{"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/residual-connection/papers/230","list_of":"/method/residual-connection","method":"Residual Connection","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":230,"pages_in_order":285,"rows_per_page":100,"rows":[22901,23000],"of":28401,"counts":{"archive_papers_tagged":28401,"with_a_code_link":12847,"where_syntology_ran_a_sample":3897,"not_listed_spam_title":0,"listed":28401,"listed_where_code_ran":3897,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3291,"every_run_a_failure_of_syntologys_instrument":606,"listed_with_a_run_with_no_instrument_failure":3291,"listed_every_run_a_failure_of_syntologys_instrument":606,"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/residual-connection","prev":"/method/residual-connection/papers/229","next":"/method/residual-connection/papers/231","papers":[{"paper":null,"slug":"end-to-end-acoustic-modelling-for-phone","title":"End-to-end acoustic modelling for phone recognition of young readers","date":"2021-03-04","arxiv_id":"2103.02899","n_code_links":0,"syntology":null},{"paper":"/paper/extract-the-knowledge-of-graph-neural","slug":"extract-the-knowledge-of-graph-neural","title":"Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework","date":"2021-03-04","arxiv_id":"2103.02885","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"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) · 1 unverified","official":{"repos":["BUPT-GAMMA/CPF"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hardware-acceleration-of-fully-quantized-bert","title":"Hardware Acceleration of Fully Quantized BERT for Efficient Natural Language Processing","date":"2021-03-04","arxiv_id":"2103.02800","n_code_links":0,"syntology":null},{"paper":"/paper/the-transformer-network-for-the-traveling","slug":"the-transformer-network-for-the-traveling","title":"The Transformer Network for the Traveling Salesman Problem","date":"2021-03-04","arxiv_id":"2103.03012","n_code_links":1,"syntology":null},{"paper":null,"slug":"few-shot-learning-for-slot-tagging-with","title":"Few-shot Learning for Slot Tagging with Attentive Relational Network","date":"2021-03-03","arxiv_id":"2103.02333","n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-language-understanding-for","title":"Natural Language Understanding for Argumentative Dialogue Systems in the Opinion Building Domain","date":"2021-03-03","arxiv_id":"2103.02691","n_code_links":0,"syntology":null},{"paper":null,"slug":"sensing-population-distribution-from","title":"Sensing population distribution from satellite imagery via deep learning: model selection, neighboring effect, and systematic biases","date":"2021-03-03","arxiv_id":"2103.02155","n_code_links":0,"syntology":null},{"paper":null,"slug":"university-of-copenhagen-participation-in","title":"University of Copenhagen Participation in TREC Health Misinformation Track 2020","date":"2021-03-03","arxiv_id":"2103.02462","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hint-from-arithmetic-on-systematic","title":"A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics","date":"2021-03-02","arxiv_id":"2103.01403","n_code_links":0,"syntology":null},{"paper":null,"slug":"decomposing-lexical-and-compositional-syntax","title":"Disentangling Syntax and Semantics in the Brain with Deep Networks","date":"2021-03-02","arxiv_id":"2103.01620","n_code_links":0,"syntology":null},{"paper":null,"slug":"dual-reinforcement-based-specification","title":"Dual Reinforcement-Based Specification Generation for Image De-Rendering","date":"2021-03-02","arxiv_id":"2103.01867","n_code_links":0,"syntology":null},{"paper":null,"slug":"hate-towards-the-political-opponent-a-twitter","title":"Hate Towards the Political Opponent: A Twitter Corpus Study of the 2020 US Elections on the Basis of Offensive Speech and Stance Detection","date":"2021-03-02","arxiv_id":"2103.01664","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-product-description-generation-via","title":"Probing