{"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/185","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":185,"pages_in_order":275,"rows_per_page":100,"rows":[18401,18500],"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/184","next":"/method/dropout/papers/186","papers":[{"paper":null,"slug":"unleashing-the-power-of-transformer-for","title":"Unleashing the Power of Transformer for Graphs","date":"2022-02-18","arxiv_id":"2202.10581","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hybrid-2-stage-vision-transformer-for-ai","title":"Multi-Scale Hybrid Vision Transformer for Learning Gastric Histology: AI-Based Decision Support System for Gastric Cancer Treatment","date":"2022-02-17","arxiv_id":"2202.08510","n_code_links":0,"syntology":null},{"paper":null,"slug":"baddr-bayes-adaptive-deep-dropout-rl-for","title":"BADDr: Bayes-Adaptive Deep Dropout RL for POMDPs","date":"2022-02-17","arxiv_id":"2202.08884","n_code_links":0,"syntology":null},{"paper":"/paper/designing-effective-sparse-expert-models","slug":"designing-effective-sparse-expert-models","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","date":"2022-02-17","arxiv_id":"2202.08906","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tensorflow/mesh"],"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":"end-to-end-neuron-instance-segmentation-based","title":"A General Deep Learning framework for Neuron Instance Segmentation based on Efficient UNet and Morphological Post-processing","date":"2022-02-17","arxiv_id":"2202.08682","n_code_links":0,"syntology":null},{"paper":"/paper/graph-masked-autoencoder","slug":"graph-masked-autoencoder","title":"Graph Masked Autoencoders with Transformers","date":"2022-02-17","arxiv_id":"2202.08391","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-english-to-sinhala-neural-machine","title":"Improving English to Sinhala Neural Machine Translation using Part-of-Speech Tag","date":"2022-02-17","arxiv_id":"2202.08882","n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-over-smoothing-in-bert-from-the-1","title":"Revisiting Over-smoothing in BERT from the Perspective of Graph","date":"2022-02-17","arxiv_id":"2202.08625","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantically-proportional-patchmix-for-few","title":"Semantically Proportional Patchmix for Few-Shot Learning","date":"2022-02-17","arxiv_id":"2202.08647","n_code_links":0,"syntology":null},{"paper":"/paper/sgpt-gpt-sentence-embeddings-for-semantic","slug":"sgpt-gpt-sentence-embeddings-for-semantic","title":"SGPT: GPT Sentence Embeddings for Semantic Search","date":"2022-02-17","arxiv_id":"2202.08904","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["muennighoff/sgpt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/transformer-for-graphs-an-overview-from","slug":"transformer-for-graphs-an-overview-from","title":"Transformer for Graphs: An Overview from Architecture Perspective","date":"2022-02-17","arxiv_id":"2202.08455","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["qwerfdsaplking/graph-trans"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"trasetr-track-to-segment-transformer-with","title":"TraSeTR: Track-to-Segment Transformer with Contrastive Query for Instance-level Instrument Segmentation in Robotic Surgery","date":"2022-02-17","arxiv_id":"2202.08453","n_code_links":0,"syntology":null},{"paper":null,"slug":"when-bert-meets-quantum-temporal-convolution","title":"When BERT Meets Quantum Temporal Convolution Learning for Text Classification in Heterogeneous Computing","date":"2022-02-17","arxiv_id":"2203.03550","n_code_links":0,"syntology":null},{"paper":"/paper/a-survey-of-pretraining-on-graphs-taxonomy","slug":"a-survey-of-pretraining-on-graphs-taxonomy","title":"A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applications","date":"2022-02-16","arxiv_id":"2202.07893","n_code_links":3,"syntology":null},{"paper":"/paper/actionformer-localizing-moments-of-actions","slug":"actionformer-localizing-moments-of-actions","title":"ActionFormer: Localizing Moments of Actions with