{"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/242","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":242,"pages_in_order":285,"rows_per_page":100,"rows":[24101,24200],"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/241","next":"/method/residual-connection/papers/243","papers":[{"paper":null,"slug":"a-pre-training-strategy-for-recommendation","title":"Pre-training Graph Transformer with Multimodal Side Information for Recommendation","date":"2020-10-23","arxiv_id":"2010.12284","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-approach-for-handling-out-of","slug":"a-simple-approach-for-handling-out-of","title":"A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code","date":"2020-10-23","arxiv_id":"2010.12663","n_code_links":1,"syntology":null},{"paper":"/paper/barthez-a-skilled-pretrained-french-sequence","slug":"barthez-a-skilled-pretrained-french-sequence","title":"BARThez: a Skilled Pretrained French Sequence-to-Sequence Model","date":"2020-10-23","arxiv_id":"2010.12321","n_code_links":5,"syntology":null},{"paper":"/paper/deep-learning-framework-for-measuring-the","slug":"deep-learning-framework-for-measuring-the","title":"Deep Learning Framework for Measuring the Digital Strategy of Companies from Earnings Calls","date":"2020-10-23","arxiv_id":"2010.12418","n_code_links":1,"syntology":null},{"paper":"/paper/did-you-ask-a-good-question-a-cross-domain","slug":"did-you-ask-a-good-question-a-cross-domain","title":"Did You Ask a Good Question? A Cross-Domain Question Intention Classification Benchmark for Text-to-SQL","date":"2020-10-23","arxiv_id":"2010.12634","n_code_links":1,"syntology":null},{"paper":"/paper/don-t-shoot-butterfly-with-rifles-multi","slug":"don-t-shoot-butterfly-with-rifles-multi","title":"Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer","date":"2020-10-23","arxiv_id":"2010.12180","n_code_links":1,"syntology":null},{"paper":"/paper/ernie-gram-pre-training-with-explicitly-n","slug":"ernie-gram-pre-training-with-explicitly-n","title":"ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding","date":"2020-10-23","arxiv_id":"2010.12148","n_code_links":2,"syntology":null},{"paper":null,"slug":"gibert-introducing-linguistic-knowledge-into","title":"GiBERT: Introducing Linguistic Knowledge into BERT through a Lightweight Gated Injection Method","date":"2020-10-23","arxiv_id":"2010.12532","n_code_links":0,"syntology":null},{"paper":null,"slug":"graphspeech-syntax-aware-graph-attention","title":"GraphSpeech: Syntax-Aware Graph Attention Network For Neural Speech Synthesis","date":"2020-10-23","arxiv_id":"2010.12423","n_code_links":0,"syntology":null},{"paper":"/paper/hatebert-retraining-bert-for-abusive-language","slug":"hatebert-retraining-bert-for-abusive-language","title":"HateBERT: Retraining BERT for Abusive Language Detection in English","date":"2020-10-23","arxiv_id":"2010.12472","n_code_links":1,"syntology":null},{"paper":"/paper/lightseq-a-high-performance-inference-library","slug":"lightseq-a-high-performance-inference-library","title":"LightSeq: A High Performance Inference Library for Transformers","date":"2020-10-23","arxiv_id":"2010.13887","n_code_links":1,"syntology":null},{"paper":"/paper/long-document-ranking-with-query-directed","slug":"long-document-ranking-with-query-directed","title":"Long Document Ranking with Query-Directed Sparse Transformer","date":"2020-10-23","arxiv_id":"2010.12683","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-bert-post-pretraining-alignment","title":"Multilingual BERT Post-Pretraining Alignment","date":"2020-10-23","arxiv_id":"2010.12547","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-transformer-growth-for-progressive","title":"On the Transformer Growth for Progressive BERT Training","date":"2020-10-23","arxiv_id":"2010.12562","n_code_links":0,"syntology":null},{"paper":"/paper/posterior-differential-regularization-with-f","slug":"posterior-differential-regularization-with-f","title":"Posterior Differential Regularization with f-divergence for Improving Model Robustness","date":"2020-10-23","arxiv_id":"2010.12638","n_code_links":2,"syntology":null},{"paper":null,"slug":"pre-trained-model-for-chinese-word","title":"Pre-training with Meta Learning for Chinese