Product Description Generation via Posterior Distillation","date":"2021-03-02","arxiv_id":"2103.01594","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-pretraining-of-visual","slug":"self-supervised-pretraining-of-visual","title":"Self-supervised Pretraining of Visual Features in the Wild","date":"2021-03-02","arxiv_id":"2103.01988","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-cnns-to-identify-the-origin-of-finger","title":"Using CNNs to Identify the Origin of Finger Vein Image","date":"2021-03-02","arxiv_id":"2103.01632","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-based-knowledge-extraction-method-of","title":"BERT-based knowledge extraction method of unstructured domain text","date":"2021-03-01","arxiv_id":"2103.00728","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-based-patent-novelty-search-by-training","title":"BERT based patent novelty search by training claims to their own description","date":"2021-03-01","arxiv_id":"2103.01126","n_code_links":0,"syntology":null},{"paper":null,"slug":"brain-programming-is-immune-to-adversarial","title":"Brain Programming is Immune to Adversarial Attacks: Towards Accurate and Robust Image Classification using Symbolic Learning","date":"2021-03-01","arxiv_id":"2103.01359","n_code_links":0,"syntology":null},{"paper":null,"slug":"combat-covid-19-infodemic-using-explainable","title":"Combat COVID-19 Infodemic Using Explainable Natural Language Processing Models","date":"2021-03-01","arxiv_id":"2103.00747","n_code_links":0,"syntology":null},{"paper":"/paper/convolutional-normalization-improving-deep","slug":"convolutional-normalization-improving-deep","title":"Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training","date":"2021-03-01","arxiv_id":"2103.00673","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":6,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["shengliu66/ConvNorm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"crossmap-transformer-a-crossmodal-masked-path","title":"CrossMap Transformer: A Crossmodal Masked Path Transformer Using Double Back-Translation for Vision-and-Language Navigation","date":"2021-03-01","arxiv_id":"2103.00852","n_code_links":0,"syntology":null},{"paper":"/paper/dtw-merge-a-novel-data-augmentation-technique","slug":"dtw-merge-a-novel-data-augmentation-technique","title":"DTW-Merge: A Novel Data Augmentation Technique for Time Series Classification","date":"2021-03-01","arxiv_id":"2103.01119","n_code_links":1,"syntology":null},{"paper":null,"slug":"long-document-summarization-in-a-low-resource","title":"Long Document Summarization in a Low Resource Setting using Pretrained Language Models","date":"2021-03-01","arxiv_id":"2103.00751","n_code_links":0,"syntology":null},{"paper":"/paper/over-sampling-de-occlusion-attention-network","slug":"over-sampling-de-occlusion-attention-network","title":"Over-sampling De-occlusion Attention Network for Prohibited Items Detection in Noisy X-ray Images","date":"2021-03-01","arxiv_id":"2103.00809","n_code_links":1,"syntology":null},{"paper":null,"slug":"nlp-cuet-dravidianlangtech-eacl2021","title":"NLP-CUET@DravidianLangTech-EACL2021: Investigating Visual and Textual Features to Identify Trolls from Multimodal Social Media Memes","date":"2021-02-28","arxiv_id":"2103.00466","n_code_links":0,"syntology":null},{"paper":"/paper/nlp-cuet-dravidianlangtech-eacl2021-offensive","slug":"nlp-cuet-dravidianlangtech-eacl2021-offensive","title":"NLP-CUET@DravidianLangTech-EACL2021: Offensive Language Detection from Multilingual Code-Mixed Text using Transformers","date":"2021-02-28","arxiv_id":"2103.00455","n_code_links":1,"syntology":null},{"paper":"/paper/nlp-cuet-lt-edi-eacl2021-multilingual-code","slug":"nlp-cuet-lt-edi-eacl2021-multilingual-code","title":"NLP-CUET@LT-EDI-EACL2021: Multilingual Code-Mixed Hope Speech Detection using Cross-lingual Representation