{"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/264","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":264,"pages_in_order":275,"rows_per_page":100,"rows":[26301,26400],"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/263","next":"/method/dropout/papers/265","papers":[{"paper":"/paper/190602124","slug":"190602124","title":"PatentBERT: Patent Classification with Fine-Tuning a pre-trained BERT Model","date":"2019-05-14","arxiv_id":"1906.02124","n_code_links":1,"syntology":null},{"paper":"/paper/american-sign-language-alphabet-recognition","slug":"american-sign-language-alphabet-recognition","title":"American Sign Language Alphabet Recognition using Deep Learning","date":"2019-05-14","arxiv_id":"1905.05487","n_code_links":0,"syntology":null},{"paper":"/paper/bert-with-history-answer-embedding-for","slug":"bert-with-history-answer-embedding-for","title":"BERT with History Answer Embedding for Conversational Question Answering","date":"2019-05-14","arxiv_id":"1905.05412","n_code_links":1,"syntology":null},{"paper":"/paper/cognitive-graph-for-multi-hop-reading","slug":"cognitive-graph-for-multi-hop-reading","title":"Cognitive Graph for Multi-Hop Reading Comprehension at Scale","date":"2019-05-14","arxiv_id":"1905.05460","n_code_links":2,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["THUDM/CogQA"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/deep-residual-output-layers-for-neural","slug":"deep-residual-output-layers-for-neural","title":"Deep Residual Output Layers for Neural Language Generation","date":"2019-05-14","arxiv_id":"1905.05513","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-recognition-system-for-recognizing","title":"End to End Recognition System for Recognizing Offline Unconstrained Vietnamese Handwriting","date":"2019-05-14","arxiv_id":"1905.05381","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-fine-tune-bert-for-text-classification","slug":"how-to-fine-tune-bert-for-text-classification","title":"How to Fine-Tune BERT for Text Classification?","date":"2019-05-14","arxiv_id":"1905.05583","n_code_links":15,"syntology":{"ran":12,"of":18,"n_ran_checked":7,"n_instrument":5,"unverified":6,"pointer_only":5,"phrase":"12 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; 5 where Syntology's instrument failed) · 6 unverified","official":{"repos":["xuyige/BERT4doc-Classification"],"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":["listed","official"]}}},{"paper":"/paper/learning-to-groove-with-inverse-sequence","slug":"learning-to-groove-with-inverse-sequence","title":"Learning to Groove with Inverse Sequence Transformations","date":"2019-05-14","arxiv_id":"1905.06118","n_code_links":1,"syntology":null},{"paper":"/paper/sense-vocabulary-compression-through-the","slug":"sense-vocabulary-compression-through-the","title":"Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation","date":"2019-05-14","arxiv_id":"1905.05677","n_code_links":2,"syntology":null},{"paper":null,"slug":"190508606","title":"VGG Fine-tuning for Cooking State Recognition","date":"2019-05-13","arxiv_id":"1905.08606","n_code_links":0,"syntology":null},{"paper":null,"slug":"almost-unsupervised-text-to-speech-and","title":"Almost Unsupervised Text to Speech and Automatic Speech Recognition","date":"2019-05-13","arxiv_id":"1905.06791","n_code_links":0,"syntology":null},{"paper":"/paper/cutmix-regularization-strategy-to-train","slug":"cutmix-regularization-strategy-to-train","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","date":"2019-05-13","arxiv_id":"1905.04899","n_code_links":30,"syntology":{"ran":17,"of":24,"n_ran_checked":11,"n_instrument":6,"unverified":7,"pointer_only":5,"phrase":"17 ran (of which 6 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 7 unverified","official":{"repos":["clovaai/CutMix-PyTorch"],"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/synchronous-bidirectional-neural-machine","slug":"synchronous-bidirectional-neural-machine","title":"Synchronous Bidirectional Neural Machine Translation","date":"2019-05-13","arxiv_id":"1905.04847","n_code_links":2,"syntology":null},{"paper":"/paper/weakly-supervised-caricature-face-parsing","slug":"weakly-supervised-caricature-face-parsing","title":"Weakly-supervised Caricature Face Parsing through