{"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/dropout/papers/250","list_of":"/method/dropout","method":"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":250,"pages_in_order":275,"rows_per_page":100,"rows":[24901,25000],"of":27472,"counts":{"archive_papers_tagged":27472,"with_a_code_link":12129,"where_syntology_ran_a_sample":3620,"not_listed_spam_title":0,"listed":27472,"listed_where_code_ran":3620,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3044,"every_run_a_failure_of_syntologys_instrument":576,"listed_with_a_run_with_no_instrument_failure":3044,"listed_every_run_a_failure_of_syntologys_instrument":576,"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/dropout","prev":"/method/dropout/papers/249","next":"/method/dropout/papers/251","papers":[{"paper":"/paper/sketchformer-transformer-based-representation","slug":"sketchformer-transformer-based-representation","title":"Sketchformer: Transformer-based Representation for Sketched Structure","date":"2020-02-24","arxiv_id":"2002.10381","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":null}},{"paper":"/paper/beyond-dropout-feature-map-distortion-to","slug":"beyond-dropout-feature-map-distortion-to","title":"Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks","date":"2020-02-23","arxiv_id":"2002.11022","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["huawei-noah/Disout"],"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":["listed","official"]}}},{"paper":"/paper/gradual-channel-pruning-while-training-using","slug":"gradual-channel-pruning-while-training-using","title":"Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural Networks","date":"2020-02-23","arxiv_id":"2002.09958","n_code_links":1,"syntology":null},{"paper":"/paper/neuron-shapley-discovering-the-responsible","slug":"neuron-shapley-discovering-the-responsible","title":"Neuron Shapley: Discovering the Responsible Neurons","date":"2020-02-23","arxiv_id":"2002.09815","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["amiratag/neuronshapley"],"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/practical-and-bilateral-privacy-preserving","slug":"practical-and-bilateral-privacy-preserving","title":"An Accuracy-Lossless Perturbation Method for Defending Privacy Attacks in Federated Learning","date":"2020-02-23","arxiv_id":"2002.09843","n_code_links":1,"syntology":null},{"paper":null,"slug":"incorporating-effective-global-information","title":"Incorporating Effective Global Information via Adaptive Gate Attention for Text Classification","date":"2020-02-22","arxiv_id":"2002.09673","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-question-answering-models-from","title":"Training Question Answering Models From Synthetic Data","date":"2020-02-22","arxiv_id":"2002.09599","n_code_links":0,"syntology":null},{"paper":"/paper/accessing-higher-level-representations-in","slug":"accessing-higher-level-representations-in","title":"Addressing Some Limitations of Transformers with Feedback Memory","date":"2020-02-21","arxiv_id":"2002.09402","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/transformer-sequential"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":null,"slug":"exploiting-the-full-capacity-of-deep-neural","title":"Exploiting the Full Capacity of Deep Neural Networks while Avoiding Overfitting by Targeted Sparsity Regularization","date":"2020-02-21","arxiv_id":"2002.09237","n_code_links":0,"syntology":null},{"paper":null,"slug":"introducing-fuzzy-layers-for-deep-learning","title":"Introducing Fuzzy Layers for Deep Learning","date":"2020-02-21","arxiv_id":"2003.00880","n_code_links":0,"syntology":null},{"paper":"/paper/learning-dynamic-knowledge-graphs-to","slug":"learning-dynamic-knowledge-graphs-to","title":"Learning Dynamic Belief Graphs to Generalize on Text-Based Games","date":"2020-02-21","arxiv_id":"2002.09127","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-hawkes-process","slug":"transformer-hawkes-process","title":"Transformer Hawkes Process","date":"2020-02-21","arxiv_id":"2002.09291","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["SimiaoZuo/Transformer-Hawkes-Process"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"comparing-different-deep-learning","title":"Comparing Different Deep Learning Architectures for Classification of Chest Radiographs","date":"2020-02-20","arxiv_id":"2002.08991","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-pretraining-and-fine-tuning-of-bert","title":"Federated pretraining and fine tuning