Learner","date":"2021-02-28","arxiv_id":"2103.00464","n_code_links":1,"syntology":null},{"paper":"/paper/ultra-data-efficient-gan-training-drawing-a","slug":"ultra-data-efficient-gan-training-drawing-a","title":"Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective","date":"2021-02-28","arxiv_id":"2103.00397","n_code_links":1,"syntology":null},{"paper":"/paper/covid-19-tweets-analysis-through-transformer","slug":"covid-19-tweets-analysis-through-transformer","title":"COVID-19 Tweets Analysis through Transformer Language Models","date":"2021-02-27","arxiv_id":"2103.00199","n_code_links":1,"syntology":null},{"paper":"/paper/generative-chemical-transformer-attention","slug":"generative-chemical-transformer-attention","title":"Generative Chemical Transformer: Neural Machine Learning of Molecular Geometric Structures from Chemical Language via Attention","date":"2021-02-27","arxiv_id":"2103.00213","n_code_links":2,"syntology":null},{"paper":"/paper/transformer-in-transformer","slug":"transformer-in-transformer","title":"Transformer in Transformer","date":"2021-02-27","arxiv_id":"2103.00112","n_code_links":12,"syntology":{"ran":16,"of":24,"n_ran_checked":15,"n_instrument":1,"unverified":8,"pointer_only":5,"phrase":"16 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 1 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","official":{"repos":["huawei-noah/CV-backbones"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"transformers-with-competitive-ensembles-of-1","title":"Transformers with Competitive Ensembles of Independent Mechanisms","date":"2021-02-27","arxiv_id":"2103.00336","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-transfer-learning-for-finding","title":"Multi-task transfer learning for finding actionable information from crisis-related messages on social media","date":"2021-02-26","arxiv_id":"2102.13395","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-framework-for-pruning-deep-neural-networks","title":"A Framework For Pruning Deep Neural Networks Using Energy-Based Models","date":"2021-02-25","arxiv_id":"2102.13188","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-based-acronym-disambiguation-with","title":"BERT-based Acronym Disambiguation with Multiple Training Strategies","date":"2021-02-25","arxiv_id":"2103.00488","n_code_links":0,"syntology":null},{"paper":"/paper/bridging-adversarial-and-statistical-domain","slug":"bridging-adversarial-and-statistical-domain","title":"Bridging Adversarial and Statistical Domain Transfer via Spectral Adaptation Networks","date":"2021-02-25","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"emotion-aware-emotion-agnostic-or-automatic","title":"Emotion-Aware, Emotion-Agnostic, or Automatic: Corpus Creation Strategies to Obtain Cognitive Event Appraisal Annotations","date":"2021-02-25","arxiv_id":"2102.12858","n_code_links":0,"syntology":null},{"paper":"/paper/even-your-teacher-needs-guidance-ground-truth","slug":"even-your-teacher-needs-guidance-ground-truth","title":"Even your Teacher Needs Guidance: Ground-Truth Targets Dampen Regularization Imposed by Self-Distillation","date":"2021-02-25","arxiv_id":"2102.13088","n_code_links":1,"syntology":null},{"paper":null,"slug":"highly-efficient-representation-and-active","title":"Highly Efficient Representation and Active Learning Framework and Its Application to Imbalanced Medical Image Classification","date":"2021-02-25","arxiv_id":"2103.05109","n_code_links":0,"syntology":null},{"paper":null,"slug":"lazyformer-self-attention-with-lazy-update","title":"LazyFormer: Self Attention with Lazy Update","date":"2021-02-25","arxiv_id":"2102.12702","n_code_links":0,"syntology":null},{"paper":"/paper/let-linguistic-knowledge-enhanced-graph","slug":"let-linguistic-knowledge-enhanced-graph","title":"LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching","date":"2021-02-25","arxiv_id":"2102.12671","n_code_links":1,"syntology":null},{"paper":null,"slug":"mixspeech-data-augmentation-for-low-resource","title":"MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition","date":"2021-02-25","arxiv_id":"2102.12664","n_code_links":0,"syntology":null},{"paper":null,"slug":"pharmke-knowledge-extraction-platform-for","title":"PharmKE: Knowledge Extraction Platform for Pharmaceutical Texts using Transfer Learning","date":"2021-02-25","arxiv_id":"2102.13139","n_code_links":0,"syntology":null},{"paper":"/paper/sentiment-analysis-of-persian-english-code","slug":"sentiment-analysis-of-persian-english-code","title":"Sentiment Analysis of Persian-English Code-mixed Texts","date":"2021-02-25","arxiv_id":"2102.12700","n_code_links":1,"syntology":null},{"paper":"/paper/visualizing-muzero-models","slug":"visualizing-muzero-models","title":"Visualizing MuZero Models","date":"2021-02-25","arxiv_id":"2102.12924","n_code_links":1,"syntology":null},{"paper":null,"slug":"combining-off-and-on-policy-training-in-model","title":"Combining Off and On-Policy Training in Model-Based Reinforcement Learning","date":"2021-02-24","arxiv_id":"2102.12194","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-universal-language-model-to-downstream","title":"From Universal Language Model to Downstream Task: Improving RoBERTa-Based Vietnamese Hate Speech Detection","date":"2021-02-24","arxiv_id":"2102.12162","n_code_links":0,"syntology":null},{"paper":null,"slug":"hopeful-men-lt-edi-eacl2021-hope-speech","title":"Hopeful_Men@LT-EDI-EACL2021: Hope Speech Detection Using Indic Transliteration and Transformers","date":"2021-02-24","arxiv_id":"2102.12082","n_code_links":0,"syntology":null},{"paper":"/paper/lrg-at-semeval-2021-task-4-improving-reading","slug":"lrg-at-semeval-2021-task-4-improving-reading","title":"LRG at SemEval-2021 Task 4: Improving Reading Comprehension with Abstract Words using Augmentation, Linguistic Features and Voting","date":"2021-02-24","arxiv_id":"2102.12255","n_code_links":1,"syntology":null},{"paper":"/paper/nlrg-at-semeval-2021-task-5-toxic-spans","slug":"nlrg-at-semeval-2021-task-5-toxic-spans","title":"NLRG at SemEval-2021 Task 5: Toxic Spans Detection Leveraging BERT-based Token Classification and Span Prediction Techniques","date":"2021-02-24","arxiv_id":"2102.12254","n_code_links":1,"syntology":null},{"paper":"/paper/pada-a-prompt-based-autoregressive-approach","slug":"pada-a-prompt-based-autoregressive-approach","title":"PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains","date":"2021-02-24","arxiv_id":"2102.12206","n_code_links":1,"syntology":null},{"paper":"/paper/pyramid-vision-transformer-a-versatile","slug":"pyramid-vision-transformer-a-versatile","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","date":"2021-02-24","arxiv_id":"2102.12122","n_code_links":11,"syntology":{"ran":22,"of":30,"n_ran_checked":18,"n_instrument":4,"unverified":8,"pointer_only":1,"phrase":"22 ran (of which 16 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 0 violated, 16 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","official":{"repos":["whai362/PVT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"railway-anomaly-detection-model-using","title":"Railway Anomaly detection model using synthetic defect images generated by CycleGAN","date":"2021-02-24","arxiv_id":"2102.12595","n_code_links":0,"syntology":null},{"paper":null,"slug":"task-specific-pre-training-and-cross-lingual","title":"Task-Specific Pre-Training and Cross Lingual Transfer for Code-Switched Data","date":"2021-02-24","arxiv_id":"2102.12407","n_code_links":0,"syntology":null},{"paper":"/paper/when-attention-meets-fast-recurrence-training","slug":"when-attention-meets-fast-recurrence-training","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","date":"2021-02-24","arxiv_id":"2102.12459","n_code_links":1,"syntology":null},{"paper":"/paper/accurate-learning-of-graph-representations-1","slug":"accurate-learning-of-graph-representations-1","title":"Accurate Learning of Graph Representations with Graph Multiset