{"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/masked-language-modeling/papers/2","list_of":"/task/masked-language-modeling","task":"Masked 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":2,"pages_in_order":5,"rows_per_page":100,"rows":[101,200],"of":475,"counts":{"archive_papers_tagged":475,"with_a_code_link":254,"where_syntology_ran_a_sample":67,"not_listed_spam_title":0,"listed":475,"listed_where_code_ran":67,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":52,"every_run_a_failure_of_syntologys_instrument":15,"listed_with_a_run_with_no_instrument_failure":52,"listed_every_run_a_failure_of_syntologys_instrument":15,"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/masked-language-modeling","prev":"/task/masked-language-modeling","next":"/task/masked-language-modeling/papers/3","papers":[{"url":"/paper/latent-state-models-of-training-dynamics","slug":"latent-state-models-of-training-dynamics","title":"Latent State Models of Training Dynamics","date":"2023-08-18","arxiv_id":"2308.09543","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/latent-state-models-of-training-dynamics#ran","syntology_url":"https://syntology.ai/paper/2308.09543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09543"}},"official":{"repos":["michahu/modeling-training"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/raven-in-context-learning-with-retrieval","slug":"raven-in-context-learning-with-retrieval","title":"RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models","date":"2023-08-15","arxiv_id":"2308.07922","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/raven-in-context-learning-with-retrieval#ran","syntology_url":"https://syntology.ai/paper/2308.07922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07922"}},"official":{"repos":["jeffhj/raven"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/pairing-interacting-protein-sequences-using","slug":"pairing-interacting-protein-sequences-using","title":"Pairing interacting protein sequences using masked language modeling","date":"2023-08-14","arxiv_id":"2308.07136","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/pairing-interacting-protein-sequences-using#ran","syntology_url":"https://syntology.ai/paper/2308.07136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07136"}},"official":{"repos":["bitbol-lab/diffpalm"],"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/predicting-masked-tokens-in-stochastic","slug":"predicting-masked-tokens-in-stochastic","title":"Stochastic positional embeddings improve masked image modeling","date":"2023-07-31","arxiv_id":"2308.00566","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":11,"phrase":"8 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/predicting-masked-tokens-in-stochastic#ran","syntology_url":"https://syntology.ai/paper/2308.00566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.00566"}},"official":{"repos":["amirbar/stop"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/genemask-fast-pretraining-of-gene-sequences","slug":"genemask-fast-pretraining-of-gene-sequences","title":"GeneMask: Fast Pretraining of Gene Sequences to Enable Few-Shot Learning","date":"2023-07-29","arxiv_id":"2307.15933","repositories_listed":1,"syntology":null},{"url":"/paper/masked-latent-semantic-modeling-an-efficient","slug":"masked-latent-semantic-modeling-an-efficient","title":"Masked Latent Semantic Modeling: an Efficient Pre-training Alternative to Masked Language Modeling","date":"2023-07-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/biomedical-language-models-are-robust-to-sub","slug":"biomedical-language-models-are-robust-to-sub","title":"Biomedical Language Models are Robust to Sub-optimal Tokenization","date":"2023-06-30","arxiv_id":"2306.17649","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/biomedical-language-models-are-robust-to-sub#ran","syntology_url":"https://syntology.ai/paper/2306.17649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.17649"}},"official":{"repos":["osu-nlp-group/bio-tokenization"],"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/s2snet-a-pretrained-neural-network-for","slug":"s2snet-a-pretrained-neural-network-for","title":"S2SNet: A Pretrained Neural Network for Superconductivity Discovery","date":"2023-06-28","arxiv_id":"2306.16270","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-image-enhancement-featuring","slug":"personalized-image-enhancement-featuring","title":"Personalized