Domain Adaptation","date":"2019-05-13","arxiv_id":"1905.05091","n_code_links":1,"syntology":null},{"paper":null,"slug":"densifying-assumed-sparse-tensors-improving","title":"Densifying Assumed-sparse Tensors: Improving Memory Efficiency and MPI Collective Performance during Tensor Accumulation for Parallelized Training of Neural Machine Translation Models","date":"2019-05-10","arxiv_id":"1905.04035","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-modeling-with-deep-transformers","title":"Language Modeling with Deep Transformers","date":"2019-05-10","arxiv_id":"1905.04226","n_code_links":0,"syntology":null},{"paper":"/paper/using-syntactical-and-logical-forms-to","slug":"using-syntactical-and-logical-forms-to","title":"A logical-based corpus for cross-lingual evaluation","date":"2019-05-10","arxiv_id":"1905.05704","n_code_links":1,"syntology":null},{"paper":"/paper/190503381","slug":"190503381","title":"AutoAssist: A Framework to Accelerate Training of Deep Neural Networks","date":"2019-05-08","arxiv_id":"1905.03381","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/faq-retrieval-using-query-question-similarity","slug":"faq-retrieval-using-query-question-similarity","title":"FAQ Retrieval using Query-Question Similarity and BERT-Based Query-Answer Relevance","date":"2019-05-08","arxiv_id":"1905.02851","n_code_links":1,"syntology":null},{"paper":null,"slug":"photometric-transformer-networks-and-label","title":"Photometric Transformer Networks and Label Adjustment for Breast Density Prediction","date":"2019-05-08","arxiv_id":"1905.02906","n_code_links":0,"syntology":null},{"paper":"/paper/rwth-asr-systems-for-librispeech-hybrid-vs","slug":"rwth-asr-systems-for-librispeech-hybrid-vs","title":"RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation","date":"2019-05-08","arxiv_id":"1905.03072","n_code_links":2,"syntology":null},{"paper":"/paper/unified-language-model-pre-training-for","slug":"unified-language-model-pre-training-for","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","date":"2019-05-08","arxiv_id":"1905.03197","n_code_links":9,"syntology":null},{"paper":"/paper/a-modular-deep-learning-approach-for-extreme","slug":"a-modular-deep-learning-approach-for-extreme","title":"Taming Pretrained Transformers for Extreme Multi-label Text Classification","date":"2019-05-07","arxiv_id":"1905.02331","n_code_links":2,"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":["OctoberChang/X-Transformer"],"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":"/paper/mass-masked-sequence-to-sequence-pre-training","slug":"mass-masked-sequence-to-sequence-pre-training","title":"MASS: Masked Sequence to Sequence Pre-training for Language Generation","date":"2019-05-07","arxiv_id":"1905.02450","n_code_links":7,"syntology":null},{"paper":null,"slug":"uncertainty-aware-data-aggregation-for-deep","title":"Uncertainty-Aware Data Aggregation for Deep Imitation Learning","date":"2019-05-07","arxiv_id":"1905.02780","n_code_links":0,"syntology":null},{"paper":"/paper/anonymized-bert-an-augmentation-approach-to","slug":"anonymized-bert-an-augmentation-approach-to","title":"Anonymized BERT: An Augmentation Approach to the Gendered Pronoun Resolution Challenge","date":"2019-05-06","arxiv_id":"1905.01780","n_code_links":1,"syntology":null},{"paper":"/paper/pog-personalized-outfit-generation-for","slug":"pog-personalized-outfit-generation-for","title":"POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion","date":"2019-05-06","arxiv_id":"1905.01866","n_code_links":1,"syntology":null},{"paper":"/paper/searching-for-mobilenetv3","slug":"searching-for-mobilenetv3","title":"Searching for MobileNetV3","date":"2019-05-06","arxiv_id":"1905.02244","n_code_links":67,"syntology":{"ran":86,"of":105,"n_ran_checked":75,"n_instrument":11,"unverified":19,"pointer_only":46,"phrase":"86 ran (of which 22 constructed an object rather than computing a result; 75 with no instrument failure: 6 honoured, 2 violated, 67 with no contract checked; 11 where Syntology's instrument failed) · 19 unverified","official":null}},{"paper":null,"slug":"investigating-the-successes-and-failures-of","title":"Investigating the Successes and Failures of BERT for Passage