of BERT using clinical notes from multiple silos","date":"2020-02-20","arxiv_id":"2002.08562","n_code_links":0,"syntology":null},{"paper":"/paper/maxup-a-simple-way-to-improve-generalization","slug":"maxup-a-simple-way-to-improve-generalization","title":"MaxUp: A Simple Way to Improve Generalization of Neural Network Training","date":"2020-02-20","arxiv_id":"2002.09024","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":null}},{"paper":"/paper/compressing-bert-studying-the-effects-of-1","slug":"compressing-bert-studying-the-effects-of-1","title":"Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning","date":"2020-02-19","arxiv_id":"2002.08307","n_code_links":1,"syntology":null},{"paper":"/paper/defraudnetend2end-fingerprint-spoof-detection","slug":"defraudnetend2end-fingerprint-spoof-detection","title":"DeFraudNet:End2End Fingerprint Spoof Detection using Patch Level Attention","date":"2020-02-19","arxiv_id":"2002.08214","n_code_links":1,"syntology":null},{"paper":"/paper/lambert-layout-aware-language-modeling-using","slug":"lambert-layout-aware-language-modeling-using","title":"LAMBERT: Layout-Aware (Language) Modeling for information extraction","date":"2020-02-19","arxiv_id":"2002.08087","n_code_links":1,"syntology":null},{"paper":"/paper/modelling-response-to-trypophobia-trigger","slug":"modelling-response-to-trypophobia-trigger","title":"Modelling response to trypophobia trigger using intermediate layers of ImageNet networks","date":"2020-02-19","arxiv_id":"2002.08490","n_code_links":1,"syntology":null},{"paper":"/paper/molecule-attention-transformer","slug":"molecule-attention-transformer","title":"Molecule Attention Transformer","date":"2020-02-19","arxiv_id":"2002.08264","n_code_links":7,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["gmum/MAT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/the-microsoft-toolkit-of-multi-task-deep","slug":"the-microsoft-toolkit-of-multi-task-deep","title":"The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2020-02-19","arxiv_id":"2002.07972","n_code_links":3,"syntology":null},{"paper":"/paper/toward-making-the-most-of-context-in-neural","slug":"toward-making-the-most-of-context-in-neural","title":"Towards Making the Most of Context in Neural Machine Translation","date":"2020-02-19","arxiv_id":"2002.07982","n_code_links":1,"syntology":null},{"paper":null,"slug":"tree-structured-attention-with-hierarchical-1","title":"Tree-structured Attention with Hierarchical Accumulation","date":"2020-02-19","arxiv_id":"2002.08046","n_code_links":0,"syntology":null},{"paper":null,"slug":"conditional-self-attention-for-query-based","title":"Conditional Self-Attention for Query-based Summarization","date":"2020-02-18","arxiv_id":"2002.07338","n_code_links":0,"syntology":null},{"paper":"/paper/from-english-to-foreign-languages-1","slug":"from-english-to-foreign-languages-1","title":"From English To Foreign Languages: Transferring Pre-trained Language Models","date":"2020-02-18","arxiv_id":"2002.07306","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":null}},{"paper":"/paper/gradient-based-adversarial-training-on","slug":"gradient-based-adversarial-training-on","title":"Gradient-Based Adversarial Training on Transformer Networks for Detecting Check-Worthy Factual Claims","date":"2020-02-18","arxiv_id":"2002.07725","n_code_links":1,"syntology":null},{"paper":"/paper/hierarchical-transformer-network-for","slug":"hierarchical-transformer-network-for","title":"Hierarchical Transformer Network for Utterance-level Emotion Recognition","date":"2020-02-18","arxiv_id":"2002.07551","n_code_links":0,"syntology":null},{"paper":"/paper/sequential-latent-knowledge-selection-for-1","slug":"sequential-latent-knowledge-selection-for-1","title":"Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue","date":"2020-02-18","arxiv_id":"2002.07510","n_code_links":3,"syntology":{"ran":0,"of":5,"n_ran_checked":0,"n_instrument":0,"unverified":5,"pointer_only":5,"phrase":"0 ran · 5 unverified","official":{"repos":["bckim92/sequential-knowledge-transformer"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":"/paper/uncertainty-in-structured-prediction","slug":"uncertainty-in-structured-prediction","title":"Uncertainty Estimation in Autoregressive Structured Prediction","date":"2020-02-18","arxiv_id":"2002.07650","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-financial-service-chatbot-based-on-deep","title":"A Financial Service Chatbot based on Deep Bidirectional