Image Enhancement Featuring Masked Style Modeling","date":"2023-06-15","arxiv_id":"2306.09334","repositories_listed":1,"syntology":null},{"url":"/paper/pushing-the-limits-of-unsupervised-unit","slug":"pushing-the-limits-of-unsupervised-unit","title":"Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation","date":"2023-06-15","arxiv_id":"2306.08920","repositories_listed":1,"syntology":null},{"url":"/paper/generate-to-understand-for-representation","slug":"generate-to-understand-for-representation","title":"Generate to Understand for Representation","date":"2023-06-14","arxiv_id":"2306.10056","repositories_listed":1,"syntology":null},{"url":"/paper/global-and-local-semantic-completion-learning","slug":"global-and-local-semantic-completion-learning","title":"Global and Local Semantic Completion Learning for Vision-Language Pre-training","date":"2023-06-12","arxiv_id":"2306.07096","repositories_listed":1,"syntology":null},{"url":"/paper/contextual-masked-auto-encoder-for-retrieval","slug":"contextual-masked-auto-encoder-for-retrieval","title":"Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems","date":"2023-06-07","arxiv_id":"2306.04357","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-difference-of-bert-style-and-clip","slug":"on-the-difference-of-bert-style-and-clip","title":"On the Difference of BERT-style and CLIP-style Text Encoders","date":"2023-06-06","arxiv_id":"2306.03678","repositories_listed":1,"syntology":null},{"url":"/paper/fair-multilingual-vandalism-detection-system","slug":"fair-multilingual-vandalism-detection-system","title":"Fair multilingual vandalism detection system for Wikipedia","date":"2023-06-02","arxiv_id":"2306.01650","repositories_listed":1,"syntology":null},{"url":"/paper/preserving-pre-trained-features-helps","slug":"preserving-pre-trained-features-helps","title":"Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models","date":"2023-05-30","arxiv_id":"2305.19249","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/preserving-pre-trained-features-helps#ran","syntology_url":"https://syntology.ai/paper/2305.19249","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19249"}},"official":{"repos":["thu-ml/lm-calibration"],"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/adapting-learned-sparse-retrieval-for-long","slug":"adapting-learned-sparse-retrieval-for-long","title":"Adapting Learned Sparse Retrieval for Long Documents","date":"2023-05-29","arxiv_id":"2305.18494","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-masked-language-modeling-for","slug":"rethinking-masked-language-modeling-for","title":"Rethinking Masked Language Modeling for Chinese Spelling Correction","date":"2023-05-28","arxiv_id":"2305.17721","repositories_listed":1,"syntology":null},{"url":"/paper/an-investigation-of-noise-in-morphological","slug":"an-investigation-of-noise-in-morphological","title":"An Investigation of Noise in Morphological Inflection","date":"2023-05-26","arxiv_id":"2305.16581","repositories_listed":1,"syntology":null},{"url":"/paper/honey-i-shrunk-the-language-language-model","slug":"honey-i-shrunk-the-language-language-model","title":"Honey, I Shrunk the Language: Language Model Behavior at Reduced Scale","date":"2023-05-26","arxiv_id":"2305.17266","repositories_listed":1,"syntology":null},{"url":"/paper/masked-and-permuted-implicit-context-learning","slug":"masked-and-permuted-implicit-context-learning","title":"Masked and Permuted Implicit Context Learning for Scene Text Recognition","date":"2023-05-25","arxiv_id":"2305.16172","repositories_listed":1,"syntology":null},{"url":"/paper/self-evolution-learning-for-discriminative","slug":"self-evolution-learning-for-discriminative","title":"Self-Evolution Learning for Discriminative Language Model Pretraining","date":"2023-05-24","arxiv_id":"2305.15275","repositories_listed":1,"syntology":null},{"url":"/paper/axomiyaberta-a-phonologically-aware","slug":"axomiyaberta-a-phonologically-aware","title":"AxomiyaBERTa: A Phonologically-aware Transformer Model for Assamese","date":"2023-05-23","arxiv_id":"2305.13641","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-open-information-extraction-for","slug":"leveraging-open-information-extraction-for","title":"Leveraging Open Information Extraction for More Robust Domain Transfer of Event Trigger