Re-Ranking","date":"2019-05-05","arxiv_id":"1905.01758","n_code_links":0,"syntology":null},{"paper":null,"slug":"sinreq-generalized-sinusoidal-regularization","title":"SinReQ: Generalized Sinusoidal Regularization for Low-Bitwidth Deep Quantized Training","date":"2019-05-04","arxiv_id":"1905.01416","n_code_links":0,"syntology":null},{"paper":null,"slug":"directing-dnns-attention-for-facial","title":"Directing DNNs Attention for Facial Attribution Classification using Gradient-weighted Class Activation Mapping","date":"2019-05-02","arxiv_id":"1905.00593","n_code_links":0,"syntology":null},{"paper":null,"slug":"aligning-artificial-neural-networks-to-the","title":"Aligning Artificial Neural Networks to the Brain yields Shallow Recurrent Architectures","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bnn-improved-binary-network-training-1","title":"BNN+: Improved Binary Network Training","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cutting-down-training-memory-by-re-fowarding-1","title":"Cutting Down Training Memory by Re-fowarding","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-layers-as-stochastic-solvers","title":"Deep Layers as Stochastic Solvers","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-out-of-distribution-samples-using","title":"Detecting Out-Of-Distribution Samples Using Low-Order Deep Features Statistics","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/discourse-representation-structure-parsing-1","slug":"discourse-representation-structure-parsing-1","title":"Discourse Representation Structure Parsing with Recurrent Neural Networks and the Transformer Model","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/fast-autoaugment","slug":"fast-autoaugment","title":"Fast AutoAugment","date":"2019-05-01","arxiv_id":"1905.00397","n_code_links":11,"syntology":{"ran":37,"of":40,"n_ran_checked":21,"n_instrument":16,"unverified":3,"pointer_only":7,"phrase":"37 ran (of which 2 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 16 where Syntology's instrument failed) · 3 unverified","official":{"repos":["kakaobrain/fast-autoaugment"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"feed-forward-propagation-in-probabilistic","title":"Feed-forward Propagation in Probabilistic Neural Networks with Categorical and Max Layers","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-transformer","title":"Graph Transformer","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"jumpout-improved-dropout-for-deep-neural","title":"Jumpout: Improved Dropout for Deep Neural Networks with Rectified Linear Units","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-search-efficient-densenet-with","title":"Learning to Search Efficient DenseNet with Layer-wise Pruning","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multi-agent-dual-learning","slug":"multi-agent-dual-learning","title":"Multi-Agent Dual Learning","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-statistical-and-information","title":"On the Statistical and Information Theoretical Characteristics of DNN Representations","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"robustness-and-equivariance-of-neural","title":"Robustness and Equivariance of Neural Networks","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sufficient-conditions-for-robustness-to","title":"Sufficient Conditions for Robustness to Adversarial Examples: a Theoretical and Empirical Study with Bayesian Neural Networks","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"total-style-transfer-with-a-single-feed","title":"Total Style Transfer with a Single Feed-Forward Network","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-better-understanding-of-vector","title":"Towards a better understanding of Vector Quantized Autoencoders","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"traditional-and-heavy-tailed-self-1","title":"Traditional and Heavy Tailed Self Regularization in Neural Network Models","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-xl-language-modeling-with-longer","title":"Transformer-XL: Language Modeling with Longer-Term Dependency","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"what-a-difference-a-pixel-makes-an-empirical","title":"What a difference a pixel makes: An empirical examination of features used by CNNs for