{"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":"/method/attention-dropout/papers/71","list_of":"/method/attention-dropout","method":"Attention Dropout","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":71,"pages_in_order":109,"rows_per_page":100,"rows":[7001,7100],"of":10892,"counts":{"archive_papers_tagged":10892,"with_a_code_link":4634,"where_syntology_ran_a_sample":1270,"not_listed_spam_title":0,"listed":10892,"listed_where_code_ran":1270,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1043,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1043,"listed_every_run_a_failure_of_syntologys_instrument":227,"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":"/method/attention-dropout","prev":"/method/attention-dropout/papers/70","next":"/method/attention-dropout/papers/72","papers":[{"paper":"/paper/dependency-based-mixture-language-models","slug":"dependency-based-mixture-language-models","title":"Dependency-based Mixture Language Models","date":"2022-03-19","arxiv_id":"2203.10256","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["fadedcosine/dependency-guided-neural-text-generation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/perturbations-in-the-wild-leveraging-human-1","slug":"perturbations-in-the-wild-leveraging-human-1","title":"Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense","date":"2022-03-19","arxiv_id":"2203.10346","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lethaiq/perturbations-in-the-wild"],"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"]}}},{"paper":null,"slug":"are-you-robert-or-roberta-deceiving-online","title":"Are You Robert or RoBERTa? Deceiving Online Authorship Attribution Models Using Neural Text Generators","date":"2022-03-18","arxiv_id":"2203.09813","n_code_links":0,"syntology":null},{"paper":"/paper/coloring-the-blank-slate-pre-training-imparts-1","slug":"coloring-the-blank-slate-pre-training-imparts-1","title":"Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models","date":"2022-03-17","arxiv_id":"2203.09397","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sebschu/multilingual-transformations"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/entropy-based-attention-regularization-frees","slug":"entropy-based-attention-regularization-frees","title":"Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists","date":"2022-03-17","arxiv_id":"2203.09192","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["g8a9/ear"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/fine-and-coarse-granularity-hybrid-self","slug":"fine-and-coarse-granularity-hybrid-self","title":"Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT","date":"2022-03-17","arxiv_id":"2203.09055","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-detection-of-personal-employment","slug":"multilingual-detection-of-personal-employment","title":"Multilingual Detection of Personal Employment Status on Twitter","date":"2022-03-17","arxiv_id":"2203.09178","n_code_links":1,"syntology":null},{"paper":"/paper/adapler-speeding-up-inference-by-adaptive-1","slug":"adapler-speeding-up-inference-by-adaptive-1","title":"AdapLeR: Speeding up Inference by Adaptive Length Reduction","date":"2022-03-16","arxiv_id":"2203.08991","n_code_links":1,"syntology":null},{"paper":"/paper/kinyabert-a-morphology-aware-kinyarwanda-1","slug":"kinyabert-a-morphology-aware-kinyarwanda-1","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","date":"2022-03-16","arxiv_id":"2203.08459","n_code_links":1,"syntology":{"ran":6,"of":12,"n_ran_checked":2,"n_instrument":4,"unverified":6,"pointer_only":0,"phrase":"6 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; 4 where Syntology's instrument failed) · 6 unverified","official":{"repos":["anzeyimana/kinyabert-acl2022"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/label-semantics-for-few-shot-named-entity","slug":"label-semantics-for-few-shot-named-entity","title":"Label Semantics for Few Shot Named Entity Recognition","date":"2022-03-16","arxiv_id":"2203.08985","n_code_links":1,"syntology":null},{"paper":"/paper/thinking-about-gpt-3-in-context-learning-for","slug":"thinking-about-gpt-3-in-context-learning-for","title":"Thinking