Detection","date":"2023-05-23","arxiv_id":"2305.14163","repositories_listed":1,"syntology":null},{"url":"/paper/bidirectional-transformer-reranker-for","slug":"bidirectional-transformer-reranker-for","title":"Bidirectional Transformer Reranker for Grammatical Error Correction","date":"2023-05-22","arxiv_id":"2305.13000","repositories_listed":1,"syntology":null},{"url":"/paper/federated-learning-of-medical-concepts","slug":"federated-learning-of-medical-concepts","title":"Federated Learning of Medical Concepts Embedding using BEHRT","date":"2023-05-22","arxiv_id":"2305.13052","repositories_listed":1,"syntology":null},{"url":"/paper/escoxlm-r-multilingual-taxonomy-driven-pre","slug":"escoxlm-r-multilingual-taxonomy-driven-pre","title":"ESCOXLM-R: Multilingual Taxonomy-driven Pre-training for the Job Market Domain","date":"2023-05-20","arxiv_id":"2305.12092","repositories_listed":1,"syntology":null},{"url":"/paper/how-does-the-task-complexity-of-masked","slug":"how-does-the-task-complexity-of-masked","title":"How does the task complexity of masked pretraining objectives affect downstream performance?","date":"2023-05-18","arxiv_id":"2305.10992","repositories_listed":1,"syntology":null},{"url":"/paper/dinosr-self-distillation-and-online","slug":"dinosr-self-distillation-and-online","title":"DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning","date":"2023-05-17","arxiv_id":"2305.10005","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-improvement-of-factual-knowledge","slug":"unsupervised-improvement-of-factual-knowledge","title":"Unsupervised Improvement of Factual Knowledge in Language Models","date":"2023-04-04","arxiv_id":"2304.01597","repositories_listed":1,"syntology":null},{"url":"/paper/peach-pre-training-sequence-to-sequence","slug":"peach-pre-training-sequence-to-sequence","title":"PEACH: Pre-Training Sequence-to-Sequence Multilingual Models for Translation with Semi-Supervised Pseudo-Parallel Document Generation","date":"2023-04-03","arxiv_id":"2304.01282","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-audible-video-description","slug":"fine-grained-audible-video-description","title":"Fine-grained Audible Video Description","date":"2023-03-27","arxiv_id":"2303.15616","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"7 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; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/fine-grained-audible-video-description#ran","syntology_url":"https://syntology.ai/paper/2303.15616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15616"}},"official":{"repos":["opennlplab/favdbench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/accelerating-vision-language-pretraining-with","slug":"accelerating-vision-language-pretraining-with","title":"Accelerating Vision-Language Pretraining with Free Language Modeling","date":"2023-03-24","arxiv_id":"2303.14038","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-implicit-relation-reasoning-and","slug":"cross-modal-implicit-relation-reasoning-and","title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval","date":"2023-03-22","arxiv_id":"2303.12501","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/cross-modal-implicit-relation-reasoning-and#ran","syntology_url":"https://syntology.ai/paper/2303.12501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12501"}},"official":{"repos":["anosorae/irra"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/structextv2-masked-visual-textual-prediction","slug":"structextv2-masked-visual-textual-prediction","title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","date":"2023-03-01","arxiv_id":"2303.00289","repositories_listed":1,"syntology":null},{"url":"/paper/symbolic-discovery-of-optimization-algorithms-1","slug":"symbolic-discovery-of-optimization-algorithms-1","title":"Symbolic Discovery of Optimization Algorithms","date":"2023-02-13","arxiv_id":"2302.06675","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/symbolic-discovery-of-optimization-algorithms-1#ran","syntology_url":"https://syntology.ai/paper/2302.06675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.06675"}},"official":null}},{"url":"/paper/representation-deficiency-in-masked-language","slug":"representation-deficiency-in-masked-language","title":"Representation Deficiency in Masked Language Modeling","date":"2023-02-04","arxiv_id":"2302.02060","repositories_listed":1,"syntology":null},{"url":"/paper/debiasing-the-cloze-task-in-sequential","slug":"debiasing-the-cloze-task-in-sequential","title":"Debiasing