Word Segmentation","date":"2020-10-23","arxiv_id":"2010.12272","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantum-superposition-spiking-neural-network","title":"Quantum Superposition Inspired Spiking Neural Network","date":"2020-10-23","arxiv_id":"2010.12197","n_code_links":0,"syntology":null},{"paper":"/paper/resnet-or-densenet-introducing-dense","slug":"resnet-or-densenet-introducing-dense","title":"ResNet or DenseNet? Introducing Dense Shortcuts to ResNet","date":"2020-10-23","arxiv_id":"2010.12496","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":3,"phrase":"0 ran · 3 unverified","official":null}},{"paper":null,"slug":"st-bert-cross-modal-language-model-pre","title":"ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding","date":"2020-10-23","arxiv_id":"2010.12283","n_code_links":0,"syntology":null},{"paper":null,"slug":"stabilizing-transformer-based-action-sequence","title":"Stabilizing Transformer-Based Action Sequence Generation For Q-Learning","date":"2020-10-23","arxiv_id":"2010.12698","n_code_links":0,"syntology":null},{"paper":null,"slug":"topic-modeling-with-contextualized-word","title":"Topic Modeling with Contextualized Word Representation Clusters","date":"2020-10-23","arxiv_id":"2010.12626","n_code_links":0,"syntology":null},{"paper":null,"slug":"traffic-abstractions-of-nonlinear-event","title":"Abstracting the Traffic of Nonlinear Event-Triggered Control Systems","date":"2020-10-23","arxiv_id":"2010.12341","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-end-to-end-speech","slug":"transformer-based-end-to-end-speech","title":"Transformer-based End-to-End Speech Recognition with Local Dense Synthesizer Attention","date":"2020-10-23","arxiv_id":"2010.12155","n_code_links":1,"syntology":null},{"paper":"/paper/an-image-is-worth-16x16-words-transformers-1","slug":"an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","arxiv_id":"2010.11929","n_code_links":158,"syntology":{"ran":307,"of":419,"n_ran_checked":286,"n_instrument":21,"unverified":112,"pointer_only":154,"phrase":"307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified","official":{"repos":["google-research/vision_transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["community","listed","unlocated"]}}},{"paper":null,"slug":"developing-real-time-streaming-transformer","title":"Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset","date":"2020-10-22","arxiv_id":"2010.11395","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-dense-representations-for-ranking","slug":"distilling-dense-representations-for-ranking","title":"Distilling Dense Representations for Ranking using Tightly-Coupled Teachers","date":"2020-10-22","arxiv_id":"2010.11386","n_code_links":2,"syntology":null},{"paper":null,"slug":"efficient-scale-permuted-backbone-with-1","title":"Efficient Scale-Permuted Backbone with Learned Resource Distribution","date":"2020-10-22","arxiv_id":"2010.11426","n_code_links":0,"syntology":null},{"paper":"/paper/face-hallucination-using-split-attention-in","slug":"face-hallucination-using-split-attention-in","title":"Face Hallucination via Split-Attention in Split-Attention Network","date":"2020-10-22","arxiv_id":"2010.11575","n_code_links":1,"syntology":null},{"paper":"/paper/how-phonotactics-affect-multilingual-and-zero","slug":"how-phonotactics-affect-multilingual-and-zero","title":"How Phonotactics Affect Multilingual and Zero-shot ASR Performance","date":"2020-10-22","arxiv_id":"2010.12104","n_code_links":1,"syntology":null},{"paper":"/paper/improving-bert-performance-for-aspect-based","slug":"improving-bert-performance-for-aspect-based","title":"Improving BERT Performance for Aspect-Based Sentiment Analysis","date":"2020-10-22","arxiv_id":"2010.11731","n_code_links":2,"syntology":{"ran":7,"of":11,"n_ran_checked":4,"n_instrument":3,"unverified":4,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["IMPLabUniPr/BERT-for-ABSA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/investigating-the-true-performance-of","slug":"investigating-the-true-performance-of","title":"Exploiting News Article Structure for Automatic Corpus Generation of Entailment