{"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-modelling/papers/61","list_of":"/task/language-modelling","task":"Language Modelling","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":61,"pages_in_order":177,"rows_per_page":100,"rows":[6001,6100],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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-modelling","prev":"/task/language-modelling/papers/60","next":"/task/language-modelling/papers/62","papers":[{"url":"/paper/semantic-based-self-critical-training-for","slug":"semantic-based-self-critical-training-for","title":"Semantic-Based Self-Critical Training For Question Generation","date":"2021-08-26","arxiv_id":"2108.12026","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/one-chatbot-per-person-creating-personalized","slug":"one-chatbot-per-person-creating-personalized","title":"One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profiles","date":"2021-08-20","arxiv_id":"2108.09355","repositories_listed":1,"syntology":null},{"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/deriving-disinformation-insights-from","slug":"deriving-disinformation-insights-from","title":"Deriving Disinformation Insights from Geolocalized Twitter Callouts","date":"2021-08-06","arxiv_id":"2108.03067","repositories_listed":1,"syntology":null},{"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/emlm-a-new-pre-training-objective-for-emotion","slug":"emlm-a-new-pre-training-objective-for-emotion","title":"eMLM: A New Pre-training Objective for Emotion Related Tasks","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},{"url":"/paper/plome-pre-training-with-misspelled-knowledge","slug":"plome-pre-training-with-misspelled-knowledge","title":"PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/protaugment-intent-detection-meta-learning","slug":"protaugment-intent-detection-meta-learning","title":"ProtAugment: Intent Detection Meta-Learning through Unsupervised Diverse Paraphrasing","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/text-in-context-token-level-error-detection","slug":"text-in-context-token-level-error-detection","title":"Text-in-Context: Token-Level Error Detection for Table-to-Text Generation","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/time-efficient-code-completion-model-for-the","slug":"time-efficient-code-completion-model-for-the","title":"Time-Efficient Code Completion Model for the R Programming Language","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/structural-guidance-for-transformer-language","slug":"structural-guidance-for-transformer-language","title":"Structural Guidance for Transformer Language Models","date":"2021-07-30","arxiv_id":"2108.00104","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/structural-guidance-for-transformer-language#ran","syntology_url":"https://syntology.ai/paper/2108.00104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.00104"}},"official":{"repos":["IBM/transformers-struct-guidance"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/goal-oriented-script-construction","slug":"goal-oriented-script-construction","title":"Goal-Oriented Script Construction","date":"2021-07-28","arxiv_id":"2107.13189","repositories_listed":1,"syntology":null},{"url":"/paper/mwp-bert-a-strong-baseline-for-math-word","slug":"mwp-bert-a-strong-baseline-for-math-word","title":"MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving","date":"2021-07-28","arxiv_id":"2107.13435","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 2 unverified","sample_list":"/paper/mwp-bert-a-strong-baseline-for-math-word#ran","syntology_url":"https://syntology.ai/paper/2107.13435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.13435"}},"official":{"repos":["lzhenwen/mwp-bert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/pre-train-prompt-and-predict-a-systematic","slug":"pre-train-prompt-and-predict-a-systematic","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","date":"2021-07-28","arxiv_id":"2107.13586","repositories_listed":1,"syntology":null},{"url":"/paper/gabert-an-irish-language-model","slug":"gabert-an-irish-language-model","title":"gaBERT -- an Irish Language Model","date":"2021-07-27","arxiv_id":"2107.12930","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-emotion-prediction-by-modeling","slug":"fine-grained-emotion-prediction-by-modeling","title":"Fine-Grained Emotion Prediction by Modeling Emotion Definitions","date":"2021-07-26","arxiv_id":"2107.12135","repositories_listed":1,"syntology":null},{"url":"/paper/brazilian-portuguese-speech-recognition-using","slug":"brazilian-portuguese-speech-recognition-using","title":"Brazilian Portuguese Speech Recognition Using Wav2vec 2.0","date":"2021-07-23","arxiv_id":"2107.11414","repositories_listed":1,"syntology":null},{"url":"/paper/fnetar-mixing-tokens-with-autoregressive","slug":"fnetar-mixing-tokens-with-autoregressive","title":"FNetAR: Mixing Tokens with Autoregressive Fourier