categorisation","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"resnet-can-be-pruned-60x-introducing-network","title":"ResNet Can Be Pruned 60x: Introducing Network Purification and Unused Path Removal (P-RM) after Weight Pruning","date":"2019-04-30","arxiv_id":"1905.00136","n_code_links":0,"syntology":null},{"paper":null,"slug":"very-deep-self-attention-networks-for-end-to","title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","date":"2019-04-30","arxiv_id":"1904.13377","n_code_links":0,"syntology":null},{"paper":null,"slug":"neuromorphic-acceleration-for-approximate","title":"Neuromorphic Acceleration for Approximate Bayesian Inference on Neural Networks via Permanent Dropout","date":"2019-04-29","arxiv_id":"1904.12904","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-data-augmentation-1","slug":"unsupervised-data-augmentation-1","title":"Unsupervised Data Augmentation for Consistency Training","date":"2019-04-29","arxiv_id":"1904.12848","n_code_links":20,"syntology":{"ran":30,"of":52,"n_ran_checked":22,"n_instrument":8,"unverified":22,"pointer_only":17,"phrase":"30 ran (of which 3 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified","official":{"repos":["google-research/uda"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":14,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"softmax-optimizations-for-intel-xeon","title":"Softmax Optimizations for Intel Xeon Processor-based Platforms","date":"2019-04-28","arxiv_id":"1904.12380","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-source-filter-waveform-models-for","title":"Neural source-filter waveform models for statistical parametric speech synthesis","date":"2019-04-27","arxiv_id":"1904.12088","n_code_links":0,"syntology":null},{"paper":"/paper/on-exact-computation-with-an-infinitely-wide","slug":"on-exact-computation-with-an-infinitely-wide","title":"On Exact Computation with an Infinitely Wide Neural Net","date":"2019-04-26","arxiv_id":"1904.11955","n_code_links":2,"syntology":null},{"paper":"/paper/transformers-with-convolutional-context-for","slug":"transformers-with-convolutional-context-for","title":"Transformers with convolutional context for ASR","date":"2019-04-26","arxiv_id":"1904.11660","n_code_links":4,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/190411486","slug":"190411486","title":"Making Convolutional Networks Shift-Invariant Again","date":"2019-04-25","arxiv_id":"1904.11486","n_code_links":7,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["adobe/antialiased-cnns"],"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":"survey-of-dropout-methods-for-deep-neural","title":"Survey of Dropout Methods for Deep Neural Networks","date":"2019-04-25","arxiv_id":"1904.13310","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-memory-neural-network-training-a","title":"Low-Memory Neural Network Training: A Technical Report","date":"2019-04-24","arxiv_id":"1904.10631","n_code_links":0,"syntology":null},{"paper":null,"slug":"prediction-of-progression-to-alzheimers","title":"Prediction of Progression to Alzheimer's disease with Deep InfoMax","date":"2019-04-24","arxiv_id":"1904.10931","n_code_links":0,"syntology":null},{"paper":"/paper/the-vgg-image-annotator-via","slug":"the-vgg-image-annotator-via","title":"The VIA Annotation Software for Images, Audio and Video","date":"2019-04-24","arxiv_id":"1904.10699","n_code_links":1,"syntology":null},{"paper":"/paper/190410509","slug":"190410509","title":"Generating Long Sequences with Sparse Transformers","date":"2019-04-23","arxiv_id":"1904.10509","n_code_links":7,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 4 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) · 1 unverified","official":{"repos":["openai/sparse_attention"],"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/lung-nodule-classification-using-deep-local","slug":"lung-nodule-classification-using-deep-local","title":"Lung Nodule Classification using Deep Local-Global Networks","date":"2019-04-23","arxiv_id":"1904.10126","n_code_links":1,"syntology":null},{"paper":"/paper/190409925","slug":"190409925","title":"Attention Augmented Convolutional Networks","date":"2019-04-22","arxiv_id":"1904.09925","n_code_links":14,"syntology":{"ran":3,"of":6,"n_ran_checked":1,"n_instrument":2,"unverified":3,"pointer_only":1,"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) · 