about GPT-3 In-Context Learning for Biomedical IE? Think Again","date":"2022-03-16","arxiv_id":"2203.08410","n_code_links":1,"syntology":null},{"paper":"/paper/data-contamination-from-memorization-to-1","slug":"data-contamination-from-memorization-to-1","title":"Data Contamination: From Memorization to Exploitation","date":"2022-03-15","arxiv_id":"2203.08242","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["schwartz-lab-nlp/data_contamination"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/do-berts-learn-to-use-browser-user-interface-1","slug":"do-berts-learn-to-use-browser-user-interface-1","title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs","date":"2022-03-15","arxiv_id":"2203.07828","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["Alab-NII/bertbui_pub"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/do-language-models-plagiarize","slug":"do-language-models-plagiarize","title":"Do Language Models Plagiarize?","date":"2022-03-15","arxiv_id":"2203.07618","n_code_links":1,"syntology":null},{"paper":"/paper/imputing-out-of-vocabulary-embeddings-with","slug":"imputing-out-of-vocabulary-embeddings-with","title":"Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost","date":"2022-03-15","arxiv_id":"2203.07860","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tigerchen52/love"],"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":["found_in_text","official"]}}},{"paper":null,"slug":"the-ghost-in-the-machine-has-an-american","title":"The Ghost in the Machine has an American accent: value conflict in GPT-3","date":"2022-03-15","arxiv_id":"2203.07785","n_code_links":0,"syntology":null},{"paper":"/paper/unified-visual-transformer-compression-1","slug":"unified-visual-transformer-compression-1","title":"Unified Visual Transformer Compression","date":"2022-03-15","arxiv_id":"2203.08243","n_code_links":1,"syntology":{"ran":9,"of":16,"n_ran_checked":6,"n_instrument":3,"unverified":7,"pointer_only":3,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","official":{"repos":["VITA-Group/UVC"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"can-pre-trained-transformers-be-used-in","title":"Can pre-trained Transformers be used in detecting complex sensitive sentences? -- A Monsanto case study","date":"2022-03-14","arxiv_id":"2203.06793","n_code_links":0,"syntology":null},{"paper":null,"slug":"contrastive-visual-semantic-pretraining","title":"Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations","date":"2022-03-14","arxiv_id":"2203.07511","n_code_links":0,"syntology":null},{"paper":"/paper/grips-gradient-free-edit-based-instruction","slug":"grips-gradient-free-edit-based-instruction","title":"GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models","date":"2022-03-14","arxiv_id":"2203.07281","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["archiki/grips"],"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":["listed","official"]}}},{"paper":"/paper/the-optimal-bert-surgeon-scalable-and","slug":"the-optimal-bert-surgeon-scalable-and","title":"The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models","date":"2022-03-14","arxiv_id":"2203.07259","n_code_links":1,"syntology":null},{"paper":"/paper/vast-the-valence-assessing-semantics-test-for","slug":"vast-the-valence-assessing-semantics-test-for","title":"VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models","date":"2022-03-14","arxiv_id":"2203.07504","n_code_links":1,"syntology":null},{"paper":null,"slug":"wcl-bbcd-a-contrastive-learning-and-knowledge","title":"WCL-BBCD: A Contrastive Learning and Knowledge Graph Approach to Named Entity Recognition","date":"2022-03-14","arxiv_id":"2203.06925","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-impact-of-covid-19-on","title":"Investigating the Impact of COVID-19 on Education by Social Network Mining","date":"2022-03-13","arxiv_id":"2203.06584","n_code_links":0,"syntology":null},{"paper":"/paper/bibert-accurate-fully-binarized-bert-1","slug":"bibert-accurate-fully-binarized-bert-1","title":"BiBERT: Accurate Fully Binarized BERT","date":"2022-03-12","arxiv_id":"2203.06390","n_code_links":1,"syntology":null},{"paper":"/paper/elle-efficient-lifelong-pre-training-for-1","slug":"elle-efficient-lifelong-pre-training-for-1","title":"ELLE: Efficient Lifelong Pre-training for Emerging Data","date":"2022-03-12","arxiv_id":"2203.06311","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["thunlp/elle"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/finer-financial-numeric-entity-recognition","slug":"finer-financial-numeric-entity-recognition","title":"FiNER: Financial Numeric Entity Recognition for XBRL Tagging","date":"2022-03-12","arxiv_id":"2203.06482","n_code_links":2,"syntology":null},{"paper":"/paper/markbert-marking-word-boundaries-improves-1","slug":"markbert-marking-word-boundaries-improves-1","title":"MarkBERT: Marking Word Boundaries Improves Chinese BERT","date":"2022-03-12","arxiv_id":"2203.06378","n_code_links":1,"syntology":null},{"paper":"/paper/the-principle-of-diversity-training-stronger","slug":"the-principle-of-diversity-training-stronger","title":"The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy","date":"2022-03-12","arxiv_id":"2203.06345","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":10,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["vita-group/diverse-vit"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-sentence-is-worth-128-pseudo-tokens-a-1","slug":"a-sentence-is-worth-128-pseudo-tokens-a-1","title":"A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings","date":"2022-03-11","arxiv_id":"2203.05877","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":3,"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) · 2 unverified","official":{"repos":["namco0816/pt-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"]}}},{"paper":"/paper/bertopic-neural-topic-modeling-with-a-class","slug":"bertopic-neural-topic-modeling-with-a-class","title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","date":"2022-03-11","arxiv_id":"2203.05794","n_code_links":3,"syntology":{"ran":5,"of":8,"n_ran_checked":4,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 0 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) · 3 unverified","official":{"repos":["MaartenGr/BERTopic","maartengr/bertopic_evaluation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/block-sparse-adversarial-attack-to-fool","slug":"block-sparse-adversarial-attack-to-fool","title":"Block-Sparse Adversarial Attack to Fool Transformer-Based Text Classifiers","date":"2022-03-11","arxiv_id":"2203.05948","n_code_links":1,"syntology":null},{"paper":null,"slug":"hierarchical-bert-for-medical-document","title":"Hierarchical BERT for Medical Document Understanding","date":"2022-03-11","arxiv_id":"2204.09600","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-word-embeddings-to-analyze-protests","title":"Using Word Embeddings to Analyze Protests News","date":"2022-03-11","arxiv_id":"2203.05875","n_code_links":0,"syntology":null},{"paper":"/paper/verbert-automating-brazilian-case-law","slug":"verbert-automating-brazilian-case-law","title":"verBERT: Automating Brazilian Case Law Document Multi-label Categorization Using BERT","date":"2022-03-11","arxiv_id":"2203.06224","n_code_links":1,"syntology":null},{"paper":"/paper/when-classifying-grammatical-role-bert-doesn-1","slug":"when-classifying-grammatical-role-bert-doesn-1","title":"When classifying grammatical role, BERT doesn't care about word order... except when it matters","date":"2022-03-11","arxiv_id":"2203.06204","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-new-approach-to-calculating-bertscore-for","title":"A new approach to calculating BERTScore for automatic assessment of translation quality","date":"2022-03-10","arxiv_id":"2203.05598","n_code_links":0,"syntology":null},{"paper":"/paper/contextualized-sensorimotor-norms-multi-1","slug":"contextualized-sensorimotor-norms-multi-1","title":"Contextualized Sensorimotor Norms: multi-dimensional measures of sensorimotor strength for ambiguous English words, in