Transforms","date":"2021-07-22","arxiv_id":"2107.10932","repositories_listed":1,"syntology":null},{"url":"/paper/human-in-the-loop-for-data-collection-a-multi","slug":"human-in-the-loop-for-data-collection-a-multi","title":"Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech","date":"2021-07-19","arxiv_id":"2107.08720","repositories_listed":1,"syntology":null},{"url":"/paper/darmok-and-jalad-at-tanagra-a-dataset-and","slug":"darmok-and-jalad-at-tanagra-a-dataset-and","title":"Picard understanding Darmok: A Dataset and Model for Metaphor-Rich Translation in a Constructed Language","date":"2021-07-16","arxiv_id":"2107.08146","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-contrastive-learning-with","slug":"self-supervised-contrastive-learning-with","title":"Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based Attacks","date":"2021-07-15","arxiv_id":"2107.07610","repositories_listed":1,"syntology":null},{"url":"/paper/turning-tables-generating-examples-from-semi","slug":"turning-tables-generating-examples-from-semi","title":"Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills","date":"2021-07-15","arxiv_id":"2107.07261","repositories_listed":1,"syntology":null},{"url":"/paper/a-note-on-learning-rare-events-in-molecular","slug":"a-note-on-learning-rare-events-in-molecular","title":"A Note on Learning Rare Events in Molecular Dynamics using LSTM and Transformer","date":"2021-07-14","arxiv_id":"2107.06573","repositories_listed":1,"syntology":null},{"url":"/paper/from-machine-translation-to-code-switching","slug":"from-machine-translation-to-code-switching","title":"From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text","date":"2021-07-14","arxiv_id":"2107.06483","repositories_listed":1,"syntology":null},{"url":"/paper/zr-2021vg-zero-resource-speech-challenge","slug":"zr-2021vg-zero-resource-speech-challenge","title":"ZR-2021VG: Zero-Resource Speech Challenge, Visually-Grounded Language Modelling track, 2021 edition","date":"2021-07-14","arxiv_id":"2107.06546","repositories_listed":1,"syntology":null},{"url":"/paper/codified-audio-language-modeling-learns","slug":"codified-audio-language-modeling-learns","title":"Codified audio language modeling learns useful representations for music information retrieval","date":"2021-07-12","arxiv_id":"2107.05677","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/codified-audio-language-modeling-learns#ran","syntology_url":"https://syntology.ai/paper/2107.05677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.05677"}},"official":{"repos":["p-lambda/jukemir"],"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/midibert-piano-large-scale-pre-training-for","slug":"midibert-piano-large-scale-pre-training-for","title":"BERT-like Pre-training for Symbolic Piano Music Classification Tasks","date":"2021-07-12","arxiv_id":"2107.05223","repositories_listed":1,"syntology":null},{"url":"/paper/moocrep-a-unified-pre-trained-embedding-of","slug":"moocrep-a-unified-pre-trained-embedding-of","title":"MOOCRep: A Unified Pre-trained Embedding of MOOC Entities","date":"2021-07-12","arxiv_id":"2107.05154","repositories_listed":1,"syntology":null},{"url":"/paper/inspiration-through-observation-demonstrating","slug":"inspiration-through-observation-demonstrating","title":"Inspiration through Observation: Demonstrating the Influence of Automatically Generated Text on Creative Writing","date":"2021-07-08","arxiv_id":"2107.04007","repositories_listed":1,"syntology":null},{"url":"/paper/differentiable-random-access-memory-using","slug":"differentiable-random-access-memory-using","title":"Differentiable Random Access Memory using Lattices","date":"2021-07-07","arxiv_id":"2107.03474","repositories_listed":1,"syntology":null},{"url":"/paper/vidlankd-improving-language-understanding-via","slug":"vidlankd-improving-language-understanding-via","title":"VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer","date":"2021-07-06","arxiv_id":"2107.02681","repositories_listed":1,"syntology":null},{"url":"/paper/deeprapper-neural-rap-generation-with-rhyme","slug":"deeprapper-neural-rap-generation-with-rhyme","title":"DeepRapper: Neural Rap Generation with Rhyme and Rhythm Modeling","date":"2021-07-05","arxiv_id":"2107.01875","repositories_listed":1,"syntology":null},{"url":"/paper/robust-end-to-end-offline-chinese-handwriting","slug":"robust-end-to-end-offline-chinese-handwriting","title":"Robust End-to-End Offline Chinese Handwriting Text Page Spotter with Text Kernel","date":"2021-07-04","arxiv_id":"2107.01547","repositories_listed":1,"syntology":null},{"url":"/paper/r2d2-recursive-transformer-based-on","slug":"r2d2-recursive-transformer-based-on","title":"R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling","date":"2021-07-02","arxiv_id":"2107.00967","repositories_listed":1,"syntology":null},{"url":"/paper/stabilizing-equilibrium-models-by-jacobian","slug":"stabilizing-equilibrium-models-by-jacobian","title":"Stabilizing