3 unverified","official":null}},{"paper":"/paper/190411800","slug":"190411800","title":"Adaptive Matrix Completion for the Users and the Items in Tail","date":"2019-04-22","arxiv_id":"1904.11800","n_code_links":1,"syntology":null},{"paper":"/paper/190501969","slug":"190501969","title":"Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring","date":"2019-04-22","arxiv_id":"1905.01969","n_code_links":7,"syntology":null},{"paper":"/paper/adversarial-dropout-for-recurrent-neural","slug":"adversarial-dropout-for-recurrent-neural","title":"Adversarial Dropout for Recurrent Neural Networks","date":"2019-04-22","arxiv_id":"1904.09816","n_code_links":2,"syntology":null},{"paper":null,"slug":"190412613","title":"State Classification of Cooking Objects Using a VGG CNN","date":"2019-04-21","arxiv_id":"1904.12613","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-past-and-future-for-neural-machine","slug":"dynamic-past-and-future-for-neural-machine","title":"Dynamic Past and Future for Neural Machine Translation","date":"2019-04-21","arxiv_id":"1904.09646","n_code_links":1,"syntology":null},{"paper":null,"slug":"model-compression-with-multi-task-knowledge","title":"Model Compression with Multi-Task Knowledge Distillation for Web-scale Question Answering System","date":"2019-04-21","arxiv_id":"1904.09636","n_code_links":0,"syntology":null},{"paper":"/paper/190409380","slug":"190409380","title":"Repurposing Entailment for Multi-Hop Question Answering Tasks","date":"2019-04-20","arxiv_id":"1904.09380","n_code_links":4,"syntology":null},{"paper":"/paper/190409408","slug":"190409408","title":"Language Models with Transformers","date":"2019-04-20","arxiv_id":"1904.09408","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cgraywang/gluon-nlp-1"],"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"]}}},{"paper":"/paper/190409324","slug":"190409324","title":"Mask-Predict: Parallel Decoding of Conditional Masked Language Models","date":"2019-04-19","arxiv_id":"1904.09324","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/Mask-Predict"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"190501971","title":"An Evaluation of Transfer Learning for Classifying Sales Engagement Emails at Large Scale","date":"2019-04-19","arxiv_id":"1905.01971","n_code_links":0,"syntology":null},{"paper":"/paper/beto-bentz-becas-the-surprising-cross-lingual","slug":"beto-bentz-becas-the-surprising-cross-lingual","title":"Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT","date":"2019-04-19","arxiv_id":"1904.09077","n_code_links":2,"syntology":null},{"paper":"/paper/ernie-enhanced-representation-through","slug":"ernie-enhanced-representation-through","title":"ERNIE: Enhanced Representation through Knowledge Integration","date":"2019-04-19","arxiv_id":"1904.09223","n_code_links":19,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["PaddlePaddle/PaddleNLP"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"unifying-question-answering-and-text","title":"Unifying Question Answering, Text Classification, and Regression via Span Extraction","date":"2019-04-19","arxiv_id":"1904.09286","n_code_links":0,"syntology":null},{"paper":"/paper/190413216","slug":"190413216","title":"Signal2Image Modules in Deep Neural Networks for EEG Classification","date":"2019-04-18","arxiv_id":"1904.13216","n_code_links":1,"syntology":null},{"paper":null,"slug":"190501975","title":"Point-less: More Abstractive Summarization with Pointer-Generator Networks","date":"2019-04-18","arxiv_id":"1905.01975","n_code_links":0,"syntology":null},{"paper":"/paper/real-time-style-transfer-with-strength","slug":"real-time-style-transfer-with-strength","title":"Real-Time Style Transfer With Strength Control","date":"2019-04-18","arxiv_id":"1904.08643","n_code_links":1,"syntology":null},{"paper":"/paper/do-lateral-views-help-automated-chest-x-ray","slug":"do-lateral-views-help-automated-chest-x-ray","title":"Do Lateral Views Help Automated Chest X-ray Predictions?","date":"2019-04-17","arxiv_id":"1904.08534","n_code_links":1,"syntology":null},{"paper":"/paper/docbert-bert-for-document-classification","slug":"docbert-bert-for-document-classification","title":"DocBERT: BERT for Document