context","date":"2022-03-10","arxiv_id":"2203.05648","n_code_links":1,"syntology":null},{"paper":null,"slug":"semantic-norm-recognition-and-its-application","title":"Semantic Norm Recognition and its application to Portuguese Law","date":"2022-03-10","arxiv_id":"2203.05425","n_code_links":0,"syntology":null},{"paper":"/paper/speciesist-language-and-nonhuman-animal-bias-1","slug":"speciesist-language-and-nonhuman-animal-bias-1","title":"Speciesist Language and Nonhuman Animal Bias in English Masked Language Models","date":"2022-03-10","arxiv_id":"2203.05140","n_code_links":1,"syntology":null},{"paper":"/paper/coarse-to-fine-sparse-transformer-for","slug":"coarse-to-fine-sparse-transformer-for","title":"Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction","date":"2022-03-09","arxiv_id":"2203.04845","n_code_links":1,"syntology":{"ran":13,"of":16,"n_ran_checked":9,"n_instrument":4,"unverified":3,"pointer_only":0,"phrase":"13 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["caiyuanhao1998/MST"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":8,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/nlx-gpt-a-model-for-natural-language","slug":"nlx-gpt-a-model-for-natural-language","title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","date":"2022-03-09","arxiv_id":"2203.05081","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-generalized-models-for-task-oriented","title":"Towards Generalized Models for Task-oriented Dialogue Modeling on Spoken Conversations","date":"2022-03-08","arxiv_id":"2203.04045","n_code_links":0,"syntology":null},{"paper":"/paper/it5-large-scale-text-to-text-pretraining-for","slug":"it5-large-scale-text-to-text-pretraining-for","title":"IT5: Text-to-text Pretraining for Italian Language Understanding and Generation","date":"2022-03-07","arxiv_id":"2203.03759","n_code_links":3,"syntology":null},{"paper":"/paper/pre-trained-token-replaced-detection-model-as","slug":"pre-trained-token-replaced-detection-model-as","title":"Pre-trained Token-replaced Detection Model as Few-shot Learner","date":"2022-03-07","arxiv_id":"2203.03235","n_code_links":1,"syntology":null},{"paper":"/paper/tensor-programs-v-tuning-large-neural","slug":"tensor-programs-v-tuning-large-neural","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","date":"2022-03-07","arxiv_id":"2203.03466","n_code_links":7,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/mup"],"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":["listed","official"]}}},{"paper":"/paper/divide-and-conquer-text-semantic-matching-1","slug":"divide-and-conquer-text-semantic-matching-1","title":"Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents","date":"2022-03-06","arxiv_id":"2203.02898","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-neural-network-enhanced-language-models","title":"Graph Neural Network Enhanced Language Models for Efficient Multilingual Text Classification","date":"2022-03-06","arxiv_id":"2203.02912","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-pre-trained-bert-for-audio","title":"Leveraging Pre-trained BERT for Audio Captioning","date":"2022-03-06","arxiv_id":"2203.02838","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-offensive-language-on-social","title":"Detecting Offensive Language on Social Networks: An End-to-end Detection Method based on Graph Attention Networks","date":"2022-03-04","arxiv_id":"2203.02123","n_code_links":0,"syntology":null},{"paper":"/paper/dit-self-supervised-pre-training-for-document","slug":"dit-self-supervised-pre-training-for-document","title":"DiT: Self-supervised Pre-training for Document Image Transformer","date":"2022-03-04","arxiv_id":"2203.02378","n_code_links":4,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":0,"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","official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/litetransformersearch-training-free-on-device","slug":"litetransformersearch-training-free-on-device","title":"LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models","date":"2022-03-04","arxiv_id":"2203.02094","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["microsoft/archai"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/training-language-models-to-follow","slug":"training-language-models-to-follow","title":"Training