Pooling","date":"2021-02-23","arxiv_id":"2102.11533","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["JinheonBaek/GMT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deep-deformation-detail-synthesis-for-thin","title":"Deep Deformation Detail Synthesis for Thin Shell Models","date":"2021-02-23","arxiv_id":"2102.11541","n_code_links":0,"syntology":null},{"paper":"/paper/do-transformer-modifications-transfer-across","slug":"do-transformer-modifications-transfer-across","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","date":"2021-02-23","arxiv_id":"2102.11972","n_code_links":1,"syntology":null},{"paper":"/paper/histo-fetch-on-the-fly-processing-of","slug":"histo-fetch-on-the-fly-processing-of","title":"Histo-fetch -- On-the-fly processing of gigapixel whole slide images simplifies and speeds neural network training","date":"2021-02-23","arxiv_id":"2102.11433","n_code_links":1,"syntology":null},{"paper":null,"slug":"minimally-supervised-structure-rich-text","title":"Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks","date":"2021-02-23","arxiv_id":"2102.11479","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-and-transferable-anomaly-detection-in","title":"Robust and Transferable Anomaly Detection in Log Data using Pre-Trained Language Models","date":"2021-02-23","arxiv_id":"2102.11570","n_code_links":0,"syntology":null},{"paper":"/paper/sise-pc-semi-supervised-image-subsampling-for","slug":"sise-pc-semi-supervised-image-subsampling-for","title":"SISE-PC: Semi-supervised Image Subsampling for Explainable Pathology","date":"2021-02-23","arxiv_id":"2102.11560","n_code_links":1,"syntology":null},{"paper":"/paper/visualchexbert-addressing-the-discrepancy","slug":"visualchexbert-addressing-the-discrepancy","title":"VisualCheXbert: Addressing the Discrepancy Between Radiology Report Labels and Image Labels","date":"2021-02-23","arxiv_id":"2102.11467","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["stanfordmlgroup/VisualCheXbert"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"wavelet-transform-analytics-for-rf-based-uav","title":"Wavelet Transform Analytics for RF-Based UAV Detection and Identification System Using Machine Learning","date":"2021-02-23","arxiv_id":"2102.11894","n_code_links":0,"syntology":null},{"paper":"/paper/cstr-a-classification-perspective-on-scene","slug":"cstr-a-classification-perspective-on-scene","title":"Revisiting Classification Perspective on Scene Text Recognition","date":"2021-02-22","arxiv_id":"2102.10884","n_code_links":1,"syntology":null},{"paper":"/paper/deepfake-video-detection-using-convolutional","slug":"deepfake-video-detection-using-convolutional","title":"Deepfake Video Detection Using Convolutional Vision Transformer","date":"2021-02-22","arxiv_id":"2102.11126","n_code_links":1,"syntology":null},{"paper":null,"slug":"determination-of-fault-location-in","title":"Determination of Fault Location in Transmission Lines with Image Processing and Artificial Neural Networks","date":"2021-02-22","arxiv_id":"2102.11073","n_code_links":0,"syntology":null},{"paper":"/paper/do-we-really-need-explicit-position-encodings","slug":"do-we-really-need-explicit-position-encodings","title":"Conditional Positional Encodings for Vision Transformers","date":"2021-02-22","arxiv_id":"2102.10882","n_code_links":2,"syntology":null},{"paper":"/paper/evaluating-contextualized-language-models-for","slug":"evaluating-contextualized-language-models-for","title":"Evaluating Contextualized Language Models for Hungarian","date":"2021-02-22","arxiv_id":"2102.10848","n_code_links":1,"syntology":null},{"paper":null,"slug":"few-shot-learning-for-information","title":"Few Shot Learning for Information Verification","date":"2021-02-22","arxiv_id":"2102.10956","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-human-readable-transcript-for","title":"Generating Human Readable Transcript for Automatic Speech Recognition with Pre-trained Language Model","date":"2021-02-22","arxiv_id":"2102.11114","n_code_links":0,"syntology":null},{"paper":"/paper/lightweight-combinational-machine-learning","slug":"lightweight-combinational-machine-learning","title":"Lightweight