Transformers","date":"2020-02-17","arxiv_id":"2003.04987","n_code_links":0,"syntology":null},{"paper":null,"slug":"controlling-computation-versus-quality-for","title":"Controlling Computation versus Quality for Neural Sequence Models","date":"2020-02-17","arxiv_id":"2002.07106","n_code_links":0,"syntology":null},{"paper":"/paper/data-and-model-dependencies-of-membership","slug":"data-and-model-dependencies-of-membership","title":"Data and Model Dependencies of Membership Inference Attack","date":"2020-02-17","arxiv_id":"2002.06856","n_code_links":1,"syntology":null},{"paper":"/paper/incorporating-bert-into-neural-machine-1","slug":"incorporating-bert-into-neural-machine-1","title":"Incorporating BERT into Neural Machine Translation","date":"2020-02-17","arxiv_id":"2002.06823","n_code_links":3,"syntology":null},{"paper":null,"slug":"low-rank-bottleneck-in-multi-head-attention","title":"Low-Rank Bottleneck in Multi-head Attention Models","date":"2020-02-17","arxiv_id":"2002.07028","n_code_links":0,"syntology":null},{"paper":null,"slug":"generator-from-edges-reconstruction-of-facial","title":"Generator From Edges: Reconstruction of Facial Images","date":"2020-02-16","arxiv_id":"2002.06682","n_code_links":0,"syntology":null},{"paper":"/paper/multi-layer-representation-fusion-for-neural-2","slug":"multi-layer-representation-fusion-for-neural-2","title":"Multi-layer Representation Fusion for Neural Machine Translation","date":"2020-02-16","arxiv_id":"2002.06714","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":null}},{"paper":"/paper/neural-machine-translation-with-joint","slug":"neural-machine-translation-with-joint","title":"Neural Machine Translation with Joint Representation","date":"2020-02-16","arxiv_id":"2002.06546","n_code_links":1,"syntology":null},{"paper":"/paper/sbert-wk-a-sentence-embedding-method-by","slug":"sbert-wk-a-sentence-embedding-method-by","title":"SBERT-WK: A Sentence Embedding Method by Dissecting BERT-based Word Models","date":"2020-02-16","arxiv_id":"2002.06652","n_code_links":3,"syntology":null},{"paper":null,"slug":"the-utility-of-general-domain-transfer","title":"The Utility of General Domain Transfer Learning for Medical Language Tasks","date":"2020-02-16","arxiv_id":"2002.06670","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-pretrained-language-models-weight","slug":"fine-tuning-pretrained-language-models-weight","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","date":"2020-02-15","arxiv_id":"2002.06305","n_code_links":4,"syntology":null},{"paper":null,"slug":"small-energy-masking-for-improved-neural","title":"Small energy masking for improved neural network training for end-to-end speech recognition","date":"2020-02-15","arxiv_id":"2002.06312","n_code_links":0,"syntology":null},{"paper":"/paper/univilm-a-unified-video-and-language-pre","slug":"univilm-a-unified-video-and-language-pre","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","date":"2020-02-15","arxiv_id":"2002.06353","n_code_links":2,"syntology":{"ran":1,"of":4,"n_ran_checked":0,"n_instrument":1,"unverified":3,"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) · 3 unverified","official":{"repos":["microsoft/UniVL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"deep-attentive-study-session-dropout","title":"Deep Attentive Study Session Dropout Prediction in Mobile Learning Environment","date":"2020-02-14","arxiv_id":"2002.11624","n_code_links":0,"syntology":null},{"paper":"/paper/fquad-french-question-answering-dataset","slug":"fquad-french-question-answering-dataset","title":"FQuAD: French Question Answering Dataset","date":"2020-02-14","arxiv_id":"2002.06071","n_code_links":0,"syntology":null},{"paper":"/paper/skip-connections-matter-on-the","slug":"skip-connections-matter-on-the","title":"Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets","date":"2020-02-14","arxiv_id":"2002.05990","n_code_links":4,"syntology":{"ran":4,"of":9,"n_ran_checked":1,"n_instrument":3,"unverified":5,"pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["csdongxian/skip-connections-matter"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"stress-test-evaluation-of-transformer-based","title":"Stress Test Evaluation of Transformer-based Models in Natural Language Understanding Tasks","date":"2020-02-14","arxiv_id":"2002.06261","n_code_links":0,"syntology":null},{"paper":"/paper/towards-an-appropriate-query-key-and-value","slug":"towards-an-appropriate-query-key-and-value","title":"Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing","date":"2020-02-14","arxiv_id":"2002.07033","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/transformer-on-a-diet","slug":"transformer-on-a-diet","title":"Transformer