Equilibrium Models by Jacobian Regularization","date":"2021-06-28","arxiv_id":"2106.14342","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":1,"phrase":"0 ran · 3 unverified","sample_list":"/paper/stabilizing-equilibrium-models-by-jacobian#ran","syntology_url":"https://syntology.ai/paper/2106.14342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14342"}},"official":{"repos":["locuslab/deq"],"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/combining-analogy-with-language-models-for","slug":"combining-analogy-with-language-models-for","title":"Combining Analogy with Language Models for Knowledge Extraction","date":"2021-06-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-task-oriented-dialog-modeling-with","slug":"end-to-end-task-oriented-dialog-modeling-with","title":"End-to-End Task-Oriented Dialog Modeling with Semi-Structured Knowledge Management","date":"2021-06-22","arxiv_id":"2106.11796","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-tuning-or-fine-tuning-investigating","slug":"prompt-tuning-or-fine-tuning-investigating","title":"Prompt Tuning or Fine-Tuning - Investigating Relational Knowledge in Pre-Trained Language Models","date":"2021-06-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/clip2video-mastering-video-text-retrieval-via","slug":"clip2video-mastering-video-text-retrieval-via","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","date":"2021-06-21","arxiv_id":"2106.11097","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/clip2video-mastering-video-text-retrieval-via#ran","syntology_url":"https://syntology.ai/paper/2106.11097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11097"}},"official":{"repos":["CryhanFang/CLIP2Video"],"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/a-brief-study-on-the-effects-of-training","slug":"a-brief-study-on-the-effects-of-training","title":"A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss","date":"2021-06-20","arxiv_id":"2106.10619","repositories_listed":1,"syntology":null},{"url":"/paper/rstnet-captioning-with-adaptive-attention-on","slug":"rstnet-captioning-with-adaptive-attention-on","title":"RSTNet: Captioning With Adaptive Attention on Visual and Non-Visual Words","date":"2021-06-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/spbert-pre-training-bert-on-sparql-queries","slug":"spbert-pre-training-bert-on-sparql-queries","title":"SPBERT: An Efficient Pre-training BERT on SPARQL Queries for Question Answering over Knowledge Graphs","date":"2021-06-18","arxiv_id":"2106.09997","repositories_listed":1,"syntology":null},{"url":"/paper/on-anytime-learning-at-macroscale","slug":"on-anytime-learning-at-macroscale","title":"On Anytime Learning at Macroscale","date":"2021-06-17","arxiv_id":"2106.09563","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"4 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/on-anytime-learning-at-macroscale#ran","syntology_url":"https://syntology.ai/paper/2106.09563","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09563"}},"official":{"repos":["facebookresearch/alma"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/discrete-auto-regressive-variational","slug":"discrete-auto-regressive-variational","title":"Discrete Auto-regressive Variational Attention Models for Text Modeling","date":"2021-06-16","arxiv_id":"2106.08571","repositories_listed":1,"syntology":null},{"url":"/paper/bilateral-personalized-dialogue-generation","slug":"bilateral-personalized-dialogue-generation","title":"Bilateral Personalized Dialogue Generation with Contrastive Learning","date":"2021-06-15","arxiv_id":"2106.07857","repositories_listed":1,"syntology":null},{"url":"/paper/direction-is-what-you-need-improving-word","slug":"direction-is-what-you-need-improving-word","title":"Direction is what you need: Improving Word Embedding Compression in Large Language Models","date":"2021-06-15","arxiv_id":"2106.08181","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/direction-is-what-you-need-improving-word#ran","syntology_url":"https://syntology.ai/paper/2106.08181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08181"}},"official":{"repos":["MohammadrezaBanaei/orientation_based_embedding_compression"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sas-self-augmented-strategy-for-language","slug":"sas-self-augmented-strategy-for-language","title":"SAS: Self-Augmentation Strategy for Language Model Pre-training","date":"2021-06-14","arxiv_id":"2106.07176","repositories_listed":1,"syntology":null},{"url":"/paper/incorporating-external-pos-tagger-for","slug":"incorporating-external-pos-tagger-for","title":"Incorporating External POS Tagger for Punctuation Restoration","date":"2021-06-12","arxiv_id":"2106.06731","repositories_listed":1,"syntology":null},{"url":"/paper/bioelectra-pretrained-biomedical-text-encoder","slug":"bioelectra-pretrained-biomedical-text-encoder","title":"BioELECTRA:Pretrained Biomedical text Encoder using