the Cloze Task in Sequential Recommendation with Bidirectional Transformers","date":"2023-01-22","arxiv_id":"2301.09210","repositories_listed":1,"syntology":null},{"url":"/paper/cramming-training-a-language-model-on-a","slug":"cramming-training-a-language-model-on-a","title":"Cramming: Training a Language Model on a Single GPU in One Day","date":"2022-12-28","arxiv_id":"2212.14034","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":2,"n_no_contract":0,"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, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cramming-training-a-language-model-on-a#ran","syntology_url":"https://syntology.ai/paper/2212.14034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14034"}},"official":{"repos":["jonasgeiping/cramming"],"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/microbert-effective-training-of-low-resource","slug":"microbert-effective-training-of-low-resource","title":"MicroBERT: Effective Training of Low-resource Monolingual BERTs through Parameter Reduction and Multitask Learning","date":"2022-12-23","arxiv_id":"2212.12510","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-pre-training-of-masked-language","slug":"efficient-pre-training-of-masked-language","title":"Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking","date":"2022-12-15","arxiv_id":"2212.07617","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":1,"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/efficient-pre-training-of-masked-language#ran","syntology_url":"https://syntology.ai/paper/2212.07617","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.07617"}},"official":{"repos":["koreamglee/concept-based-curriculum-masking"],"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/nonparametric-masked-language-modeling","slug":"nonparametric-masked-language-modeling","title":"Nonparametric Masked Language Modeling","date":"2022-12-02","arxiv_id":"2212.01349","repositories_listed":1,"syntology":null},{"url":"/paper/seeing-what-you-miss-vision-language-pre","slug":"seeing-what-you-miss-vision-language-pre","title":"Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning","date":"2022-11-24","arxiv_id":"2211.13437","repositories_listed":1,"syntology":null},{"url":"/paper/unified-multimodal-model-with-unlikelihood","slug":"unified-multimodal-model-with-unlikelihood","title":"Unified Multimodal Model with Unlikelihood Training for Visual Dialog","date":"2022-11-23","arxiv_id":"2211.13235","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-crisis-related-tweet-classification","slug":"enhancing-crisis-related-tweet-classification","title":"Enhancing Crisis-Related Tweet Classification with Entity-Masked Language Modeling and Multi-Task Learning","date":"2022-11-21","arxiv_id":"2211.11468","repositories_listed":1,"syntology":null},{"url":"/paper/codeeditor-learning-to-edit-source-code-with","slug":"codeeditor-learning-to-edit-source-code-with","title":"CodeEditor: Learning to Edit Source Code with Pre-trained Models","date":"2022-10-31","arxiv_id":"2210.17040","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-label-correlations-in-a-multi","slug":"leveraging-label-correlations-in-a-multi","title":"Leveraging Label Correlations in a Multi-label Setting: A Case Study in Emotion","date":"2022-10-28","arxiv_id":"2210.15842","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-oriented-masking-pre-training","slug":"retrieval-oriented-masking-pre-training","title":"Retrieval Oriented Masking Pre-training Language Model for Dense Passage Retrieval","date":"2022-10-27","arxiv_id":"2210.15133","repositories_listed":1,"syntology":null},{"url":"/paper/towards-unifying-reference-expression","slug":"towards-unifying-reference-expression","title":"Towards Unifying Reference Expression Generation and Comprehension","date":"2022-10-24","arxiv_id":"2210.13076","repositories_listed":1,"syntology":null},{"url":"/paper/generative-prompt-tuning-for-relation-1","slug":"generative-prompt-tuning-for-relation-1","title":"Generative Prompt Tuning for Relation Classification","date":"2022-10-22","arxiv_id":"2210.12435","repositories_listed":1,"syntology":null},{"url":"/paper/informask-unsupervised-informative-masking","slug":"informask-unsupervised-informative-masking","title":"InforMask: Unsupervised Informative Masking for Language Model