{"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/249","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":249,"pages_in_order":275,"rows_per_page":100,"rows":[24801,24900],"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/248","next":"/method/dropout/papers/250","papers":[{"paper":null,"slug":"the-value-of-text-for-small-business-default","title":"The value of text for small business default prediction: A deep learning approach","date":"2020-03-19","arxiv_id":"2003.08964","n_code_links":0,"syntology":null},{"paper":"/paper/fixing-the-train-test-resolution-discrepancy-2","slug":"fixing-the-train-test-resolution-discrepancy-2","title":"Fixing the train-test resolution discrepancy: FixEfficientNet","date":"2020-03-18","arxiv_id":"2003.08237","n_code_links":1,"syntology":null},{"paper":null,"slug":"scene-text-recognition-via-transformer","title":"Scene Text Recognition via Transformer","date":"2020-03-18","arxiv_id":"2003.08077","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-networks-for-trajectory","slug":"transformer-networks-for-trajectory","title":"Transformer Networks for Trajectory Forecasting","date":"2020-03-18","arxiv_id":"2003.08111","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["FGiuliari/Trajectory-Transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/tttttackling-winogrande-schemas","slug":"tttttackling-winogrande-schemas","title":"TTTTTackling WinoGrande Schemas","date":"2020-03-18","arxiv_id":"2003.08380","n_code_links":0,"syntology":null},{"paper":"/paper/x-stance-a-multilingual-multi-target-dataset","slug":"x-stance-a-multilingual-multi-target-dataset","title":"X-Stance: A Multilingual Multi-Target Dataset for Stance Detection","date":"2020-03-18","arxiv_id":"2003.08385","n_code_links":1,"syntology":null},{"paper":null,"slug":"author2vec-a-framework-for-generating-user","title":"Author2Vec: A Framework for Generating User Embedding","date":"2020-03-17","arxiv_id":"2003.11627","n_code_links":0,"syntology":null},{"paper":"/paper/calibration-of-pre-trained-transformers","slug":"calibration-of-pre-trained-transformers","title":"Calibration of Pre-trained Transformers","date":"2020-03-17","arxiv_id":"2003.07892","n_code_links":1,"syntology":null},{"paper":"/paper/human-activity-recognition-from-wearable","slug":"human-activity-recognition-from-wearable","title":"Human Activity Recognition from Wearable Sensor Data Using Self-Attention","date":"2020-03-17","arxiv_id":"2003.09018","n_code_links":2,"syntology":null},{"paper":"/paper/multi-modal-dense-video-captioning","slug":"multi-modal-dense-video-captioning","title":"Multi-modal Dense Video Captioning","date":"2020-03-17","arxiv_id":"2003.07758","n_code_links":4,"syntology":null},{"paper":"/paper/po-emo-conceptualization-annotation-and","slug":"po-emo-conceptualization-annotation-and","title":"PO-EMO: Conceptualization, Annotation, and Modeling of Aesthetic Emotions in German and English Poetry","date":"2020-03-17","arxiv_id":"2003.07723","n_code_links":1,"syntology":null},{"paper":"/paper/rethinking-batch-normalization-in","slug":"rethinking-batch-normalization-in","title":"PowerNorm: Rethinking Batch Normalization in Transformers","date":"2020-03-17","arxiv_id":"2003.07845","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-contextual-embeddings","title":"A Survey on Contextual Embeddings","date":"2020-03-16","arxiv_id":"2003.07278","n_code_links":0,"syntology":null},{"paper":"/paper/cost-sensitive-bert-for-generalisable-1","slug":"cost-sensitive-bert-for-generalisable-1","title":"Cost-Sensitive BERT for Generalisable Sentence Classification with Imbalanced Data","date":"2020-03-16","arxiv_id":"2003.11563","n_code_links":1,"syntology":null},{"paper":null,"slug":"explaining-memorization-and-generalization-a","title":"Weak and Strong Gradient Directions: Explaining Memorization, Generalization, and Hardness of Examples at Scale","date":"2020-03-16","arxiv_id":"2003.07422","n_code_links":0,"syntology":null},{"paper":"/paper/trans-blstm-transformer-with-bidirectional","slug":"trans-blstm-transformer-with-bidirectional","title":"TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding","date":"2020-03-16","arxiv_id":"2003.07000","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-evaluation-of-advanced-deep","title":"Performance Evaluation of Advanced Deep Learning Architectures for Offline Handwritten Character