,"syntology":null},{"url":"/paper/memory-and-knowledge-augmented-language","slug":"memory-and-knowledge-augmented-language","title":"Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories","date":"2021-09-08","arxiv_id":"2109.03754","repositories_listed":1,"syntology":null},{"url":"/paper/nsp-bert-a-prompt-based-zero-shot-learner","slug":"nsp-bert-a-prompt-based-zero-shot-learner","title":"NSP-BERT: A Prompt-based Few-Shot Learner Through an Original Pre-training Task--Next Sentence Prediction","date":"2021-09-08","arxiv_id":"2109.03564","repositories_listed":1,"syntology":null},{"url":"/paper/infusing-future-information-into-monotonic","slug":"infusing-future-information-into-monotonic","title":"Infusing Future Information into Monotonic Attention Through Language Models","date":"2021-09-07","arxiv_id":"2109.03121","repositories_listed":1,"syntology":null},{"url":"/paper/text-free-prosody-aware-generative-spoken","slug":"text-free-prosody-aware-generative-spoken","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","date":"2021-09-07","arxiv_id":"2109.03264","repositories_listed":1,"syntology":null},{"url":"/paper/permuteformer-efficient-relative-position","slug":"permuteformer-efficient-relative-position","title":"PermuteFormer: Efficient Relative Position Encoding for Long Sequences","date":"2021-09-06","arxiv_id":"2109.02377","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/permuteformer-efficient-relative-position#ran","syntology_url":"https://syntology.ai/paper/2109.02377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.02377"}},"official":{"repos":["cpcp1998/permuteformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/data-efficient-masked-language-modeling-for","slug":"data-efficient-masked-language-modeling-for","title":"Data Efficient Masked Language Modeling for Vision and Language","date":"2021-09-05","arxiv_id":"2109.02040","repositories_listed":1,"syntology":null},{"url":"/paper/learning-hierarchical-structures-with","slug":"learning-hierarchical-structures-with","title":"Learning Hierarchical Structures with Differentiable Nondeterministic Stacks","date":"2021-09-05","arxiv_id":"2109.01982","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-hierarchical-structures-with#ran","syntology_url":"https://syntology.ai/paper/2109.01982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01982"}},"official":{"repos":["bdusell/nondeterministic-stack-rnn"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/teaching-autoregressive-language-models","slug":"teaching-autoregressive-language-models","title":"Teaching Autoregressive Language Models Complex Tasks By Demonstration","date":"2021-09-05","arxiv_id":"2109.02102","repositories_listed":1,"syntology":null},{"url":"/paper/frustratingly-simple-pretraining-alternatives","slug":"frustratingly-simple-pretraining-alternatives","title":"Frustratingly Simple Pretraining Alternatives to Masked Language Modeling","date":"2021-09-04","arxiv_id":"2109.01819","repositories_listed":1,"syntology":null},{"url":"/paper/imposing-relation-structure-in-language-model","slug":"imposing-relation-structure-in-language-model","title":"Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning","date":"2021-09-02","arxiv_id":"2109.00840","repositories_listed":1,"syntology":null},{"url":"/paper/skim-attention-learning-to-focus-via-document","slug":"skim-attention-learning-to-focus-via-document","title":"Skim-Attention: Learning to Focus via Document Layout","date":"2021-09-02","arxiv_id":"2109.01078","repositories_listed":1,"syntology":null},{"url":"/paper/ctal-pre-training-cross-modal-transformer-for","slug":"ctal-pre-training-cross-modal-transformer-for","title":"CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations","date":"2021-09-01","arxiv_id":"2109.00181","repositories_listed":1,"syntology":{"n":19,"n_ran":15,"n_constructed":2,"n_ran_checked":15,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":14,"n_pointer_only":6,"phrase":"15 ran (of which 2 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ctal-pre-training-cross-modal-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2109.00181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00181"}},"official":{"repos":["ydkwim/ctal"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/infty-former-infinite-memory-transformer","slug":"infty-former-infinite-memory-transformer","title":"$\\infty$-former: Infinite Memory Transformer","date":"2021-09-01","arxiv_id":"2109.00301","repositories_listed":1,"syntology":null},{"url":"/paper/effective-sequence-to-sequence-dialogue-state","slug":"effective-sequence-to-sequence-dialogue-state","title":"Effective Sequence-to-Sequence Dialogue State