Transformers","date":"2022-02-16","arxiv_id":"2202.07925","n_code_links":1,"syntology":null},{"paper":"/paper/edgeformer-a-parameter-efficient-transformer","slug":"edgeformer-a-parameter-efficient-transformer","title":"EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation","date":"2022-02-16","arxiv_id":"2202.07959","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["microsoft/unilm"],"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":["found_in_text"]}}},{"paper":null,"slug":"no-one-left-behind-inclusive-federated","title":"No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices","date":"2022-02-16","arxiv_id":"2202.08036","n_code_links":0,"syntology":null},{"paper":"/paper/probing-pretrained-models-of-source-code","slug":"probing-pretrained-models-of-source-code","title":"Probing Pretrained Models of Source Code","date":"2022-02-16","arxiv_id":"2202.08975","n_code_links":1,"syntology":null},{"paper":null,"slug":"singing-tacotron-global-duration-control","title":"Singing-Tacotron: Global duration control attention and dynamic filter for End-to-end singing voice synthesis","date":"2022-02-16","arxiv_id":"2202.07907","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-learning-phases-in-nn-from-fitting-the","title":"The learning phases in NN: From Fitting the Majority to Fitting a Few","date":"2022-02-16","arxiv_id":"2202.08299","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-nlp-task-effectiveness-of-long-range","title":"The NLP Task Effectiveness of Long-Range Transformers","date":"2022-02-16","arxiv_id":"2202.07856","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-dynamic-neural-networks-for","title":"A Survey on Dynamic Neural Networks for Natural Language Processing","date":"2022-02-15","arxiv_id":"2202.07101","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-model-compression-for-natural","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","date":"2022-02-15","arxiv_id":"2202.07105","n_code_links":0,"syntology":null},{"paper":null,"slug":"blue-at-memotion-2-0-2022-you-have-my-image","title":"BLUE at Memotion 2.0 2022: You have my Image, my Text and my Transformer","date":"2022-02-15","arxiv_id":"2202.07543","n_code_links":0,"syntology":null},{"paper":null,"slug":"defending-against-reconstruction-attacks-with","title":"Defending against Reconstruction Attacks with Rényi Differential Privacy","date":"2022-02-15","arxiv_id":"2202.07623","n_code_links":0,"syntology":null},{"paper":"/paper/improving-the-repeatability-of-deep-learning","slug":"improving-the-repeatability-of-deep-learning","title":"Improving the repeatability of deep learning models with Monte Carlo dropout","date":"2022-02-15","arxiv_id":"2202.07562","n_code_links":1,"syntology":null},{"paper":"/paper/one-configuration-to-rule-them-all-towards","slug":"one-configuration-to-rule-them-all-towards","title":"One Configuration to Rule Them All? Towards Hyperparameter Transfer in Topic Models using Multi-Objective Bayesian Optimization","date":"2022-02-15","arxiv_id":"2202.07631","n_code_links":1,"syntology":null},{"paper":"/paper/personalized-prompt-learning-for-explainable","slug":"personalized-prompt-learning-for-explainable","title":"Personalized Prompt Learning for Explainable Recommendation","date":"2022-02-15","arxiv_id":"2202.07371","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-on-the-edge-identifying-where-a","title":"Predicting on the Edge: Identifying Where a Larger Model Does Better","date":"2022-02-15","arxiv_id":"2202.07652","n_code_links":0,"syntology":null},{"paper":"/paper/prior-gradient-mask-guided-pruning-aware-fine","slug":"prior-gradient-mask-guided-pruning-aware-fine","title":"Prior Gradient Mask Guided Pruning-Aware Fine-Tuning","date":"2022-02-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/tomayto-tomahto-beyond-token-level-answer","slug":"tomayto-tomahto-beyond-token-level-answer","title":"Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation","date":"2022-02-15","arxiv_id":"2202.07654","n_code_links":1,"syntology":null},{"paper":null,"slug":"toxic-comments-hunter-score-severity-of-toxic","title":"Toxic Comments Hunter : Score Severity of Toxic Comments","date":"2022-02-15","arxiv_id":"2203.03548","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-in-time-series-a-survey","slug":"transformers-in-time-series-a-survey","title":"Transformers in Time Series: A Survey","date":"2022-02-15","arxiv_id":"2202.07125","n_code_links":11,"syntology":null},{"paper":null,"slug":"vinter-image-narrative-generation-with","title":"ViNTER: Image Narrative Generation with Emotion-Arc-Aware Transformer","date":"2022-02-15","arxiv_id":"2202.07305","n_code_links":0,"syntology":null},{"paper":"/paper/xai-for-transformers-better-explanations","slug":"xai-for-transformers-better-explanations","title":"XAI