Pretraining","date":"2022-10-21","arxiv_id":"2210.11771","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/informask-unsupervised-informative-masking#ran","syntology_url":"https://syntology.ai/paper/2210.11771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11771"}},"official":{"repos":["nafissadeq/informask"],"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/plausible-may-not-be-faithful-probing-object","slug":"plausible-may-not-be-faithful-probing-object","title":"Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training","date":"2022-10-14","arxiv_id":"2210.07688","repositories_listed":1,"syntology":null},{"url":"/paper/map-modality-agnostic-uncertainty-aware","slug":"map-modality-agnostic-uncertainty-aware","title":"MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model","date":"2022-10-11","arxiv_id":"2210.05335","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-and-advancing-chinese-natural","slug":"revisiting-and-advancing-chinese-natural","title":"Revisiting and Advancing Chinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-training","date":"2022-10-11","arxiv_id":"2210.05287","repositories_listed":1,"syntology":null},{"url":"/paper/the-effectiveness-of-masked-language-modeling","slug":"the-effectiveness-of-masked-language-modeling","title":"The Effectiveness of Masked Language Modeling and Adapters for Factual Knowledge Injection","date":"2022-10-03","arxiv_id":"2210.00907","repositories_listed":1,"syntology":null},{"url":"/paper/idiapers-causal-news-corpus-2022-efficient","slug":"idiapers-causal-news-corpus-2022-efficient","title":"IDIAPers @ Causal News Corpus 2022: Efficient Causal Relation Identification Through a Prompt-based Few-shot Approach","date":"2022-09-08","arxiv_id":"2209.03895","repositories_listed":1,"syntology":null},{"url":"/paper/transpolymer-a-transformer-based-language","slug":"transpolymer-a-transformer-based-language","title":"TransPolymer: a Transformer-based language model for polymer property predictions","date":"2022-09-03","arxiv_id":"2209.01307","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":0,"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/transpolymer-a-transformer-based-language#ran","syntology_url":"https://syntology.ai/paper/2209.01307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.01307"}},"official":{"repos":["ChangwenXu98/TransPolymer"],"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/learning-better-masking-for-better-language","slug":"learning-better-masking-for-better-language","title":"Learning Better Masking for Better Language Model Pre-training","date":"2022-08-23","arxiv_id":"2208.10806","repositories_listed":1,"syntology":null},{"url":"/paper/grit-vlp-grouped-mini-batch-sampling-for","slug":"grit-vlp-grouped-mini-batch-sampling-for","title":"GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training","date":"2022-08-08","arxiv_id":"2208.04060","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/grit-vlp-grouped-mini-batch-sampling-for#ran","syntology_url":"https://syntology.ai/paper/2208.04060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.04060"}},"official":{"repos":["jaeseokbyun/grit-vlp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-no-1-in-clue-semantic-matching","slug":"towards-no-1-in-clue-semantic-matching","title":"Towards No.1 in CLUE Semantic Matching Challenge: Pre-trained Language Model Erlangshen with Propensity-Corrected Loss","date":"2022-08-05","arxiv_id":"2208.02959","repositories_listed":1,"syntology":null},{"url":"/paper/point-mcbert-a-multi-choice-self-supervised","slug":"point-mcbert-a-multi-choice-self-supervised","title":"Boosting Point-BERT by Multi-choice Tokens","date":"2022-07-27","arxiv_id":"2207.13226","repositories_listed":1,"syntology":null},{"url":"/paper/multilinguals-at-semeval-2022-task-11-complex-1","slug":"multilinguals-at-semeval-2022-task-11-complex-1","title":"Multilinguals at SemEval-2022 Task 11: Complex NER in Semantically Ambiguous Settings for Low Resource