Tracking","date":"2021-08-31","arxiv_id":"2108.13990","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-conformer-progressive-downsampling","slug":"efficient-conformer-progressive-downsampling","title":"Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognition","date":"2021-08-31","arxiv_id":"2109.01163","repositories_listed":1,"syntology":null},{"url":"/paper/melm-data-augmentation-with-masked-entity","slug":"melm-data-augmentation-with-masked-entity","title":"MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER","date":"2021-08-31","arxiv_id":"2108.13655","repositories_listed":1,"syntology":null},{"url":"/paper/sentence-bottleneck-autoencoders-from","slug":"sentence-bottleneck-autoencoders-from","title":"Sentence Bottleneck Autoencoders from Transformer Language Models","date":"2021-08-31","arxiv_id":"2109.00055","repositories_listed":1,"syntology":null},{"url":"/paper/selective-differential-privacy-for-language","slug":"selective-differential-privacy-for-language","title":"Selective Differential Privacy for Language Modeling","date":"2021-08-30","arxiv_id":"2108.12944","repositories_listed":1,"syntology":null},{"url":"/paper/want-to-reduce-labeling-cost-gpt-3-can-help","slug":"want-to-reduce-labeling-cost-gpt-3-can-help","title":"Want To Reduce Labeling Cost? GPT-3 Can Help","date":"2021-08-30","arxiv_id":"2108.13487","repositories_listed":1,"syntology":null},{"url":"/paper/self-training-improves-pre-training-for-few","slug":"self-training-improves-pre-training-for-few","title":"Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems","date":"2021-08-28","arxiv_id":"2108.12589","repositories_listed":1,"syntology":null},{"url":"/paper/models-in-a-spelling-bee-language-models","slug":"models-in-a-spelling-bee-language-models","title":"Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens","date":"2021-08-25","arxiv_id":"2108.11193","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/models-in-a-spelling-bee-language-models#ran","syntology_url":"https://syntology.ai/paper/2108.11193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.11193"}},"official":{"repos":["itay1itzhak/spellingbee"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cushlepor-customised-hlepor-metric-using","slug":"cushlepor-customised-hlepor-metric-using","title":"cushLEPOR: customising hLEPOR metric using Optuna for higher agreement with human judgments or pre-trained language model LaBSE","date":"2021-08-21","arxiv_id":"2108.09484","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-perceived-multi-modal-pretraining","slug":"knowledge-perceived-multi-modal-pretraining","title":"Knowledge Perceived Multi-modal Pretraining in E-commerce","date":"2021-08-20","arxiv_id":"2109.00895","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/knowledge-perceived-multi-modal-pretraining#ran","syntology_url":"https://syntology.ai/paper/2109.00895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00895"}},"official":{"repos":["yushanzhu/k3m"],"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":["official"]}}},{"url":"/paper/pre-training-for-ad-hoc-retrieval-hyperlink","slug":"pre-training-for-ad-hoc-retrieval-hyperlink","title":"Pre-training for Ad-hoc Retrieval: Hyperlink is Also You Need","date":"2021-08-20","arxiv_id":"2108.09346","repositories_listed":1,"syntology":null},{"url":"/paper/a-weak-supervised-dataset-of-fine-grained","slug":"a-weak-supervised-dataset-of-fine-grained","title":"A Weakly Supervised Dataset of Fine-Grained Emotions in Portuguese","date":"2021-08-17","arxiv_id":"2108.07638","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-protein-using-large-scale-pretrain","slug":"modeling-protein-using-large-scale-pretrain","title":"Modeling Protein Using Large-scale Pretrain Language Model","date":"2021-08-17","arxiv_id":"2108.07435","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/modeling-protein-using-large-scale-pretrain#ran","syntology_url":"https://syntology.ai/paper/2108.07435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.07435"}},"official":{"repos":["THUDM/ProteinLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/autoencoders-as-tools-for-program-synthesis","slug":"autoencoders-as-tools-for-program-synthesis","title":"Autoencoders as Tools for Program Synthesis","date":"2021-08-16","arxiv_id":"2108.07129","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-corpus-aware-language-model-pre","slug":"unsupervised-corpus-aware-language-model-pre","title":"Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval","date":"2021-08-12","arxiv_id":"2108.05540","repositories_listed":1,"syntology":null},{"url":"/paper/perturbing-inputs-for-fragile-interpretations","slug":"perturbing-inputs-for-fragile-interpretations","title":"Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing","date":"2021-08-11","arxiv_id":"2108.04990","repositories_listed":1,"syntology":null},{"url":"/paper/berthop-an-effective-vision-and-language","slug":"berthop-an-effective-vision-and-language","title":"BERTHop: An Effective Vision-and-Language Model for Chest X-ray Disease Diagnosis","date":"2021-08-10","arxiv_id":"2108.04938","repositories_listed":1,"syntology":null},{"url":"/paper/do-images-really-do-the-talking-analysing-the","slug":"do-images-really-do-the-talking-analysing-the","title":"Do Images really do the Talking? Analysing the significance of Images in Tamil Troll meme