Discriminators","date":"2021-06-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/generate-annotate-and-learn-generative-models","slug":"generate-annotate-and-learn-generative-models","title":"Generate, Annotate, and Learn: NLP with Synthetic Text","date":"2021-06-11","arxiv_id":"2106.06168","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/generate-annotate-and-learn-generative-models#ran","syntology_url":"https://syntology.ai/paper/2106.06168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06168"}},"official":{"repos":["xlhex/gal_syntex"],"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","unlocated"]}}},{"url":"/paper/improving-pretrained-cross-lingual-language","slug":"improving-pretrained-cross-lingual-language","title":"Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment","date":"2021-06-11","arxiv_id":"2106.06381","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-pretrained-cross-lingual-language#ran","syntology_url":"https://syntology.ai/paper/2106.06381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06381"}},"official":{"repos":["CZWin32768/XLM-Align"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/convolutions-and-self-attention-re","slug":"convolutions-and-self-attention-re","title":"Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models","date":"2021-06-10","arxiv_id":"2106.05505","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-unsupervised-pretraining-objectives","slug":"exploring-unsupervised-pretraining-objectives","title":"Exploring Unsupervised Pretraining Objectives for Machine Translation","date":"2021-06-10","arxiv_id":"2106.05634","repositories_listed":1,"syntology":null},{"url":"/paper/auto-tagging-of-short-conversational-1","slug":"auto-tagging-of-short-conversational-1","title":"Auto-tagging of Short Conversational Sentences using Natural Language Processing Methods","date":"2021-06-09","arxiv_id":"2106.04959","repositories_listed":1,"syntology":null},{"url":"/paper/interpretable-and-low-resource-entity","slug":"interpretable-and-low-resource-entity","title":"Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making","date":"2021-06-08","arxiv_id":"2106.04174","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/interpretable-and-low-resource-entity#ran","syntology_url":"https://syntology.ai/paper/2106.04174","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04174"}},"official":{"repos":["THU-KEG/HIF-KAT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/parameter-efficient-multi-task-fine-tuning","slug":"parameter-efficient-multi-task-fine-tuning","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","date":"2021-06-08","arxiv_id":"2106.04489","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/parameter-efficient-multi-task-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2106.04489","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04489"}},"official":{"repos":["rabeehk/hyperformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/staircase-attention-for-recurrent-processing","slug":"staircase-attention-for-recurrent-processing","title":"Staircase Attention for Recurrent Processing of Sequences","date":"2021-06-08","arxiv_id":"2106.04279","repositories_listed":1,"syntology":null},{"url":"/paper/ultra-fine-entity-typing-with-weak","slug":"ultra-fine-entity-typing-with-weak","title":"Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model","date":"2021-06-08","arxiv_id":"2106.04098","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-language-relatedness-for-low-web","slug":"exploiting-language-relatedness-for-low-web","title":"Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study","date":"2021-06-07","arxiv_id":"2106.03958","repositories_listed":1,"syntology":null},{"url":"/paper/generating-hypothetical-events-for-abductive","slug":"generating-hypothetical-events-for-abductive","title":"Generating Hypothetical Events for Abductive Inference","date":"2021-06-07","arxiv_id":"2106.03973","repositories_listed":1,"syntology":null},{"url":"/paper/a-targeted-assessment-of-incremental","slug":"a-targeted-assessment-of-incremental","title":"A Targeted Assessment of Incremental Processing in Neural LanguageModels and Humans","date":"2021-06-06","arxiv_id":"2106.03232","repositories_listed":1,"syntology":null},{"url":"/paper/bertnesia-investigating-the-capture-and-1","slug":"bertnesia-investigating-the-capture-and-1","title":"BERTnesia: Investigating the capture and forgetting of knowledge in BERT","date":"2021-06-05","arxiv_id":"2106.02902","repositories_listed":1,"syntology":null},{"url":"/paper/clip-a-dataset-for-extracting-action-items","slug":"clip-a-dataset-for-extracting-action-items","title":"CLIP: A Dataset for Extracting Action Items for Physicians from Hospital Discharge