Languages","date":"2022-07-14","arxiv_id":"2207.06882","repositories_listed":1,"syntology":null},{"url":"/paper/semmae-semantic-guided-masking-for-learning","slug":"semmae-semantic-guided-masking-for-learning","title":"SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders","date":"2022-06-21","arxiv_id":"2206.10207","repositories_listed":1,"syntology":null},{"url":"/paper/lavender-unifying-video-language","slug":"lavender-unifying-video-language","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","date":"2022-06-14","arxiv_id":"2206.07160","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/lavender-unifying-video-language#ran","syntology_url":"https://syntology.ai/paper/2206.07160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07160"}},"official":{"repos":["microsoft/lavender"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/glipv2-unifying-localization-and-vision","slug":"glipv2-unifying-localization-and-vision","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","date":"2022-06-12","arxiv_id":"2206.05836","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":0,"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/glipv2-unifying-localization-and-vision#ran","syntology_url":"https://syntology.ai/paper/2206.05836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05836"}},"official":{"repos":["microsoft/GLIP"],"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/cross-view-language-modeling-towards-unified","slug":"cross-view-language-modeling-towards-unified","title":"Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training","date":"2022-06-01","arxiv_id":"2206.00621","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":8,"phrase":"6 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cross-view-language-modeling-towards-unified#ran","syntology_url":"https://syntology.ai/paper/2206.00621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.00621"}},"official":{"repos":["zengyan-97/cclm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/training-and-inference-on-any-order","slug":"training-and-inference-on-any-order","title":"Training and Inference on Any-Order Autoregressive Models the Right Way","date":"2022-05-26","arxiv_id":"2205.13554","repositories_listed":1,"syntology":null},{"url":"/paper/transcormer-transformer-for-sentence-scoring","slug":"transcormer-transformer-for-sentence-scoring","title":"Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling","date":"2022-05-25","arxiv_id":"2205.12986","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/transcormer-transformer-for-sentence-scoring#ran","syntology_url":"https://syntology.ai/paper/2205.12986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.12986"}},"official":null}},{"url":"/paper/retromae-pre-training-retrieval-oriented","slug":"retromae-pre-training-retrieval-oriented","title":"RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder","date":"2022-05-24","arxiv_id":"2205.12035","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-normalization-of-temporal","slug":"multilingual-normalization-of-temporal","title":"Multilingual Normalization of Temporal Expressions with Masked Language Models","date":"2022-05-20","arxiv_id":"2205.10399","repositories_listed":1,"syntology":null},{"url":"/paper/towards-unified-prompt-tuning-for-few-shot-1","slug":"towards-unified-prompt-tuning-for-few-shot-1","title":"Towards Unified Prompt Tuning for Few-shot Text Classification","date":"2022-05-11","arxiv_id":"2205.05313","repositories_listed":1,"syntology":null},{"url":"/paper/kecp-knowledge-enhanced-contrastive-prompting","slug":"kecp-knowledge-enhanced-contrastive-prompting","title":"KECP: Knowledge Enhanced Contrastive Prompting for Few-shot Extractive Question Answering","date":"2022-05-06","arxiv_id":"2205.03071","repositories_listed":1,"syntology":null},{"url":"/paper/declaration-based-prompt-tuning-for-visual","slug":"declaration-based-prompt-tuning-for-visual","title":"Declaration-based Prompt Tuning for Visual Question Answering","date":"2022-05-05","arxiv_id":"2205.02456","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-learning-for-prompt-based-few","slug":"contrastive-learning-for-prompt-based-few","title":"Contrastive Learning for Prompt-Based Few-Shot Language Learners","date":"2022-05-03","arxiv_id":"2205.01308","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/contrastive-learning-for-prompt-based-few#ran","syntology_url":"https://syntology.ai/paper/2205.01308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01308"}},"official":{"repos":["yiren-jian/lm-supcon"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/ds-tod-efficient-domain-specialization-for-2","slug":"ds-tod-efficient-domain-specialization-for-2","title":"DS-TOD: Efficient Domain Specialization for Task-Oriented