language models to follow instructions with human feedback","date":"2022-03-04","arxiv_id":"2203.02155","n_code_links":11,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openai/following-instructions-human-feedback"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/ensembles-of-vision-transformers-as-a-new","slug":"ensembles-of-vision-transformers-as-a-new","title":"Ensembles of Vision Transformers as a New Paradigm for Automated Classification in Ecology","date":"2022-03-03","arxiv_id":"2203.01726","n_code_links":1,"syntology":null},{"paper":"/paper/semantic-guided-image-virtual-attribute","slug":"semantic-guided-image-virtual-attribute","title":"BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification","date":"2022-03-03","arxiv_id":"2203.01937","n_code_links":2,"syntology":null},{"paper":"/paper/discontinuous-constituency-and-bert-a-case-1","slug":"discontinuous-constituency-and-bert-a-case-1","title":"Discontinuous Constituency and BERT: A Case Study of Dutch","date":"2022-03-02","arxiv_id":"2203.01063","n_code_links":1,"syntology":null},{"paper":"/paper/parameter-efficient-mixture-of-experts","slug":"parameter-efficient-mixture-of-experts","title":"Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models","date":"2022-03-02","arxiv_id":"2203.01104","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rucaibox/mpo","rucaibox/mpoe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/bert-lid-leveraging-bert-to-improve-spoken","slug":"bert-lid-leveraging-bert-to-improve-spoken","title":"BERT-LID: Leveraging BERT to Improve Spoken Language Identification","date":"2022-03-01","arxiv_id":"2203.00328","n_code_links":1,"syntology":null},{"paper":null,"slug":"e-lang-energy-based-joint-inferencing-of-1","title":"E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models","date":"2022-03-01","arxiv_id":"2203.00748","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-and-adapting-chinese-gpt-to-pinyin-1","slug":"exploring-and-adapting-chinese-gpt-to-pinyin-1","title":"Exploring and Adapting Chinese GPT to Pinyin Input Method","date":"2022-03-01","arxiv_id":"2203.00249","n_code_links":1,"syntology":null},{"paper":null,"slug":"hyperprompt-prompt-based-task-conditioning-of","title":"HyperPrompt: Prompt-based Task-Conditioning of Transformers","date":"2022-03-01","arxiv_id":"2203.00759","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-whole-word-masking-always-better-for-1","title":"\"Is Whole Word Masking Always Better for Chinese BERT?\": Probing on Chinese Grammatical Error Correction","date":"2022-03-01","arxiv_id":"2203.00286","n_code_links":0,"syntology":null},{"paper":"/paper/the-impact-of-lexical-and-grammatical-1","slug":"the-impact-of-lexical-and-grammatical-1","title":"The impact of lexical and grammatical processing on generating code from natural language","date":"2022-02-28","arxiv_id":"2202.13972","n_code_links":2,"syntology":null},{"paper":"/paper/enhancing-legal-argument-mining-with-domain","slug":"enhancing-legal-argument-mining-with-domain","title":"Enhancing Legal Argument Mining with Domain Pre-training and Neural Networks","date":"2022-02-27","arxiv_id":"2202.13457","n_code_links":1,"syntology":null},{"paper":"/paper/a-systematic-evaluation-of-large-language","slug":"a-systematic-evaluation-of-large-language","title":"A Systematic Evaluation of Large Language Models of Code","date":"2022-02-26","arxiv_id":"2202.13169","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eleutherai/gpt-neox","vhellendoorn/code-lms"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bi-directional-joint-neural-networks-for","title":"Bi-directional Joint Neural Networks for Intent Classification and Slot Filling","date":"2022-02-26","arxiv_id":"2202.13079","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-level-contrastive-learning-for-cross","title":"Multi-Level Contrastive Learning for Cross-Lingual