Datasets","date":"2020-10-22","arxiv_id":"2010.11574","n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-distillation-for-bert-unsupervised","slug":"knowledge-distillation-for-bert-unsupervised","title":"Knowledge Distillation for BERT Unsupervised Domain Adaptation","date":"2020-10-22","arxiv_id":"2010.11478","n_code_links":1,"syntology":null},{"paper":"/paper/language-models-are-open-knowledge-graphs-1","slug":"language-models-are-open-knowledge-graphs-1","title":"Language Models are Open Knowledge Graphs","date":"2020-10-22","arxiv_id":"2010.11967","n_code_links":2,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/mt5-a-massively-multilingual-pre-trained-text","slug":"mt5-a-massively-multilingual-pre-trained-text","title":"mT5: A massively multilingual pre-trained text-to-text transformer","date":"2020-10-22","arxiv_id":"2010.11934","n_code_links":8,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"10 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["google-research/multilingual-t5"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/n-ode-transformer-a-depth-adaptive-variant-of","slug":"n-ode-transformer-a-depth-adaptive-variant-of","title":"N-ODE Transformer: A Depth-Adaptive Variant of the Transformer Using Neural Ordinary Differential Equations","date":"2020-10-22","arxiv_id":"2010.11358","n_code_links":1,"syntology":null},{"paper":"/paper/phew-paths-with-higher-edge-weights-give-1","slug":"phew-paths-with-higher-edge-weights-give-1","title":"PHEW: Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data","date":"2020-10-22","arxiv_id":"2010.11354","n_code_links":1,"syntology":null},{"paper":null,"slug":"scientific-claim-verification-with-vert5erini","title":"Scientific Claim Verification with VERT5ERINI","date":"2020-10-22","arxiv_id":"2010.11930","n_code_links":0,"syntology":null},{"paper":"/paper/self-alignment-pre-training-for-biomedical","slug":"self-alignment-pre-training-for-biomedical","title":"Self-Alignment Pretraining for Biomedical Entity Representations","date":"2020-10-22","arxiv_id":"2010.11784","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-fully-bilingual-deep-language","title":"Towards Fully Bilingual Deep Language Modeling","date":"2020-10-22","arxiv_id":"2010.11639","n_code_links":0,"syntology":null},{"paper":null,"slug":"unicase-rethinking-casing-in-language-models","title":"UniCase -- Rethinking Casing in Language Models","date":"2020-10-22","arxiv_id":"2010.11936","n_code_links":0,"syntology":null},{"paper":null,"slug":"2nd-place-solution-to-instance-segmentation","title":"2nd Place Solution to Instance Segmentation of IJCAI 3D AI Challenge 2020","date":"2020-10-21","arxiv_id":"2010.10957","n_code_links":0,"syntology":null},{"paper":"/paper/analyzing-the-source-and-target-contributions","slug":"analyzing-the-source-and-target-contributions","title":"Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation","date":"2020-10-21","arxiv_id":"2010.10907","n_code_links":1,"syntology":null},{"paper":"/paper/approxdet-content-and-contention-aware","slug":"approxdet-content-and-contention-aware","title":"ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles","date":"2020-10-21","arxiv_id":"2010.10754","n_code_links":1,"syntology":null},{"paper":"/paper/deep-learning-frameworks-for-pavement","slug":"deep-learning-frameworks-for-pavement","title":"Deep Learning Frameworks for Pavement Distress Classification: A Comparative Analysis","date":"2020-10-21","arxiv_id":"2010.10681","n_code_links":1,"syntology":null},{"paper":null,"slug":"detection-of-covid-19-informative-tweets","title":"Detection of COVID-19 informative tweets using RoBERTa","date":"2020-10-21","arxiv_id":"2010.11238","n_code_links":0,"syntology":null},{"paper":"/paper/generalized-conditioned-dialogue-generation","slug":"generalized-conditioned-dialogue-generation","title":"A Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue Generation","date":"2020-10-21","arxiv_id":"2010.11140","n_code_links":1,"syntology":null},{"paper":"/paper/german-s-next-language-model","slug":"german-s-next-language-model","title":"German's Next Language Model","date":"2020-10-21","arxiv_id":"2010.10906","n_code_links":1,"syntology":null},{"paper":null,"slug":"grapheme-or-phoneme-an-analysis-of-tacotron-s","title":"An Investigation of the Relation Between Grapheme Embeddings