Recognition","date":"2020-03-15","arxiv_id":"2003.06794","n_code_links":0,"syntology":null},{"paper":"/paper/document-ranking-with-a-pretrained-sequence","slug":"document-ranking-with-a-pretrained-sequence","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","date":"2020-03-14","arxiv_id":"2003.06713","n_code_links":2,"syntology":null},{"paper":null,"slug":"finnish-language-modeling-with-deep","title":"Finnish Language Modeling with Deep Transformer Models","date":"2020-03-14","arxiv_id":"2003.11562","n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-individual-dogs-in-social-media","title":"Identifying Individual Dogs in Social Media Images","date":"2020-03-14","arxiv_id":"2003.06705","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-deep-learning-methodologies-for-skin","title":"Advanced Deep Learning Methodologies for Skin Cancer Classification in Prodromal Stages","date":"2020-03-13","arxiv_id":"2003.06356","n_code_links":0,"syntology":null},{"paper":null,"slug":"b-pinns-bayesian-physics-informed-neural","title":"B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data","date":"2020-03-13","arxiv_id":"2003.06097","n_code_links":0,"syntology":null},{"paper":null,"slug":"edge-tailored-perception-fast-inferencing-in","title":"LCP: A Low-Communication Parallelization Method for Fast Neural Network Inference in Image Recognition","date":"2020-03-13","arxiv_id":"2003.06464","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-major-types-of-chinese-classical","title":"Generating Major Types of Chinese Classical Poetry in a Uniformed Framework","date":"2020-03-13","arxiv_id":"2003.11528","n_code_links":0,"syntology":null},{"paper":"/paper/gimme-signals-discriminative-signal-encoding","slug":"gimme-signals-discriminative-signal-encoding","title":"Gimme Signals: Discriminative signal encoding for multimodal activity recognition","date":"2020-03-13","arxiv_id":"2003.06156","n_code_links":2,"syntology":null},{"paper":"/paper/learning-to-encode-position-for-transformer","slug":"learning-to-encode-position-for-transformer","title":"Learning to Encode Position for Transformer with Continuous Dynamical Model","date":"2020-03-13","arxiv_id":"2003.09229","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":1,"n_instrument":2,"unverified":3,"pointer_only":6,"phrase":"3 ran (of which 2 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) · 3 unverified","official":null}},{"paper":null,"slug":"analyzing-visual-representations-in-embodied","title":"Analyzing Visual Representations in Embodied Navigation Tasks","date":"2020-03-12","arxiv_id":"2003.05993","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-content-based-sparse-attention-with-1","slug":"efficient-content-based-sparse-attention-with-1","title":"Efficient Content-Based Sparse Attention with Routing Transformers","date":"2020-03-12","arxiv_id":"2003.05997","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"syncgan-using-learnable-class-specific-priors","title":"SynCGAN: Using learnable class specific priors to generate synthetic data for improving classifier performance on cytological images","date":"2020-03-12","arxiv_id":"2003.05712","n_code_links":0,"syntology":null},{"paper":"/paper/hurtful-words-quantifying-biases-in-clinical","slug":"hurtful-words-quantifying-biases-in-clinical","title":"Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings","date":"2020-03-11","arxiv_id":"2003.11515","n_code_links":1,"syntology":null},{"paper":"/paper/investigating-entity-knowledge-in-bert-with-1","slug":"investigating-entity-knowledge-in-bert-with-1","title":"Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking","date":"2020-03-11","arxiv_id":"2003.05473","n_code_links":1,"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":["samuelbroscheit/entity_knowledge_in_bert"],"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":["official"]}}},{"paper":null,"slug":"kernel-quantization-for-efficient-network","title":"Kernel Quantization for Efficient Network Compression","date":"2020-03-11","arxiv_id":"2003.05148","n_code_links":0,"syntology":null},{"paper":"/paper/keyword-attentive-deep-semantic-matching","slug":"keyword-attentive-deep-semantic-matching","title":"Keyword-Attentive Deep Semantic Matching","date":"2020-03-11","arxiv_id":"2003.11516","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-intent-detection-with-dual-sentence","slug":"efficient-intent-detection-with-dual-sentence","title":"Efficient Intent Detection with Dual Sentence