Alignment","date":"2022-02-26","arxiv_id":"2202.13083","n_code_links":0,"syntology":null},{"paper":"/paper/apeach-attacking-pejorative-expressions-with","slug":"apeach-attacking-pejorative-expressions-with","title":"APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets","date":"2022-02-25","arxiv_id":"2202.12459","n_code_links":1,"syntology":null},{"paper":"/paper/rethinking-the-role-of-demonstrations-what","slug":"rethinking-the-role-of-demonstrations-what","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","date":"2022-02-25","arxiv_id":"2202.12837","n_code_links":2,"syntology":null},{"paper":"/paper/bertvision-a-parameter-efficient-approach-for","slug":"bertvision-a-parameter-efficient-approach-for","title":"BERTVision -- A Parameter-Efficient Approach for Question Answering","date":"2022-02-24","arxiv_id":"2202.12210","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cbenge509/bertvision"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"finding-inverse-document-frequency","title":"Finding Inverse Document Frequency Information in BERT","date":"2022-02-24","arxiv_id":"2202.12191","n_code_links":0,"syntology":null},{"paper":"/paper/from-natural-language-to-simulations-applying","slug":"from-natural-language-to-simulations-applying","title":"From Natural Language to Simulations: Applying GPT-3 Codex to Automate Simulation Modeling of Logistics Systems","date":"2022-02-24","arxiv_id":"2202.12107","n_code_links":1,"syntology":null},{"paper":null,"slug":"pretraining-without-wordpieces-learning-over","title":"Pretraining without Wordpieces: Learning Over a Vocabulary of Millions of Words","date":"2022-02-24","arxiv_id":"2202.12142","n_code_links":0,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/paper/sky-computing-accelerating-geo-distributed","slug":"sky-computing-accelerating-geo-distributed","title":"Sky Computing: Accelerating Geo-distributed Computing in Federated Learning","date":"2022-02-24","arxiv_id":"2202.11836","n_code_links":1,"syntology":null},{"paper":null,"slug":"trimbert-tailoring-bert-for-trade-offs","title":"TrimBERT: Tailoring BERT for Trade-offs","date":"2022-02-24","arxiv_id":"2202.12411","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-calibrator-to-improve-robustness-in","title":"Using calibrator to improve robustness in Machine Reading Comprehension","date":"2022-02-24","arxiv_id":"2202.11865","n_code_links":0,"syntology":null},{"paper":null,"slug":"consistent-dropout-for-policy-gradient","title":"Consistent Dropout for Policy Gradient Reinforcement Learning","date":"2022-02-23","arxiv_id":"2202.11818","n_code_links":0,"syntology":null},{"paper":"/paper/improving-ctc-based-speech-recognition-via","slug":"improving-ctc-based-speech-recognition-via","title":"Improving CTC-based speech recognition via knowledge transferring from pre-trained language models","date":"2022-02-22","arxiv_id":"2203.03582","n_code_links":1,"syntology":null},{"paper":null,"slug":"james-job-title-mapping-with-multi-aspect","title":"JAMES: Normalizing Job Titles with Multi-Aspect Graph Embeddings and Reasoning","date":"2022-02-22","arxiv_id":"2202.10739","n_code_links":0,"syntology":null},{"paper":null,"slug":"items-from-psychometric-tests-as-training","title":"Items from Psychometric Tests as Training Data for Personality Profiling Models of Twitter Users","date":"2022-02-21","arxiv_id":"2202.10415","n_code_links":0,"syntology":null},{"paper":"/paper/contextual-semantic-embeddings-for-ontology","slug":"contextual-semantic-embeddings-for-ontology","title":"Contextual Semantic Embeddings for Ontology Subsumption Prediction","date":"2022-02-20","arxiv_id":"2202.09791","n_code_links":2,"syntology":null},{"paper":null,"slug":"do-transformers-use-variable-binding","title":"Do Transformers know symbolic rules, and would we know if they did?","date":"2022-02-19","arxiv_id":"2203.00162","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-construct-validity-of-text","slug":"evaluating-the-construct-validity-of-text","title":"Evaluating the Construct Validity of Text Embeddings with Application to Survey