on a Diet","date":"2020-02-14","arxiv_id":"2002.06170","n_code_links":1,"syntology":null},{"paper":"/paper/twinbert-distilling-knowledge-to-twin","slug":"twinbert-distilling-knowledge-to-twin","title":"TwinBERT: Distilling Knowledge to Twin-Structured BERT Models for Efficient Retrieval","date":"2020-02-14","arxiv_id":"2002.06275","n_code_links":2,"syntology":null},{"paper":null,"slug":"understanding-patient-complaint","title":"Understanding patient complaint characteristics using contextual clinical BERT embeddings","date":"2020-02-14","arxiv_id":"2002.05902","n_code_links":0,"syntology":null},{"paper":null,"slug":"cbag-conditional-biomedical-abstract","title":"CBAG: Conditional Biomedical Abstract Generation","date":"2020-02-13","arxiv_id":"2002.05637","n_code_links":0,"syntology":null},{"paper":"/paper/endol2h-deep-super-resolution-for-capsule","slug":"endol2h-deep-super-resolution-for-capsule","title":"EndoL2H: Deep Super-Resolution for Capsule Endoscopy","date":"2020-02-13","arxiv_id":"2002.05459","n_code_links":3,"syntology":null},{"paper":"/paper/ensemble-neural-network-forecasts-with","slug":"ensemble-neural-network-forecasts-with","title":"Ensemble methods for neural network-based weather forecasts","date":"2020-02-13","arxiv_id":"2002.05398","n_code_links":1,"syntology":null},{"paper":null,"slug":"object-detection-on-single-monocular-images","title":"Object Detection on Single Monocular Images through Canonical Correlation Analysis","date":"2020-02-13","arxiv_id":"2002.05349","n_code_links":0,"syntology":null},{"paper":null,"slug":"simple-and-accurate-uncertainty","title":"Learning to Predict Error for MRI Reconstruction","date":"2020-02-13","arxiv_id":"2002.05582","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-and-structured-visual-attention-1","slug":"sparse-and-structured-visual-attention-1","title":"Sparse and Structured Visual Attention","date":"2020-02-13","arxiv_id":"2002.05556","n_code_links":1,"syntology":null},{"paper":"/paper/training-large-neural-networks-with-constant","slug":"training-large-neural-networks-with-constant","title":"Training Large Neural Networks with Constant Memory using a New Execution Algorithm","date":"2020-02-13","arxiv_id":"2002.05645","n_code_links":2,"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: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/attentional-speech-recognition-models","slug":"attentional-speech-recognition-models","title":"Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances","date":"2020-02-12","arxiv_id":"2002.05150","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-face-parsing-via-interlinked","slug":"end-to-end-face-parsing-via-interlinked","title":"End-to-End Face Parsing via Interlinked Convolutional Neural Networks","date":"2020-02-12","arxiv_id":"2002.04831","n_code_links":1,"syntology":null},{"paper":"/paper/glu-variants-improve-transformer","slug":"glu-variants-improve-transformer","title":"GLU Variants Improve Transformer","date":"2020-02-12","arxiv_id":"2002.05202","n_code_links":27,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"pointer_only":7,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 4 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"learnable-bernoulli-dropout-for-bayesian-deep","title":"Learnable Bernoulli Dropout for Bayesian Deep Learning","date":"2020-02-12","arxiv_id":"2002.05155","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-compare-for-better-training-and","title":"Learning to Compare for Better Training and Evaluation of Open Domain Natural Language Generation Models","date":"2020-02-12","arxiv_id":"2002.05058","n_code_links":0,"syntology":null},{"paper":"/paper/lookahead-a-far-sighted-alternative-of-1","slug":"lookahead-a-far-sighted-alternative-of-1","title":"Lookahead: a Far-Sighted Alternative of Magnitude-based Pruning","date":"2020-02-12","arxiv_id":"2002.04809","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":6,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 6 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alinlab/lookahead_pruning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-layer-normalization-in-the-transformer-1","slug":"on-layer-normalization-in-the-transformer-1","title":"On Layer Normalization in the Transformer