Encoders","date":"2020-03-10","arxiv_id":"2003.04807","n_code_links":5,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":null}},{"paper":null,"slug":"hybrid-attention-based-transformer-block","title":"Hybrid Attention-Based Transformer Block Model for Distant Supervision Relation Extraction","date":"2020-03-10","arxiv_id":"2003.11518","n_code_links":0,"syntology":null},{"paper":null,"slug":"prediction-of-bayesian-intervals-for-tropical","title":"Prediction of Bayesian Intervals for Tropical Storms","date":"2020-03-10","arxiv_id":"2003.05024","n_code_links":0,"syntology":null},{"paper":"/paper/rezero-is-all-you-need-fast-convergence-at","slug":"rezero-is-all-you-need-fast-convergence-at","title":"ReZero is All You Need: Fast Convergence at Large Depth","date":"2020-03-10","arxiv_id":"2003.04887","n_code_links":13,"syntology":{"ran":6,"of":6,"n_ran_checked":0,"n_instrument":6,"unverified":0,"pointer_only":0,"phrase":"6 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; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["majumderb/rezero"],"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/capacity-of-continuous-channels-with-memory","slug":"capacity-of-continuous-channels-with-memory","title":"Capacity of Continuous Channels with Memory via Directed Information Neural Estimator","date":"2020-03-09","arxiv_id":"2003.04179","n_code_links":1,"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: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/dual-attention-guided-dropblock-module-for","slug":"dual-attention-guided-dropblock-module-for","title":"Dual-attention Guided Dropblock Module for Weakly Supervised Object Localization","date":"2020-03-09","arxiv_id":"2003.04719","n_code_links":1,"syntology":null},{"paper":null,"slug":"implementation-of-deep-neural-networks-to","title":"Implementation of Deep Neural Networks to Classify EEG Signals using Gramian Angular Summation Field for Epilepsy Diagnosis","date":"2020-03-08","arxiv_id":"2003.04534","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-modal-learning-for-multi-modal-video","title":"Cross-modal Learning for Multi-modal Video Categorization","date":"2020-03-07","arxiv_id":"2003.03501","n_code_links":0,"syntology":null},{"paper":"/paper/salsanext-fast-semantic-segmentation-of-lidar","slug":"salsanext-fast-semantic-segmentation-of-lidar","title":"SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving","date":"2020-03-07","arxiv_id":"2003.03653","n_code_links":5,"syntology":{"ran":8,"of":11,"n_ran_checked":4,"n_instrument":4,"unverified":3,"pointer_only":1,"phrase":"8 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; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["TiagoCortinhal/SalsaNext"],"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","unlocated"]}}},{"paper":null,"slug":"ttpp-temporal-transformer-with-progressive","title":"TTPP: Temporal Transformer with Progressive Prediction for Efficient Action Anticipation","date":"2020-03-07","arxiv_id":"2003.03530","n_code_links":0,"syntology":null},{"paper":null,"slug":"dropout-explicit-forms-and-capacity-control-1","title":"Dropout: Explicit Forms and Capacity Control","date":"2020-03-06","arxiv_id":"2003.03397","n_code_links":0,"syntology":null},{"paper":"/paper/dropout-strikes-back-improved-uncertainty","slug":"dropout-strikes-back-improved-uncertainty","title":"Dropout Strikes Back: Improved Uncertainty Estimation via Diversity Sampling","date":"2020-03-06","arxiv_id":"2003.03274","n_code_links":1,"syntology":null},{"paper":null,"slug":"sensitive-data-detection-and-classification","title":"Sensitive Data Detection and Classification in Spanish Clinical Text: Experiments with BERT","date":"2020-03-06","arxiv_id":"2003.03106","n_code_links":0,"syntology":null},{"paper":"/paper/teaching-temporal-logics-to-neural-networks","slug":"teaching-temporal-logics-to-neural-networks","title":"Teaching Temporal Logics to Neural Networks","date":"2020-03-06","arxiv_id":"2003.04218","n_code_links":2,"syntology":{"ran":14,"of":24,"n_ran_checked":11,"n_instrument":3,"unverified":10,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","official":{"repos":["reactive-systems/deepltl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"transfer-learning-for-information-extraction","title":"Transfer Learning for Information Extraction with Limited Data","date":"2020-03-06","arxiv_id":"2003.03064","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-neural-connections-for-sparsity","slug":"adaptive-neural-connections-for-sparsity","title":"Adaptive