for Transformers: Better Explanations through Conservative Propagation","date":"2022-02-15","arxiv_id":"2202.07304","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":10,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ameenali/xai_transformers"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/codefill-multi-token-code-completion-by","slug":"codefill-multi-token-code-completion-by","title":"CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences","date":"2022-02-14","arxiv_id":"2202.06689","n_code_links":1,"syntology":null},{"paper":"/paper/geometric-transformer-for-fast-and-robust","slug":"geometric-transformer-for-fast-and-robust","title":"Geometric Transformer for Fast and Robust Point Cloud Registration","date":"2022-02-14","arxiv_id":"2202.06688","n_code_links":2,"syntology":{"ran":4,"of":9,"n_ran_checked":4,"n_instrument":0,"unverified":5,"pointer_only":9,"phrase":"4 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; 0 where Syntology's instrument failed) · 5 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["qinzheng93/geotransformer"],"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/handcrafted-histological-transformer-h2t","slug":"handcrafted-histological-transformer-h2t","title":"Handcrafted Histological Transformer (H2T): Unsupervised Representation of Whole Slide Images","date":"2022-02-14","arxiv_id":"2202.07001","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":["vqdang/h2t"],"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":"/paper/mixing-and-shifting-exploiting-global-and","slug":"mixing-and-shifting-exploiting-global-and","title":"Mixing and Shifting: Exploiting Global and Local Dependencies in Vision MLPs","date":"2022-02-14","arxiv_id":"2202.06510","n_code_links":2,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":6,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jegzheng/ms-mlp"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"punctuation-restoration-in-swedish-through","title":"Punctuation restoration in Swedish through fine-tuned KB-BERT","date":"2022-02-14","arxiv_id":"2202.06769","n_code_links":0,"syntology":null},{"paper":"/paper/qa4qg-using-question-answering-to-constrain","slug":"qa4qg-using-question-answering-to-constrain","title":"QA4QG: Using Question Answering to Constrain Multi-Hop Question Generation","date":"2022-02-14","arxiv_id":"2202.06538","n_code_links":1,"syntology":null},{"paper":"/paper/sequence-to-sequence-resources-for-catalan","slug":"sequence-to-sequence-resources-for-catalan","title":"Sequence-to-Sequence Resources for Catalan","date":"2022-02-14","arxiv_id":"2202.06871","n_code_links":1,"syntology":null},{"paper":"/paper/source-code-summarization-with-structural","slug":"source-code-summarization-with-structural","title":"Source Code Summarization with Structural Relative Position Guided Transformer","date":"2022-02-14","arxiv_id":"2202.06521","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-memory-as-a-differentiable-search","slug":"transformer-memory-as-a-differentiable-search","title":"Transformer Memory as a Differentiable Search Index","date":"2022-02-14","arxiv_id":"2202.06991","n_code_links":1,"syntology":null},{"paper":null,"slug":"userbert-modeling-long-and-short-term-user","title":"UserBERT: Modeling Long- and Short-Term User Preferences via Self-Supervision","date":"2022-02-14","arxiv_id":"2202.07605","n_code_links":0,"syntology":null},{"paper":"/paper/what-do-they-capture-a-structural-analysis-of","slug":"what-do-they-capture-a-structural-analysis-of","title":"What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Code","date":"2022-02-14","arxiv_id":"2202.06840","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessment-of-contextualised-representations","title":"Assessment of contextualised representations in detecting outcome phrases in clinical trials","date":"2022-02-13","arxiv_id":"2203.03547","n_code_links":0,"syntology":null},{"paper":"/paper/bvit-broad-attention-based-vision-transformer","slug":"bvit-broad-attention-based-vision-transformer","title":"BViT: Broad Attention based Vision