Notes","date":"2021-06-04","arxiv_id":"2106.02524","repositories_listed":1,"syntology":null},{"url":"/paper/enabling-lightweight-fine-tuning-for-pre","slug":"enabling-lightweight-fine-tuning-for-pre","title":"Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators","date":"2021-06-04","arxiv_id":"2106.02205","repositories_listed":1,"syntology":null},{"url":"/paper/bilingual-alignment-pre-training-for-zero","slug":"bilingual-alignment-pre-training-for-zero","title":"Bilingual Alignment Pre-Training for Zero-Shot Cross-Lingual Transfer","date":"2021-06-03","arxiv_id":"2106.01732","repositories_listed":1,"syntology":null},{"url":"/paper/dissecting-generation-modes-for-abstractive","slug":"dissecting-generation-modes-for-abstractive","title":"Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution","date":"2021-06-03","arxiv_id":"2106.01518","repositories_listed":1,"syntology":null},{"url":"/paper/mpc-bert-a-pre-trained-language-model-for","slug":"mpc-bert-a-pre-trained-language-model-for","title":"MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding","date":"2021-06-03","arxiv_id":"2106.01541","repositories_listed":1,"syntology":null},{"url":"/paper/provably-secure-generative-linguistic","slug":"provably-secure-generative-linguistic","title":"Provably Secure Generative Linguistic Steganography","date":"2021-06-03","arxiv_id":"2106.02011","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/provably-secure-generative-linguistic#ran","syntology_url":"https://syntology.ai/paper/2106.02011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02011"}},"official":{"repos":["Mhzzzzz/ADG-steganography"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/template-based-named-entity-recognition-using","slug":"template-based-named-entity-recognition-using","title":"Template-Based Named Entity Recognition Using BART","date":"2021-06-03","arxiv_id":"2106.01760","repositories_listed":1,"syntology":null},{"url":"/paper/a-generalizable-approach-to-learning","slug":"a-generalizable-approach-to-learning","title":"A Generalizable Approach to Learning Optimizers","date":"2021-06-02","arxiv_id":"2106.00958","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-generalizable-approach-to-learning#ran","syntology_url":"https://syntology.ai/paper/2106.00958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.00958"}},"official":{"repos":["openai/LHOPT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/attention-based-contextual-language-model","slug":"attention-based-contextual-language-model","title":"Attention-based Contextual Language Model Adaptation for Speech Recognition","date":"2021-06-02","arxiv_id":"2106.01451","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 2 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) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/attention-based-contextual-language-model#ran","syntology_url":"https://syntology.ai/paper/2106.01451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01451"}},"official":{"repos":["amazon-research/contextual-attention-nlm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-speech-recognition-in-sanskrit-a","slug":"automatic-speech-recognition-in-sanskrit-a","title":"Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights","date":"2021-06-02","arxiv_id":"2106.05852","repositories_listed":1,"syntology":null},{"url":"/paper/bert-defense-a-probabilistic-model-based-on","slug":"bert-defense-a-probabilistic-model-based-on","title":"BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attacks","date":"2021-06-02","arxiv_id":"2106.01452","repositories_listed":1,"syntology":null},{"url":"/paper/differential-privacy-for-text-analytics-via","slug":"differential-privacy-for-text-analytics-via","title":"Differential Privacy for Text Analytics via Natural Text Sanitization","date":"2021-06-02","arxiv_id":"2106.01221","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/differential-privacy-for-text-analytics-via#ran","syntology_url":"https://syntology.ai/paper/2106.01221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01221"}},"official":{"repos":["xiangyue9607/SanText"],"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/lower-perplexity-is-not-always-human-like","slug":"lower-perplexity-is-not-always-human-like","title":"Lower Perplexity is Not Always Human-Like","date":"2021-06-02","arxiv_id":"2106.01229","repositories_listed":1,"syntology":null},{"url":"/paper/mathbert-a-pre-trained-language-model-for","slug":"mathbert-a-pre-trained-language-model-for","title":"MathBERT: A Pre-trained Language Model for General NLP Tasks in Mathematics Education","date":"2021-06-02","arxiv_id":"2106.07340","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"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) · 3 unverified","sample_list":"/paper/mathbert-a-pre-trained-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2106.07340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07340"}},"official":{"repos":["tbs17/MathBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}}],"record_sha256":"a3063a1541a49fd3302da34aacbefd097732b9cced192d3cb83fd9589fd7716d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}