Architecture","date":"2020-02-12","arxiv_id":"2002.04745","n_code_links":9,"syntology":{"ran":10,"of":11,"n_ran_checked":10,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/utilizing-bert-intermediate-layers-for-aspect","slug":"utilizing-bert-intermediate-layers-for-aspect","title":"Utilizing BERT Intermediate Layers for Aspect Based Sentiment Analysis and Natural Language Inference","date":"2020-02-12","arxiv_id":"2002.04815","n_code_links":1,"syntology":null},{"paper":null,"slug":"superbloom-bloom-filter-meets-transformer-1","title":"Superbloom: Bloom filter meets Transformer","date":"2020-02-11","arxiv_id":"2002.04723","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-with-streaming-annotation","title":"Training with Streaming Annotation","date":"2020-02-11","arxiv_id":"2002.04165","n_code_links":0,"syntology":null},{"paper":null,"slug":"turbo-aggregate-breaking-the-quadratic","title":"Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning","date":"2020-02-11","arxiv_id":"2002.04156","n_code_links":0,"syntology":null},{"paper":"/paper/validating-uncertainty-in-medical-image","slug":"validating-uncertainty-in-medical-image","title":"Validating uncertainty in medical image translation","date":"2020-02-11","arxiv_id":"2002.04639","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-representation-learning-for-dynamical","title":"Deep Representation Learning for Dynamical Systems Modeling","date":"2020-02-10","arxiv_id":"2002.05111","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-multi-speaker-speech-recognition-1","title":"End-to-End Multi-speaker Speech Recognition with Transformer","date":"2020-02-10","arxiv_id":"2002.03921","n_code_links":0,"syntology":null},{"paper":null,"slug":"localized-flood-detectionwith-minimal-labeled","title":"Localized Flood DetectionWith Minimal Labeled Social Media Data Using Transfer Learning","date":"2020-02-10","arxiv_id":"2003.04973","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-alignment-of-contextual-word-1","slug":"multilingual-alignment-of-contextual-word-1","title":"Multilingual Alignment of Contextual Word Representations","date":"2020-02-10","arxiv_id":"2002.03518","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":null}},{"paper":null,"slug":"pre-training-tasks-for-embedding-based-large","title":"Pre-training Tasks for Embedding-based Large-scale Retrieval","date":"2020-02-10","arxiv_id":"2002.03932","n_code_links":0,"syntology":null},{"paper":null,"slug":"stickypillars-robust-feature-matching-on","title":"StickyPillars: Robust and Efficient Feature Matching on Point Clouds using Graph Neural Networks","date":"2020-02-10","arxiv_id":"2002.03983","n_code_links":0,"syntology":null},{"paper":null,"slug":"application-of-pre-training-models-in-named","title":"Application of Pre-training Models in Named Entity Recognition","date":"2020-02-09","arxiv_id":"2002.08902","n_code_links":0,"syntology":null},{"paper":null,"slug":"convolutional-neural-network-pruning-using","title":"Convolutional Neural Network Pruning Using Filter Attenuation","date":"2020-02-09","arxiv_id":"2002.03299","n_code_links":0,"syntology":null},{"paper":null,"slug":"momentum-improves-normalized-sgd","title":"Momentum Improves Normalized SGD","date":"2020-02-09","arxiv_id":"2002.03305","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-distance-between-two-neural-networks","slug":"on-the-distance-between-two-neural-networks","title":"On the distance between two neural networks and the stability of learning","date":"2020-02-09","arxiv_id":"2002.03432","n_code_links":2,"syntology":null},{"paper":null,"slug":"bitpruning-learning-bitlengths-for-aggressive","title":"BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization","date":"2020-02-08","arxiv_id":"2002.03090","n_code_links":0,"syntology":null},{"paper":"/paper/blank-language-models","slug":"blank-language-models","title":"Blank Language Models","date":"2020-02-08","arxiv_id":"2002.03079","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["Varal7/blank_language_model"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/bert-of-theseus-compressing-bert-by","slug":"bert-of-theseus-compressing-bert-by","title":"BERT-of-Theseus: Compressing BERT by Progressive Module Replacing","date":"2020-02-07","arxiv_id":"2002.02925","n_code_links":2,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["JetRunner/BERT-of-Theseus"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["listed"]}}},{"paper":"/paper/dropcluster-a-structured-dropout-for","slug":"dropcluster-a-structured-dropout-for","title":"DropCluster: A structured dropout for convolutional networks","date":"2020-02-07","arxiv_id":"2002.02997","n_code_links":1,"syntology":null},{"paper":"/paper/image-fine-grained-inpainting","slug":"image-fine-grained-inpainting","title":"Image Fine-grained Inpainting","date":"2020-02-07","arxiv_id":"2002.02609","n_code_links":3,"syntology":null},{"paper":"/paper/input-dropout-for-spatially-aligned","slug":"input-dropout-for-spatially-aligned","title":"Input Dropout for Spatially Aligned Modalities","date":"2020-02-07","arxiv_id":"2002.02852","n_code_links":1,"syntology":null},{"paper":null,"slug":"multimodal-matching-transformer-for-live","title":"Multimodal Matching Transformer for Live Commenting","date":"2020-02-07","arxiv_id":"2002.02649","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-capsule-model-for-intent","slug":"transformer-capsule-model-for-intent","title":"Transformer-Capsule Model for Intent Detection","date":"2020-02-07","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/transformer-transducer-a-streamable-speech","slug":"transformer-transducer-a-streamable-speech","title":"Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss","date":"2020-02-07","arxiv_id":"2002.02562","n_code_links":5,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"understanding-and-optimizing-packed-neural","title":"Understanding and Optimizing Packed Neural Network Training for Hyper-Parameter Tuning","date":"2020-02-07","arxiv_id":"2002.02885","n_code_links":0,"syntology":null},{"paper":null,"slug":"almost-sure-convergence-of-dropout-algorithms","title":"Almost Sure Convergence of Dropout Algorithms for Neural Networks","date":"2020-02-06","arxiv_id":"2002.02247","n_code_links":0,"syntology":null},{"paper":"/paper/few-shot-learning-as-domain-adaptation","slug":"few-shot-learning-as-domain-adaptation","title":"Few-Shot Learning as Domain Adaptation: Algorithm and Analysis","date":"2020-02-06","arxiv_id":"2002.02050","n_code_links":0,"syntology":null},{"paper":"/paper/introducing-aspects-of-creativity-in","slug":"introducing-aspects-of-creativity-in","title":"Introducing Aspects of Creativity in Automatic Poetry Generation","date":"2020-02-06","arxiv_id":"2002.02511","n_code_links":1,"syntology":null},{"paper":null,"slug":"perm2vec-graph-permutation-selection-for","title":"perm2vec: Graph Permutation Selection for Decoding of Error Correction Codes using Self-Attention","date":"2020-02-06","arxiv_id":"2002.02315","n_code_links":0,"syntology":null},{"paper":null,"slug":"aligning-the-pretraining-and-finetuning","title":"Aligning the Pretraining and Finetuning Objectives of Language Models","date":"2020-02-05","arxiv_id":"2002.02000","n_code_links":0,"syntology":null},{"paper":null,"slug":"dropout-prediction-over-weeks-in-moocs-by","title":"Dropout Prediction over Weeks in MOOCs by Learning Representations of Clicks and Videos","date":"2020-02-05","arxiv_id":"2002.01955","n_code_links":0,"syntology":null},{"paper":"/paper/k-adapter-infusing-knowledge-into-pre-trained","slug":"k-adapter-infusing-knowledge-into-pre-trained","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","date":"2020-02-05","arxiv_id":"2002.01808","n_code_links":2,"syntology":{"ran":11,"of":14,"n_ran_checked":6,"n_instrument":5,"unverified":3,"pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/rapid-adaptation-of-bert-for-information","slug":"rapid-adaptation-of-bert-for-information","title":"Rapid Adaptation of BERT for Information Extraction on Domain-Specific Business Documents","date":"2020-02-05","arxiv_id":"2002.01861","n_code_links":1,"syntology":null},{"paper":"/paper/vocoder-free-end-to-end-voice-conversion-with","slug":"vocoder-free-end-to-end-voice-conversion-with","title":"Vocoder-free End-to-End Voice Conversion with Transformer Network","date":"2020-02-05","arxiv_id":"2002.03808","n_code_links":1,"syntology":null},{"paper":"/paper/interpretable-time-budget-constrained","slug":"interpretable-time-budget-constrained","title":"Interpretable & Time-Budget-Constrained Contextualization for Re-Ranking","date":"2020-02-04","arxiv_id":"2002.01854","n_code_links":1,"syntology":null},{"paper":"/paper/large-batch-training-does-not-need-warmup","slug":"large-batch-training-does-not-need-warmup","title":"Large Batch Training Does Not Need Warmup","date":"2020-02-04","arxiv_id":"2002.01576","n_code_links":1,"syntology":null}],"record_sha256":"f4974395db29f925cef83ed5a82c1ece8fbb59e68ca3d75c1c0f26c290613f2d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}