Neural Connections for Sparsity Learning","date":"2020-03-05","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-robustness-through-local-2","slug":"adversarial-robustness-through-local-2","title":"A Closer Look at Accuracy vs. Robustness","date":"2020-03-05","arxiv_id":"2003.02460","n_code_links":1,"syntology":null},{"paper":"/paper/augmented-transformer-achieves-97-and-85-for","slug":"augmented-transformer-achieves-97-and-85-for","title":"State-of-the-Art Augmented NLP Transformer models for direct and single-step retrosynthesis","date":"2020-03-05","arxiv_id":"2003.02804","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-as-a-teacher-contextual-embeddings-for","title":"BERT as a Teacher: Contextual Embeddings for Sequence-Level Reward","date":"2020-03-05","arxiv_id":"2003.02738","n_code_links":0,"syntology":null},{"paper":"/paper/emptransfo-a-multi-head-transformer","slug":"emptransfo-a-multi-head-transformer","title":"EmpTransfo: A Multi-head Transformer Architecture for Creating Empathetic Dialog Systems","date":"2020-03-05","arxiv_id":"2003.02958","n_code_links":1,"syntology":null},{"paper":null,"slug":"hyponli-exploring-the-artificial-patterns-of","title":"HypoNLI: Exploring the Artificial Patterns of Hypothesis-only Bias in Natural Language Inference","date":"2020-03-05","arxiv_id":"2003.02756","n_code_links":0,"syntology":null},{"paper":"/paper/recipegpt-generative-pre-training-based","slug":"recipegpt-generative-pre-training-based","title":"RecipeGPT: Generative Pre-training Based Cooking Recipe Generation and Evaluation System","date":"2020-03-05","arxiv_id":"2003.02498","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-the-mask-making-sense-of-language","title":"What the [MASK]? Making Sense of Language-Specific BERT Models","date":"2020-03-05","arxiv_id":"2003.02912","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-on-efficiency-accuracy-and-document","title":"A Study on Efficiency, Accuracy and Document Structure for Answer Sentence Selection","date":"2020-03-04","arxiv_id":"2003.02349","n_code_links":0,"syntology":null},{"paper":"/paper/aligntts-efficient-feed-forward-text-to","slug":"aligntts-efficient-feed-forward-text-to","title":"AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment","date":"2020-03-04","arxiv_id":"2003.01950","n_code_links":2,"syntology":{"ran":3,"of":6,"n_ran_checked":1,"n_instrument":2,"unverified":3,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/data-augmentation-using-pre-trained","slug":"data-augmentation-using-pre-trained","title":"Data Augmentation using Pre-trained Transformer Models","date":"2020-03-04","arxiv_id":"2003.02245","n_code_links":4,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["varinf/TransformersDataAugmentation"],"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/jiant-a-software-toolkit-for-research-on","slug":"jiant-a-software-toolkit-for-research-on","title":"jiant: A Software Toolkit for Research on General-Purpose Text Understanding Models","date":"2020-03-04","arxiv_id":"2003.02249","n_code_links":6,"syntology":{"ran":6,"of":8,"n_ran_checked":4,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["nyu-mll/jiant"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"kleister-a-novel-task-for-information","title":"Kleister: A novel task for Information Extraction involving Long Documents with Complex Layout","date":"2020-03-04","arxiv_id":"2003.02356","n_code_links":0,"syntology":null},{"paper":"/paper/cluecorpus2020-a-large-scale-chinese-corpus","slug":"cluecorpus2020-a-large-scale-chinese-corpus","title":"CLUECorpus2020: A Large-scale Chinese Corpus for Pre-training Language Model","date":"2020-03-03","arxiv_id":"2003.01355","n_code_links":2,"syntology":null},{"paper":null,"slug":"controllable-time-delay-transformer-for-real","title":"Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection","date":"2020-03-03","arxiv_id":"2003.01309","n_code_links":0,"syntology":null},{"paper":null,"slug":"deepsperm-a-robust-and-real-time-bull-sperm","title":"DeepSperm: A robust and real-time bull sperm-cell detection in densely populated semen videos","date":"2020-03-03","arxiv_id":"2003.01395","n_code_links":0,"syntology":null},{"paper":"/paper/heterogeneous-graph-transformer","slug":"heterogeneous-graph-transformer","title":"Heterogeneous Graph