Combinational Machine Learning Algorithm for Sorting Canine Torso Radiographs","date":"2021-02-22","arxiv_id":"2102.11385","n_code_links":1,"syntology":null},{"paper":null,"slug":"mixup-training-leads-to-reduced-overfitting","title":"MixUp Training Leads to Reduced Overfitting and Improved Calibration for the Transformer Architecture","date":"2021-02-22","arxiv_id":"2102.11402","n_code_links":0,"syntology":null},{"paper":"/paper/parallelizing-legendre-memory-unit-training","slug":"parallelizing-legendre-memory-unit-training","title":"Parallelizing Legendre Memory Unit Training","date":"2021-02-22","arxiv_id":"2102.11417","n_code_links":2,"syntology":null},{"paper":null,"slug":"position-information-in-transformers-an","title":"Position Information in Transformers: An Overview","date":"2021-02-22","arxiv_id":"2102.11090","n_code_links":0,"syntology":null},{"paper":null,"slug":"rubert-a-bilingual-roman-urdu-bert-using","title":"RUBERT: A Bilingual Roman Urdu BERT Using Cross Lingual Transfer Learning","date":"2021-02-22","arxiv_id":"2102.11278","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-is-all-you-need-multimodal","slug":"transformer-is-all-you-need-multimodal","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","date":"2021-02-22","arxiv_id":"2102.10772","n_code_links":1,"syntology":null},{"paper":"/paper/using-prior-knowledge-to-guide-bert-s","slug":"using-prior-knowledge-to-guide-bert-s","title":"Using Prior Knowledge to Guide BERT's Attention in Semantic Textual Matching Tasks","date":"2021-02-22","arxiv_id":"2102.10934","n_code_links":1,"syntology":null},{"paper":"/paper/medical-transformer-gated-axial-attention-for","slug":"medical-transformer-gated-axial-attention-for","title":"Medical Transformer: Gated Axial-Attention for Medical Image Segmentation","date":"2021-02-21","arxiv_id":"2102.10662","n_code_links":2,"syntology":null},{"paper":null,"slug":"pre-training-bert-on-arabic-tweets-practical","title":"Pre-Training BERT on Arabic Tweets: Practical Considerations","date":"2021-02-21","arxiv_id":"2102.10684","n_code_links":0,"syntology":null},{"paper":null,"slug":"web-based-application-for-detecting","title":"Web-based Application for Detecting Indonesian Clickbait Headlines using IndoBERT","date":"2021-02-21","arxiv_id":"2102.10601","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-answer-sentence-reranking-via","title":"Multilingual Answer Sentence Reranking via Automatically Translated Data","date":"2021-02-20","arxiv_id":"2102.10250","n_code_links":0,"syntology":null},{"paper":"/paper/towards-accurate-and-compact-architectures","slug":"towards-accurate-and-compact-architectures","title":"Towards Accurate and Compact Architectures via Neural Architecture Transformer","date":"2021-02-20","arxiv_id":"2102.10301","n_code_links":2,"syntology":null},{"paper":"/paper/a-deep-graph-wavelet-convolutional-neural","slug":"a-deep-graph-wavelet-convolutional-neural","title":"A Deep Graph Wavelet Convolutional Neural Network for Semi-supervised Node Classification","date":"2021-02-19","arxiv_id":"2102.09780","n_code_links":1,"syntology":null},{"paper":"/paper/calibrate-before-use-improving-few-shot","slug":"calibrate-before-use-improving-few-shot","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","date":"2021-02-19","arxiv_id":"2102.09690","n_code_links":5,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"0 ran · 4 unverified","official":{"repos":["tonyzhaozh/few-shot-learning"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":null,"slug":"dialect-identification-in-nuanced-arabic","title":"Dialect Identification in Nuanced Arabic Tweets Using Farasa Segmentation and