classification","date":"2021-08-09","arxiv_id":"2108.03886","repositories_listed":1,"syntology":null},{"url":"/paper/noisy-channel-language-model-prompting-for","slug":"noisy-channel-language-model-prompting-for","title":"Noisy Channel Language Model Prompting for Few-Shot Text Classification","date":"2021-08-09","arxiv_id":"2108.04106","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/noisy-channel-language-model-prompting-for#ran","syntology_url":"https://syntology.ai/paper/2108.04106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04106"}},"official":{"repos":["shmsw25/Channel-LM-Prompting"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/structext-structured-text-understanding-with","slug":"structext-structured-text-understanding-with","title":"StrucTexT: Structured Text Understanding with Multi-Modal Transformers","date":"2021-08-06","arxiv_id":"2108.02923","repositories_listed":1,"syntology":null},{"url":"/paper/finetuning-pretrained-transformers-into","slug":"finetuning-pretrained-transformers-into","title":"Finetuning Pretrained Transformers into Variational Autoencoders","date":"2021-08-05","arxiv_id":"2108.02446","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-distillation-from-bert-transformer","slug":"knowledge-distillation-from-bert-transformer","title":"Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification","date":"2021-08-05","arxiv_id":"2108.02598","repositories_listed":1,"syntology":null},{"url":"/paper/controlled-text-generation-as-continuous","slug":"controlled-text-generation-as-continuous","title":"Controlled Text Generation as Continuous Optimization with Multiple Constraints","date":"2021-08-04","arxiv_id":"2108.01850","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/controlled-text-generation-as-continuous#ran","syntology_url":"https://syntology.ai/paper/2108.01850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.01850"}},"official":null}},{"url":"/paper/curriculum-learning-for-language-modeling","slug":"curriculum-learning-for-language-modeling","title":"Curriculum learning for language modeling","date":"2021-08-04","arxiv_id":"2108.02170","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/curriculum-learning-for-language-modeling#ran","syntology_url":"https://syntology.ai/paper/2108.02170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02170"}},"official":{"repos":["spacemanidol/CurriculumLearningForLanguageModels"],"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/exploiting-bert-for-multimodal-target","slug":"exploiting-bert-for-multimodal-target","title":"Exploiting BERT For Multimodal Target Sentiment Classification Through Input Space Translation","date":"2021-08-03","arxiv_id":"2108.01682","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-speaker-information-in-self","slug":"analyzing-speaker-information-in-self","title":"Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing","date":"2021-08-02","arxiv_id":"2108.00917","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/analyzing-speaker-information-in-self#ran","syntology_url":"https://syntology.ai/paper/2108.00917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.00917"}},"official":null}},{"url":"/paper/lichee-improving-language-model-pre-training","slug":"lichee-improving-language-model-pre-training","title":"LICHEE: Improving Language Model Pre-training with Multi-grained Tokenization","date":"2021-08-02","arxiv_id":"2108.00801","repositories_listed":1,"syntology":null},{"url":"/paper/commitbert-commit-message-generation-using-1","slug":"commitbert-commit-message-generation-using-1","title":"CommitBERT: Commit Message Generation Using Pre-Trained Programming Language Model","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/controllable-sentence-simplification-with-a","slug":"controllable-sentence-simplification-with-a","title":"Controllable Sentence Simplification with a Unified Text-to-Text Transfer Transformer","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/enslm-ensemble-language-model-for-data","slug":"enslm-ensemble-language-model-for-data","title":"EnsLM: Ensemble Language Model for Data Diversity by Semantic Clustering","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/entity-at-semeval-2021-task-5-weakly","slug":"entity-at-semeval-2021-task-5-weakly","title":"Entity at SemEval-2021 Task 5: Weakly Supervised Token Labelling for Toxic Spans Detection","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/gates-are-not-what-you-need-in-rnns","slug":"gates-are-not-what-you-need-in-rnns","title":"Gates Are Not What You Need in RNNs","date":"2021-08-01","arxiv_id":"2108.00527","repositories_listed":1,"syntology":null},{"url":"/paper/multi-lingual-question-generation-with","slug":"multi-lingual-question-generation-with","title":"Multi-Lingual Question Generation with Language Agnostic Language Model","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"record_sha256":"082a279675e62136db026fdb0a20975af58b46bc598753d5286db42a1ea25bf5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}