Transformer","date":"2020-03-03","arxiv_id":"2003.01332","n_code_links":4,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"pointer_only":3,"phrase":"2 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; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["acbull/pyHGT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hierarchical-context-enhanced-multi-domain","title":"Hierarchical Context Enhanced Multi-Domain Dialogue System for Multi-domain Task Completion","date":"2020-03-03","arxiv_id":"2003.01338","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-generative-retrieval-transformers-for","title":"Hybrid Generative-Retrieval Transformers for Dialogue Domain Adaptation","date":"2020-03-03","arxiv_id":"2003.01680","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-embeddings-based-on-self-attention","title":"Meta-Embeddings Based On Self-Attention","date":"2020-03-03","arxiv_id":"2003.01371","n_code_links":0,"syntology":null},{"paper":"/paper/mpc-guided-imitation-learning-of-neural","slug":"mpc-guided-imitation-learning-of-neural","title":"MPC-guided Imitation Learning of Neural Network Policies for the Artificial Pancreas","date":"2020-03-03","arxiv_id":"2003.01283","n_code_links":1,"syntology":null},{"paper":null,"slug":"transfer-learning-for-context-aware-spoken","title":"Transfer Learning for Context-Aware Spoken Language Understanding","date":"2020-03-03","arxiv_id":"2003.01305","n_code_links":0,"syntology":null},{"paper":null,"slug":"disease-detection-from-lung-x-ray-images","title":"Hybrid Deep Learning for Detecting Lung Diseases from X-ray Images","date":"2020-03-02","arxiv_id":"2003.00682","n_code_links":0,"syntology":null},{"paper":"/paper/fast-predictive-uncertainty-for","slug":"fast-predictive-uncertainty-for","title":"Fast Predictive Uncertainty for Classification with Bayesian Deep Networks","date":"2020-03-02","arxiv_id":"2003.01227","n_code_links":1,"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: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mariushobbhahn/LB_for_BNNs_official"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fiedler-regularization-learning-neural","title":"Fiedler Regularization: Learning Neural Networks with Graph Sparsity","date":"2020-03-02","arxiv_id":"2003.00992","n_code_links":0,"syntology":null},{"paper":"/paper/inferring-the-source-of-official-texts-can","slug":"inferring-the-source-of-official-texts-can","title":"Inferring the source of official texts: can SVM beat ULMFiT?","date":"2020-03-02","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer","title":"Transformer++","date":"2020-03-02","arxiv_id":"2003.04974","n_code_links":0,"syntology":null},{"paper":null,"slug":"stein-variational-inference-for-discrete","title":"Stein Variational Inference for Discrete Distributions","date":"2020-03-01","arxiv_id":"2003.00605","n_code_links":0,"syntology":null},{"paper":"/paper/arabert-transformer-based-model-for-arabic","slug":"arabert-transformer-based-model-for-arabic","title":"AraBERT: Transformer-based Model for Arabic Language Understanding","date":"2020-02-28","arxiv_id":"2003.00104","n_code_links":4,"syntology":null},{"paper":"/paper/automatic-perturbation-analysis-on-general","slug":"automatic-perturbation-analysis-on-general","title":"Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond","date":"2020-02-28","arxiv_id":"2002.12920","n_code_links":7,"syntology":{"ran":14,"of":18,"n_ran_checked":13,"n_instrument":1,"unverified":4,"pointer_only":2,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 2 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["KaidiXu/auto_LiRPA"],"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":"dc-bert-decoupling-question-and-document-for","title":"DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding","date":"2020-02-28","arxiv_id":"2002.12591","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficiently-guiding-imitation-learning","title":"Efficiently Guiding Imitation Learning Agents with Human Gaze","date":"2020-02-28","arxiv_id":"2002.12500","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-and-distilling-cross-modal","title":"Exploring and Distilling Cross-Modal Information for Image Captioning","date":"2020-02-28","arxiv_id":"2002.12585","n_code_links":0,"syntology":null},{"paper":null,"slug":"learned-threshold-pruning","title":"Learned Threshold Pruning","date":"2020-02-28","arxiv_id":"2003.00075","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantile-regularization-towards-implicit","title":"Quantile