Classification","date":"2019-04-17","arxiv_id":"1904.08398","n_code_links":3,"syntology":{"ran":11,"of":14,"n_ran_checked":11,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["castorini/hedwig"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"gaze-training-by-modulated-dropout-improves","title":"Gaze Training by Modulated Dropout Improves Imitation Learning","date":"2019-04-17","arxiv_id":"1904.08377","n_code_links":0,"syntology":null},{"paper":"/paper/sparseout-controlling-sparsity-in-deep","slug":"sparseout-controlling-sparsity-in-deep","title":"Sparseout: Controlling Sparsity in Deep Networks","date":"2019-04-17","arxiv_id":"1904.08050","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-empirical-evaluation-of-text","title":"An Empirical Evaluation of Text Representation Schemes on Multilingual Social Web to Filter the Textual Aggression","date":"2019-04-16","arxiv_id":"1904.08770","n_code_links":0,"syntology":null},{"paper":null,"slug":"double-transfer-learning-for-breast-cancer","title":"Double Transfer Learning for Breast Cancer Histopathologic Image Classification","date":"2019-04-16","arxiv_id":"1904.07834","n_code_links":0,"syntology":null},{"paper":null,"slug":"swtvm-exploring-the-automated-compilation-for","title":"swTVM: Towards Optimized Tensor Code Generation for Deep Learning on Sunway Many-Core Processor","date":"2019-04-16","arxiv_id":"1904.07404","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-the-behaviors-of-bert-in","title":"Understanding the Behaviors of BERT in Ranking","date":"2019-04-16","arxiv_id":"1904.07531","n_code_links":0,"syntology":null},{"paper":"/paper/190407094","slug":"190407094","title":"CEDR: Contextualized Embeddings for Document Ranking","date":"2019-04-15","arxiv_id":"1904.07094","n_code_links":7,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":2,"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) · 2 unverified","official":{"repos":["Georgetown-IR-Lab/cedr","Georgetown-IR-Lab/contextualized-reps-for-ranking"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"brain-tumor-segmentation-on-mri-with-missing","title":"Brain Tumor Segmentation on MRI with Missing Modalities","date":"2019-04-15","arxiv_id":"1904.07290","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-human-text-comprehension-through","title":"Improving Human Text Comprehension through Semi-Markov CRF-based Neural Section Title Generation","date":"2019-04-15","arxiv_id":"1904.07142","n_code_links":0,"syntology":null},{"paper":"/paper/personalized-context-aware-re-ranking-for-e","slug":"personalized-context-aware-re-ranking-for-e","title":"Personalized Re-ranking for Recommendation","date":"2019-04-15","arxiv_id":"1904.06813","n_code_links":1,"syntology":null},{"paper":null,"slug":"190412604","title":"Pre-training of Context-aware Item Representation for Next Basket Recommendation","date":"2019-04-14","arxiv_id":"1904.12604","n_code_links":0,"syntology":null},{"paper":"/paper/data-augmentation-for-bert-fine-tuning-in","slug":"data-augmentation-for-bert-fine-tuning-in","title":"Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering","date":"2019-04-14","arxiv_id":"1904.06652","n_code_links":0,"syntology":null},{"paper":"/paper/rare-words-a-major-problem-for-contextualized","slug":"rare-words-a-major-problem-for-contextualized","title":"Rare Words: A Major Problem for Contextualized Embeddings And How to Fix it by Attentive Mimicking","date":"2019-04-14","arxiv_id":"1904.06707","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["timoschick/am-for-bert","timoschick/one-token-approximation"],"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"]}}},{"paper":"/paper/shakeout-a-new-approach-to-regularized-deep","slug":"shakeout-a-new-approach-to-regularized-deep","title":"Shakeout: A New Approach to Regularized Deep Neural Network Training","date":"2019-04-13","arxiv_id":"1904.06593","n_code_links":1,"syntology":null},{"paper":null,"slug":"reliable-prediction-errors-for-deep-neural","title":"Reliable Prediction Errors for Deep Neural Networks Using Test-Time Dropout","date":"2019-04-12","arxiv_id":"1904.06330","n_code_links":0,"syntology":null}],"record_sha256":"ca7af0f9acb2b8755c8c2f094b69fc970c804d0acaf6e10102c457d25bf6e5ea","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}