Transformer","date":"2022-02-13","arxiv_id":"2202.06268","n_code_links":1,"syntology":null},{"paper":"/paper/et-bert-a-contextualized-datagram","slug":"et-bert-a-contextualized-datagram","title":"ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification","date":"2022-02-13","arxiv_id":"2202.06335","n_code_links":1,"syntology":null},{"paper":null,"slug":"lightn-light-weight-transformer-network-for","title":"LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsampling","date":"2022-02-13","arxiv_id":"2202.06263","n_code_links":0,"syntology":null},{"paper":null,"slug":"lmn-at-semeval-2022-task-11-a-transformer","title":"LMN at SemEval-2022 Task 11: A Transformer-based System for English Named Entity Recognition","date":"2022-02-13","arxiv_id":"2203.03546","n_code_links":0,"syntology":null},{"paper":"/paper/a-multi-task-semi-supervised-framework-for","slug":"a-multi-task-semi-supervised-framework-for","title":"A multi-task semi-supervised framework for Text2Graph & Graph2Text","date":"2022-02-12","arxiv_id":"2202.06041","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-issue-classifier-a-transfer","slug":"automatic-issue-classifier-a-transfer","title":"Automatic Issue Classifier: A Transfer Learning Framework for Classifying Issue Reports","date":"2022-02-12","arxiv_id":"2202.06149","n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmark-assessment-for-deepspeed","title":"Benchmark Assessment for DeepSpeed Optimization Library","date":"2022-02-12","arxiv_id":"2202.12831","n_code_links":0,"syntology":null},{"paper":"/paper/maximizing-communication-efficiency-for-large","slug":"maximizing-communication-efficiency-for-large","title":"Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam","date":"2022-02-12","arxiv_id":"2202.06009","n_code_links":1,"syntology":null},{"paper":"/paper/multi-direction-and-multi-scale-pyramid-in","slug":"multi-direction-and-multi-scale-pyramid-in","title":"Multi-direction and Multi-scale Pyramid in Transformer for Video-based Pedestrian Retrieval","date":"2022-02-12","arxiv_id":"2202.06014","n_code_links":1,"syntology":null},{"paper":"/paper/multi-direction-and-multi-scale-pyramid-in-1","slug":"multi-direction-and-multi-scale-pyramid-in-1","title":"Multi-direction and Multi-scale Pyramid in Transformer for Video-based Pedestrian Retrieval","date":"2022-02-12","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"hat5-hate-language-identification-using-text","title":"HaT5: Hate Language Identification using Text-to-Text Transfer Transformer","date":"2022-02-11","arxiv_id":"2202.05690","n_code_links":0,"syntology":null},{"paper":null,"slug":"including-facial-expressions-in-contextual","title":"Including Facial Expressions in Contextual Embeddings for Sign Language Generation","date":"2022-02-11","arxiv_id":"2202.05383","n_code_links":0,"syntology":null},{"paper":"/paper/white-box-attacks-on-hate-speech-bert","slug":"white-box-attacks-on-hate-speech-bert","title":"White-Box Attacks on Hate-speech BERT Classifiers in German with Explicit and Implicit Character Level Defense","date":"2022-02-11","arxiv_id":"2202.05778","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-task-learning-framework-for-product","title":"A Multi-task Learning Framework for Product Ranking with BERT","date":"2022-02-10","arxiv_id":"2202.05317","n_code_links":0,"syntology":null},{"paper":"/paper/aa-transunet-attention-augmented-transunet","slug":"aa-transunet-attention-augmented-transunet","title":"AA-TransUNet: Attention Augmented TransUNet For Nowcasting Tasks","date":"2022-02-10","arxiv_id":"2202.04996","n_code_links":1,"syntology":null},{"paper":null,"slug":"ppa-preference-profiling-attack-against","title":"PPA: Preference Profiling Attack Against Federated Learning","date":"2022-02-10","arxiv_id":"2202.04856","n_code_links":0,"syntology":null},{"paper":"/paper/quantune-post-training-quantization-of","slug":"quantune-post-training-quantization-of","title":"Quantune: Post-training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast Deployment","date":"2022-02-10","arxiv_id":"2202.05048","n_code_links":1,"syntology":null},{"paper":null,"slug":"slovene-superglue-benchmark-translation-and","title":"Slovene SuperGLUE Benchmark: Translation and Evaluation","date":"2022-02-10","arxiv_id":"2202.04994","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-open-domain-question-answering-systems","title":"Can Open Domain Question Answering Systems Answer Visual Knowledge Questions?","date":"2022-02-09","arxiv_id":"2202.04306","n_code_links":0,"syntology":null},{"paper":"/paper/deep-feature-rotation-for-multimodal-image-1","slug":"deep-feature-rotation-for-multimodal-image-1","title":"Deep