and Pronunciation for Tacotron-based Systems","date":"2020-10-21","arxiv_id":"2010.10694","n_code_links":0,"syntology":null},{"paper":null,"slug":"latte-mix-measuring-sentence-semantic","title":"Latte-Mix: Measuring Sentence Semantic Similarity with Latent Categorical Mixtures","date":"2020-10-21","arxiv_id":"2010.11351","n_code_links":0,"syntology":null},{"paper":"/paper/learning-speaker-embedding-from-text-to","slug":"learning-speaker-embedding-from-text-to","title":"Learning Speaker Embedding from Text-to-Speech","date":"2020-10-21","arxiv_id":"2010.11221","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-domain-dialogue-state-tracking-based-on-1","title":"Multi-Domain Dialogue State Tracking based on State Graph","date":"2020-10-21","arxiv_id":"2010.11137","n_code_links":0,"syntology":null},{"paper":"/paper/multi-unit-transformer-for-neural-machine","slug":"multi-unit-transformer-for-neural-machine","title":"Multi-Unit Transformers for Neural Machine Translation","date":"2020-10-21","arxiv_id":"2010.10743","n_code_links":1,"syntology":null},{"paper":null,"slug":"tmt-a-transformer-based-modal-translator-for","title":"TMT: A Transformer-based Modal Translator for Improving Multimodal Sequence Representations in Audio Visual Scene-aware Dialog","date":"2020-10-21","arxiv_id":"2010.10839","n_code_links":0,"syntology":null},{"paper":"/paper/token-drop-mechanism-for-neural-machine","slug":"token-drop-mechanism-for-neural-machine","title":"Token Drop mechanism for Neural Machine Translation","date":"2020-10-21","arxiv_id":"2010.11018","n_code_links":1,"syntology":null},{"paper":null,"slug":"transferable-graph-optimizers-for-ml","title":"Transferable Graph Optimizers for ML Compilers","date":"2020-10-21","arxiv_id":"2010.12438","n_code_links":0,"syntology":null},{"paper":"/paper/wavetransformer-a-novel-architecture-for","slug":"wavetransformer-a-novel-architecture-for","title":"WaveTransformer: A Novel Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information","date":"2020-10-21","arxiv_id":"2010.11098","n_code_links":1,"syntology":null},{"paper":"/paper/automets-the-autocomplete-for-medical-text","slug":"automets-the-autocomplete-for-medical-text","title":"AutoMeTS: The Autocomplete for Medical Text Simplification","date":"2020-10-20","arxiv_id":"2010.10573","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert2dnn-bert-distillation-with-massive","title":"BERT2DNN: BERT Distillation with Massive Unlabeled Data for Online E-Commerce Search","date":"2020-10-20","arxiv_id":"2010.10442","n_code_links":0,"syntology":null},{"paper":"/paper/bootleg-chasing-the-tail-with-self-supervised","slug":"bootleg-chasing-the-tail-with-self-supervised","title":"Bootleg: Chasing the Tail with Self-Supervised Named Entity Disambiguation","date":"2020-10-20","arxiv_id":"2010.10363","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":null}},{"paper":"/paper/characterbert-reconciling-elmo-and-bert-for","slug":"characterbert-reconciling-elmo-and-bert-for","title":"CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters","date":"2020-10-20","arxiv_id":"2010.10392","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":4,"n_instrument":2,"unverified":2,"pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["helboukkouri/character-bert"],"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/conjnli-natural-language-inference-over","slug":"conjnli-natural-language-inference-over","title":"ConjNLI: Natural Language Inference Over Conjunctive Sentences","date":"2020-10-20","arxiv_id":"2010.10418","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":4,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["swarnaHub/ConjNLI"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/cort-complementary-rankings-from-transformers","slug":"cort-complementary-rankings-from-transformers","title":"CoRT: Complementary Rankings from Transformers","date":"2020-10-20","arxiv_id":"2010.10252","n_code_links":1,"syntology":null},{"paper":"/paper/language-representation-in-multilingual","slug":"language-representation-in-multilingual","title":"Looking for Clues of Language in Multilingual BERT to Improve Cross-lingual