Dialog","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-cross-lingual-natural-language","slug":"enhancing-cross-lingual-natural-language","title":"Enhancing Cross-lingual Natural Language Inference by Prompt-learning from Cross-lingual Templates","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-dependency-graph-network-1","slug":"unsupervised-dependency-graph-network-1","title":"Unsupervised Dependency Graph Network","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-comprehensive-understanding-of-code-mixed","slug":"a-comprehensive-understanding-of-code-mixed","title":"A Comprehensive Understanding of Code-mixed Language Semantics using Hierarchical Transformer","date":"2022-04-27","arxiv_id":"2204.12753","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-representation-learning-of-2","slug":"unsupervised-representation-learning-of-2","title":"Unsupervised Representation Learning of Player Behavioral Data with Confidence Guided Masking","date":"2022-04-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/text-revision-by-on-the-fly-representation","slug":"text-revision-by-on-the-fly-representation","title":"Text Revision by On-the-Fly Representation Optimization","date":"2022-04-15","arxiv_id":"2204.07359","repositories_listed":1,"syntology":null},{"url":"/paper/generative-power-of-a-protein-language-model","slug":"generative-power-of-a-protein-language-model","title":"Generative power of a protein language model trained on multiple sequence alignments","date":"2022-04-14","arxiv_id":"2204.07110","repositories_listed":1,"syntology":null},{"url":"/paper/what-language-model-architecture-and","slug":"what-language-model-architecture-and","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","date":"2022-04-12","arxiv_id":"2204.05832","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/what-language-model-architecture-and#ran","syntology_url":"https://syntology.ai/paper/2204.05832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.05832"}},"official":{"repos":["bigscience-workshop/architecture-objective"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/data-augmentation-for-biomedical-factoid-1","slug":"data-augmentation-for-biomedical-factoid-1","title":"Data Augmentation for Biomedical Factoid Question Answering","date":"2022-04-10","arxiv_id":"2204.04711","repositories_listed":1,"syntology":null},{"url":"/paper/contextual-representation-learning-beyond-1","slug":"contextual-representation-learning-beyond-1","title":"Contextual Representation Learning beyond Masked Language Modeling","date":"2022-04-08","arxiv_id":"2204.04163","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-for-text-analytic-in","slug":"language-model-for-text-analytic-in","title":"SecureBERT: A Domain-Specific Language Model for Cybersecurity","date":"2022-04-06","arxiv_id":"2204.02685","repositories_listed":1,"syntology":null},{"url":"/paper/pos-bert-point-cloud-one-stage-bert-pre","slug":"pos-bert-point-cloud-one-stage-bert-pre","title":"POS-BERT: Point Cloud One-Stage BERT Pre-Training","date":"2022-04-03","arxiv_id":"2204.00989","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-transformer-decoder-for-end-to","slug":"pre-training-transformer-decoder-for-end-to","title":"Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data","date":"2022-03-31","arxiv_id":"2203.17113","repositories_listed":1,"syntology":null},{"url":"/paper/linkbert-pretraining-language-models-with","slug":"linkbert-pretraining-language-models-with","title":"LinkBERT: Pretraining Language Models with Document Links","date":"2022-03-29","arxiv_id":"2203.15827","repositories_listed":1,"syntology":{"n":14,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"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) · 11 unverified","sample_list":"/paper/linkbert-pretraining-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2203.15827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15827"}},"official":{"repos":["michiyasunaga/LinkBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/can-unsupervised-knowledge-transfer-from","slug":"can-unsupervised-knowledge-transfer-from","title":"Can Unsupervised Knowledge Transfer from Social Discussions Help Argument Mining?","date":"2022-03-24","arxiv_id":"2203.12881","repositories_listed":1,"syntology":null},{"url":"/paper/what-to-hide-from-your-students-attention","slug":"what-to-hide-from-your-students-attention","title":"What to Hide from Your Students: Attention-Guided Masked Image