AraBERT","date":"2021-02-19","arxiv_id":"2102.09749","n_code_links":0,"syntology":null},{"paper":"/paper/latent-variable-nested-set-transformers","slug":"latent-variable-nested-set-transformers","title":"Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction","date":"2021-02-19","arxiv_id":"2104.00563","n_code_links":2,"syntology":{"ran":11,"of":17,"n_ran_checked":10,"n_instrument":1,"unverified":6,"pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["roggirg/AutoBots"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"learning-dynamic-bert-via-trainable-gate","title":"Learning Dynamic BERT via Trainable Gate Variables and a Bi-modal Regularizer","date":"2021-02-19","arxiv_id":"2102.09727","n_code_links":0,"syntology":null},{"paper":null,"slug":"lottery-ticket-implies-accuracy-degradation","title":"Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?","date":"2021-02-19","arxiv_id":"2102.11068","n_code_links":0,"syntology":null},{"paper":"/paper/towards-emotion-recognition-in-hindi-english","slug":"towards-emotion-recognition-in-hindi-english","title":"Towards Emotion Recognition in Hindi-English Code-Mixed Data: A Transformer Based Approach","date":"2021-02-19","arxiv_id":"2102.09943","n_code_links":1,"syntology":null},{"paper":"/paper/training-cascaded-networks-for-speeded","slug":"training-cascaded-networks-for-speeded","title":"Improving Anytime Prediction with Parallel Cascaded Networks and a Temporal-Difference Loss","date":"2021-02-19","arxiv_id":"2102.09808","n_code_links":1,"syntology":null},{"paper":"/paper/using-transformer-based-ensemble-learning-to","slug":"using-transformer-based-ensemble-learning-to","title":"Using Transformer based Ensemble Learning to classify Scientific Articles","date":"2021-02-19","arxiv_id":"2102.09991","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-mathematical-principle-of-deep-learning","title":"A Mathematical Principle of Deep Learning: Learn the Geodesic Curve in the Wasserstein Space","date":"2021-02-18","arxiv_id":"2102.09235","n_code_links":0,"syntology":null},{"paper":"/paper/analysis-of-contextual-and-non-contextual","slug":"analysis-of-contextual-and-non-contextual","title":"Analysis Of Contextual and Non-Contextual Word Embedding Models For Hindi NER With Web Application For Data Collection","date":"2021-02-18","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/going-full-tilt-boogie-on-document","slug":"going-full-tilt-boogie-on-document","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","date":"2021-02-18","arxiv_id":"2102.09550","n_code_links":1,"syntology":null},{"paper":"/paper/quiz-style-question-generation-for-news","slug":"quiz-style-question-generation-for-news","title":"Quiz-Style Question Generation for News Stories","date":"2021-02-18","arxiv_id":"2102.09094","n_code_links":2,"syntology":null},{"paper":"/paper/recurrent-rational-networks","slug":"recurrent-rational-networks","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","date":"2021-02-18","arxiv_id":"2102.09407","n_code_links":4,"syntology":{"ran":6,"of":6,"n_ran_checked":0,"n_instrument":6,"unverified":0,"pointer_only":3,"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":["ml-research/rational_activations","ml-research/rational_rl","ml-research/rational_sl","k4ntz/activation-functions"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/training-microsoft-news-recommenders-with","slug":"training-microsoft-news-recommenders-with","title":"Training Large-Scale News Recommenders with Pretrained Language Models in the Loop","date":"2021-02-18","arxiv_id":"2102.09268","n_code_links":1,"syntology":null},{"paper":null,"slug":"unibuckernel-geolocating-swiss-german-jodels","title":"UnibucKernel: Geolocating Swiss German Jodels Using Ensemble Learning","date":"2021-02-18","arxiv_id":"2102.09379","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-dataset-and-benchmark-for-malaria-life","title":"A Dataset and Benchmark for Malaria Life-Cycle Classification in Thin Blood Smear Images","date":"2021-02-17","arxiv_id":"2102.08708","n_code_links":0,"syntology":null}],"record_sha256":"e57cf38629baccbb2fadb5f13cfecda870776a5412002125063d2af5ce0e8c73","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}