Feature Rotation for Multimodal Image Style Transfer","date":"2022-02-09","arxiv_id":"2202.04426","n_code_links":1,"syntology":null},{"paper":null,"slug":"merit-based-fusion-of-nlp-techniques-for","title":"Social Media as an Instant Source of Feedback on Water Quality","date":"2022-02-09","arxiv_id":"2202.04462","n_code_links":0,"syntology":null},{"paper":"/paper/pnlp-mixer-an-efficient-all-mlp-architecture","slug":"pnlp-mixer-an-efficient-all-mlp-architecture","title":"pNLP-Mixer: an Efficient all-MLP Architecture for Language","date":"2022-02-09","arxiv_id":"2202.04350","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-volcspeech-system-for-the-icassp-2022","title":"The Volcspeech system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge","date":"2022-02-09","arxiv_id":"2202.04261","n_code_links":0,"syntology":null},{"paper":null,"slug":"calm-contrastive-aligned-audio-language","title":"CALM: Contrastive Aligned Audio-Language Multirate and Multimodal Representations","date":"2022-02-08","arxiv_id":"2202.03587","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-language-models-learn-position-role","title":"Do Language Models Learn Position-Role Mappings?","date":"2022-02-08","arxiv_id":"2202.03611","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficacy-of-transformer-networks-for","title":"Efficacy of Transformer Networks for Classification of Raw EEG Data","date":"2022-02-08","arxiv_id":"2202.05170","n_code_links":0,"syntology":null},{"paper":"/paper/histbert-a-pre-trained-language-model-for","slug":"histbert-a-pre-trained-language-model-for","title":"HistBERT: A Pre-trained Language Model for Diachronic Lexical Semantic Analysis","date":"2022-02-08","arxiv_id":"2202.03612","n_code_links":1,"syntology":null},{"paper":null,"slug":"logical-reasoning-for-task-oriented-dialogue","title":"Logical Reasoning for Task Oriented Dialogue Systems","date":"2022-02-08","arxiv_id":"2202.04161","n_code_links":0,"syntology":null},{"paper":"/paper/particle-transformer-for-jet-tagging","slug":"particle-transformer-for-jet-tagging","title":"Particle Transformer for Jet Tagging","date":"2022-02-08","arxiv_id":"2202.03772","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jet-universe/particle_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/semantic-features-of-object-concepts","slug":"semantic-features-of-object-concepts","title":"Semantic features of object concepts generated with GPT-3","date":"2022-02-08","arxiv_id":"2202.03753","n_code_links":1,"syntology":null},{"paper":null,"slug":"swiftagg-communication-efficient-and-dropout","title":"SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guarantees","date":"2022-02-08","arxiv_id":"2202.04169","n_code_links":0,"syntology":null},{"paper":"/paper/transformnet-self-supervised-representation","slug":"transformnet-self-supervised-representation","title":"TransformNet: Self-supervised representation learning through predicting geometric transformations","date":"2022-02-08","arxiv_id":"2202.04181","n_code_links":1,"syntology":null},{"paper":null,"slug":"unsupervised-time-series-representation","title":"Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion","date":"2022-02-08","arxiv_id":"2202.04770","n_code_links":0,"syntology":null},{"paper":"/paper/what-are-the-best-systems-new-perspectives-on","slug":"what-are-the-best-systems-new-perspectives-on","title":"What are the best systems? New perspectives on NLP Benchmarking","date":"2022-02-08","arxiv_id":"2202.03799","n_code_links":1,"syntology":null},{"paper":"/paper/cedille-a-large-autoregressive-french","slug":"cedille-a-large-autoregressive-french","title":"Cedille: A large autoregressive French language model","date":"2022-02-07","arxiv_id":"2202.03371","n_code_links":1,"syntology":null},{"paper":"/paper/data2vec-a-general-framework-for-self-1","slug":"data2vec-a-general-framework-for-self-1","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","date":"2022-02-07","arxiv_id":"2202.03555","n_code_links":12,"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":{"repos":["pytorch/fairseq"],"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/deepssn-a-deep-convolutional-neural-network","slug":"deepssn-a-deep-convolutional-neural-network","title":"DeepSSN: a deep convolutional neural network to assess spatial scene