Regularization: Towards Implicit Calibration of Regression Models","date":"2020-02-28","arxiv_id":"2002.12860","n_code_links":0,"syntology":null},{"paper":"/paper/textbrewer-an-open-source-knowledge","slug":"textbrewer-an-open-source-knowledge","title":"TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing","date":"2020-02-28","arxiv_id":"2002.12620","n_code_links":1,"syntology":null},{"paper":"/paper/the-implicit-and-explicit-regularization","slug":"the-implicit-and-explicit-regularization","title":"The Implicit and Explicit Regularization Effects of Dropout","date":"2020-02-28","arxiv_id":"2002.12915","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-primer-in-bertology-what-we-know-about-how","title":"A Primer in BERTology: What we know about how BERT works","date":"2020-02-27","arxiv_id":"2002.12327","n_code_links":0,"syntology":null},{"paper":null,"slug":"adv-bert-bert-is-not-robust-on-misspellings","title":"Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT","date":"2020-02-27","arxiv_id":"2003.04985","n_code_links":0,"syntology":null},{"paper":null,"slug":"compressing-large-scale-transformer-based","title":"Compressing Large-Scale Transformer-Based Models: A Case Study on BERT","date":"2020-02-27","arxiv_id":"2002.11985","n_code_links":0,"syntology":null},{"paper":"/paper/rnnpool-efficient-non-linear-pooling-for-ram","slug":"rnnpool-efficient-non-linear-pooling-for-ram","title":"RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference","date":"2020-02-27","arxiv_id":"2002.11921","n_code_links":4,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["Microsoft/EdgeML"],"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/marathi-to-english-neural-machine-translation","slug":"marathi-to-english-neural-machine-translation","title":"Marathi To English Neural Machine Translation With Near Perfect Corpus And Transformers","date":"2020-02-26","arxiv_id":"2002.11643","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-task-learning-with-multi-head-attention","title":"Multi-task Learning with Multi-head Attention for Multi-choice Reading Comprehension","date":"2020-02-26","arxiv_id":"2003.04992","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-sinkhorn-attention","slug":"sparse-sinkhorn-attention","title":"Sparse Sinkhorn Attention","date":"2020-02-26","arxiv_id":"2002.11296","n_code_links":1,"syntology":null},{"paper":"/paper/train-large-then-compress-rethinking-model","slug":"train-large-then-compress-rethinking-model","title":"Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers","date":"2020-02-26","arxiv_id":"2002.11794","n_code_links":2,"syntology":null},{"paper":"/paper/200210957","slug":"200210957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","date":"2020-02-25","arxiv_id":"2002.10957","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-can-see-out-of-the-box-on-the-cross","title":"What BERT Sees: Cross-Modal Transfer for Visual Question Generation","date":"2020-02-25","arxiv_id":"2002.10832","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-bert-parameter-efficiency-on-the","title":"Exploring BERT Parameter Efficiency on the Stanford Question Answering Dataset v2.0","date":"2020-02-25","arxiv_id":"2002.10670","n_code_links":0,"syntology":null},{"paper":null,"slug":"fixed-encoder-self-attention-patterns-in","title":"Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translation","date":"2020-02-24","arxiv_id":"2002.10260","n_code_links":0,"syntology":null},{"paper":null,"slug":"gret-global-representation-enhanced","title":"GRET: Global Representation Enhanced Transformer","date":"2020-02-24","arxiv_id":"2002.10101","n_code_links":0,"syntology":null},{"paper":"/paper/improving-bert-fine-tuning-via-self-ensemble","slug":"improving-bert-fine-tuning-via-self-ensemble","title":"Improving BERT Fine-Tuning via Self-Ensemble and Self-Distillation","date":"2020-02-24","arxiv_id":"2002.10345","n_code_links":1,"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: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/predicting-subjective-features-from-questions","slug":"predicting-subjective-features-from-questions","title":"Predicting Subjective Features of Questions of QA Websites using BERT","date":"2020-02-24","arxiv_id":"2002.10107","n_code_links":5,"syntology":null}],"record_sha256":"1932411325a90c6006bb4fe6d0fc3587fd8e12e7457d5e8c2634bc5762128492","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}