Questions","date":"2022-02-18","arxiv_id":"2202.09166","n_code_links":1,"syntology":null},{"paper":null,"slug":"mixture-of-experts-with-expert-choice-routing","title":"Mixture-of-Experts with Expert Choice Routing","date":"2022-02-18","arxiv_id":"2202.09368","n_code_links":0,"syntology":null},{"paper":"/paper/sgpt-gpt-sentence-embeddings-for-semantic","slug":"sgpt-gpt-sentence-embeddings-for-semantic","title":"SGPT: GPT Sentence Embeddings for Semantic Search","date":"2022-02-17","arxiv_id":"2202.08904","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["muennighoff/sgpt"],"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"]}}},{"paper":null,"slug":"when-bert-meets-quantum-temporal-convolution","title":"When BERT Meets Quantum Temporal Convolution Learning for Text Classification in Heterogeneous Computing","date":"2022-02-17","arxiv_id":"2203.03550","n_code_links":0,"syntology":null},{"paper":"/paper/a-survey-of-pretraining-on-graphs-taxonomy","slug":"a-survey-of-pretraining-on-graphs-taxonomy","title":"A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applications","date":"2022-02-16","arxiv_id":"2202.07893","n_code_links":3,"syntology":null},{"paper":null,"slug":"no-one-left-behind-inclusive-federated","title":"No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices","date":"2022-02-16","arxiv_id":"2202.08036","n_code_links":0,"syntology":null},{"paper":"/paper/probing-pretrained-models-of-source-code","slug":"probing-pretrained-models-of-source-code","title":"Probing Pretrained Models of Source Code","date":"2022-02-16","arxiv_id":"2202.08975","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-nlp-task-effectiveness-of-long-range","title":"The NLP Task Effectiveness of Long-Range Transformers","date":"2022-02-16","arxiv_id":"2202.07856","n_code_links":0,"syntology":null},{"paper":null,"slug":"blue-at-memotion-2-0-2022-you-have-my-image","title":"BLUE at Memotion 2.0 2022: You have my Image, my Text and my Transformer","date":"2022-02-15","arxiv_id":"2202.07543","n_code_links":0,"syntology":null},{"paper":null,"slug":"defending-against-reconstruction-attacks-with","title":"Defending against Reconstruction Attacks with Rényi Differential Privacy","date":"2022-02-15","arxiv_id":"2202.07623","n_code_links":0,"syntology":null},{"paper":"/paper/one-configuration-to-rule-them-all-towards","slug":"one-configuration-to-rule-them-all-towards","title":"One Configuration to Rule Them All? Towards Hyperparameter Transfer in Topic Models using Multi-Objective Bayesian Optimization","date":"2022-02-15","arxiv_id":"2202.07631","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-on-the-edge-identifying-where-a","title":"Predicting on the Edge: Identifying Where a Larger Model Does Better","date":"2022-02-15","arxiv_id":"2202.07652","n_code_links":0,"syntology":null},{"paper":"/paper/tomayto-tomahto-beyond-token-level-answer","slug":"tomayto-tomahto-beyond-token-level-answer","title":"Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation","date":"2022-02-15","arxiv_id":"2202.07654","n_code_links":1,"syntology":null},{"paper":null,"slug":"toxic-comments-hunter-score-severity-of-toxic","title":"Toxic Comments Hunter : Score Severity of Toxic Comments","date":"2022-02-15","arxiv_id":"2203.03548","n_code_links":0,"syntology":null},{"paper":null,"slug":"punctuation-restoration-in-swedish-through","title":"Punctuation restoration in Swedish through fine-tuned KB-BERT","date":"2022-02-14","arxiv_id":"2202.06769","n_code_links":0,"syntology":null},{"paper":null,"slug":"userbert-modeling-long-and-short-term-user","title":"UserBERT: Modeling Long- and Short-Term User Preferences via Self-Supervision","date":"2022-02-14","arxiv_id":"2202.07605","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessment-of-contextualised-representations","title":"Assessment of contextualised representations in detecting outcome phrases in clinical trials","date":"2022-02-13","arxiv_id":"2203.03547","n_code_links":0,"syntology":null}],"record_sha256":"1017771a934f2a20a84249369b57e37c7f8d6ca5254a4a0aafdcba1e86bdf2ce","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}