similarity","date":"2022-02-07","arxiv_id":"2202.04755","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-adapter-transfer-of-self-supervised","slug":"efficient-adapter-transfer-of-self-supervised","title":"Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech Recognition","date":"2022-02-07","arxiv_id":"2202.03218","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"recent-trends-in-2d-object-detection-and","title":"Recent Trends in 2D Object Detection and Applications in Video Event Recognition","date":"2022-02-07","arxiv_id":"2202.03206","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-dialogue-state-tracking-with-weak","title":"Robust Dialogue State Tracking with Weak Supervision and Sparse Data","date":"2022-02-07","arxiv_id":"2202.03354","n_code_links":0,"syntology":null},{"paper":"/paper/structure-aware-transformer-for-graph","slug":"structure-aware-transformer-for-graph","title":"Structure-Aware Transformer for Graph Representation Learning","date":"2022-02-07","arxiv_id":"2202.03036","n_code_links":3,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["borgwardtlab/sat"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/unifying-architectures-tasks-and-modalities","slug":"unifying-architectures-tasks-and-modalities","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","date":"2022-02-07","arxiv_id":"2202.03052","n_code_links":4,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ofa-sys/ofa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/user-satisfaction-estimation-with-sequential","slug":"user-satisfaction-estimation-with-sequential","title":"User Satisfaction Estimation with Sequential Dialogue Act Modeling in Goal-oriented Conversational Systems","date":"2022-02-07","arxiv_id":"2202.02912","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-natural-language-processing-models","slug":"evaluating-natural-language-processing-models","title":"Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data","date":"2022-02-06","arxiv_id":"2202.02842","n_code_links":1,"syntology":null},{"paper":"/paper/no-parameters-left-behind-sensitivity-guided-1","slug":"no-parameters-left-behind-sensitivity-guided-1","title":"No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models","date":"2022-02-06","arxiv_id":"2202.02664","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cliang1453/sage"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"classification-on-sentence-embeddings-for","title":"Classification on Sentence Embeddings for Legal Assistance","date":"2022-02-05","arxiv_id":"2202.02639","n_code_links":0,"syntology":null},{"paper":null,"slug":"ethics-rules-of-engagement-and-ai-neural","title":"Ethics, Rules of Engagement, and AI: Neural Narrative Mapping Using Large Transformer Language Models","date":"2022-02-05","arxiv_id":"2202.02647","n_code_links":0,"syntology":null},{"paper":"/paper/a-benchmark-corpus-for-the-detection-of","slug":"a-benchmark-corpus-for-the-detection-of","title":"A Benchmark Corpus for the Detection of Automatically Generated Text in Academic Publications","date":"2022-02-04","arxiv_id":"2202.02013","n_code_links":1,"syntology":null},{"paper":"/paper/image-to-image-mlp-mixer-for-image-1","slug":"image-to-image-mlp-mixer-for-image-1","title":"Image-to-Image MLP-mixer for Image Reconstruction","date":"2022-02-04","arxiv_id":"2202.02018","n_code_links":1,"syntology":null},{"paper":null,"slug":"pre-trained-neural-language-models-for","title":"Pre-Trained Neural Language Models for Automatic Mobile App User Feedback Answer Generation","date":"2022-02-04","arxiv_id":"2202.02294","n_code_links":0,"syntology":null},{"paper":null,"slug":"stonkbert-can-language-models-predict-medium","title":"StonkBERT: Can Language Models Predict Medium-Run Stock Price Movements?","date":"2022-02-04","arxiv_id":"2202.02268","n_code_links":0,"syntology":null},{"paper":"/paper/supervised-contrastive-learning-for-product","slug":"supervised-contrastive-learning-for-product","title":"Supervised Contrastive Learning for Product Matching","date":"2022-02-04","arxiv_id":"2202.02098","n_code_links":1,"syntology":null},{"paper":"/paper/temporal-attention-for-language-models","slug":"temporal-attention-for-language-models","title":"Temporal Attention for Language Models","date":"2022-02-04","arxiv_id":"2202.02093","n_code_links":1,"syntology":null}],"record_sha256":"0cf87828167587edb7bc2e4d983d193922b8d1ada8761d08c84d925472108809","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}