Modeling","date":"2022-03-23","arxiv_id":"2203.12719","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/what-to-hide-from-your-students-attention#ran","syntology_url":"https://syntology.ai/paper/2203.12719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12719"}},"official":{"repos":["gkakogeorgiou/attmask"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hop-history-and-order-aware-pre-training-for","slug":"hop-history-and-order-aware-pre-training-for","title":"HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation","date":"2022-03-22","arxiv_id":"2203.11591","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hop-history-and-order-aware-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/2203.11591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11591"}},"official":{"repos":["yanyuanqiao/hop-vln"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/how-does-the-pre-training-objective-affect-1","slug":"how-does-the-pre-training-objective-affect-1","title":"How does the pre-training objective affect what large language models learn about linguistic properties?","date":"2022-03-20","arxiv_id":"2203.10415","repositories_listed":1,"syntology":null},{"url":"/paper/geographic-adaptation-of-pretrained-language","slug":"geographic-adaptation-of-pretrained-language","title":"Geographic Adaptation of Pretrained Language Models","date":"2022-03-16","arxiv_id":"2203.08565","repositories_listed":1,"syntology":null},{"url":"/paper/probing-bert-s-priors-with-serial","slug":"probing-bert-s-priors-with-serial","title":"Probing BERT's priors with serial reproduction chains","date":"2022-02-24","arxiv_id":"2202.12226","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/probing-bert-s-priors-with-serial#ran","syntology_url":"https://syntology.ai/paper/2202.12226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.12226"}},"official":{"repos":["taka-yamakoshi/telephonegame"],"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/should-you-mask-15-in-masked-language","slug":"should-you-mask-15-in-masked-language","title":"Should You Mask 15% in Masked Language Modeling?","date":"2022-02-16","arxiv_id":"2202.08005","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":1,"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/should-you-mask-15-in-masked-language#ran","syntology_url":"https://syntology.ai/paper/2202.08005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.08005"}},"official":{"repos":["princeton-nlp/dinkytrain"],"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/self-supervised-representation-learning-for-8","slug":"self-supervised-representation-learning-for-8","title":"Self-Supervised Representation Learning for Speech Using Visual Grounding and Masked Language Modeling","date":"2022-02-07","arxiv_id":"2202.03543","repositories_listed":1,"syntology":null},{"url":"/paper/mvp-multi-stage-vision-language-pre-training","slug":"mvp-multi-stage-vision-language-pre-training","title":"MVPTR: Multi-Level Semantic Alignment for Vision-Language Pre-Training via Multi-Stage Learning","date":"2022-01-29","arxiv_id":"2201.12596","repositories_listed":1,"syntology":null},{"url":"/paper/eliciting-knowledge-from-pretrained-language","slug":"eliciting-knowledge-from-pretrained-language","title":"Eliciting Knowledge from Pretrained Language Models for Prototypical Prompt Verbalizer","date":"2022-01-14","arxiv_id":"2201.05411","repositories_listed":1,"syntology":null},{"url":"/paper/causal-distillation-for-language-models","slug":"causal-distillation-for-language-models","title":"Causal Distillation for Language Models","date":"2021-12-05","arxiv_id":"2112.02505","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":0,"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/causal-distillation-for-language-models#ran","syntology_url":"https://syntology.ai/paper/2112.02505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.02505"}},"official":{"repos":["frankaging/Causal-Distill"],"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/dibert-dependency-injected-bidirectional","slug":"dibert-dependency-injected-bidirectional","title":"DIBERT: Dependency Injected Bidirectional Encoder Representations from Transformers","date":"2021-12-05","arxiv_id":null,"repositories_listed":1,"syntology":null}],"record_sha256":"ea1edb0655d2a1cb3c9890f43e5fc042a18856456d4993609dda835851518e08","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}