Generalization","date":"2020-10-20","arxiv_id":"2010.10041","n_code_links":1,"syntology":null},{"paper":null,"slug":"micro-ct-image-assisted-cross-modality-super","title":"Micro CT Image-Assisted Cross Modality Super-Resolution of Clinical CT Images Utilizing Synthesized Training Dataset","date":"2020-10-20","arxiv_id":"2010.10207","n_code_links":0,"syntology":null},{"paper":"/paper/optimal-subarchitecture-extraction-for-bert","slug":"optimal-subarchitecture-extraction-for-bert","title":"Optimal Subarchitecture Extraction For BERT","date":"2020-10-20","arxiv_id":"2010.10499","n_code_links":3,"syntology":null},{"paper":null,"slug":"performance-of-transfer-learning-model-vs","title":"Performance of Transfer Learning Model vs. Traditional Neural Network in Low System Resource Environment","date":"2020-10-20","arxiv_id":"2011.07962","n_code_links":0,"syntology":null},{"paper":"/paper/privacy-preserving-visual-content-tagging","slug":"privacy-preserving-visual-content-tagging","title":"Privacy-Preserving Visual Content Tagging using Graph Transformer Networks","date":"2020-10-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/privacy-preserving-visual-content-tagging-1","slug":"privacy-preserving-visual-content-tagging-1","title":"Privacy-Preserving Visual Content Tagging using Graph Transformer Networks","date":"2020-10-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/prop-pre-training-with-representative-words","slug":"prop-pre-training-with-representative-words","title":"PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval","date":"2020-10-20","arxiv_id":"2010.10137","n_code_links":1,"syntology":null},{"paper":"/paper/stronger-faster-and-more-explainable-a-graph","slug":"stronger-faster-and-more-explainable-a-graph","title":"Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition","date":"2020-10-20","arxiv_id":"2010.09978","n_code_links":1,"syntology":null},{"paper":null,"slug":"text-classification-of-covid-19-press","title":"Text Classification of Manifestos and COVID-19 Press Briefings using BERT and Convolutional Neural Networks","date":"2020-10-20","arxiv_id":"2010.10267","n_code_links":0,"syntology":null},{"paper":null,"slug":"tongji-university-undergraduate-team-for-the","title":"Tongji University Undergraduate Team for the VoxCeleb Speaker Recognition Challenge2020","date":"2020-10-20","arxiv_id":"2010.10145","n_code_links":0,"syntology":null},{"paper":"/paper/topic-aware-abstractive-text-summarization","slug":"topic-aware-abstractive-text-summarization","title":"Topic-Guided Abstractive Text Summarization: a Joint Learning Approach","date":"2020-10-20","arxiv_id":"2010.10323","n_code_links":1,"syntology":null},{"paper":"/paper/towards-maximizing-the-representation-gap","slug":"towards-maximizing-the-representation-gap","title":"Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples","date":"2020-10-20","arxiv_id":"2010.10474","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-scalable-distributed-training-of-deep","title":"Towards Scalable Distributed Training of Deep Learning on Public Cloud Clusters","date":"2020-10-20","arxiv_id":"2010.10458","n_code_links":0,"syntology":null},{"paper":"/paper/transition-based-parsing-with-stack","slug":"transition-based-parsing-with-stack","title":"Transition-based Parsing with Stack-Transformers","date":"2020-10-20","arxiv_id":"2010.10669","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-makes-multilingual-bert-multilingual","title":"What makes multilingual BERT multilingual?","date":"2020-10-20","arxiv_id":"2010.10938","n_code_links":0,"syntology":null},{"paper":"/paper/bertnesia-investigating-the-capture-and","slug":"bertnesia-investigating-the-capture-and","title":"BERTnesia: Investigating the capture and forgetting of knowledge in BERT","date":"2020-10-19","arxiv_id":"2010.09313","n_code_links":1,"syntology":null},{"paper":null,"slug":"better-distractions-transformer-based","title":"Better Distractions: Transformer-based Distractor Generation and Multiple Choice Question Filtering","date":"2020-10-19","arxiv_id":"2010.09598","n_code_links":0,"syntology":null},{"paper":"/paper/cold-start-active-learning-through-self","slug":"cold-start-active-learning-through-self","title":"Cold-start Active Learning through Self-supervised Language Modeling","date":"2020-10-19","arxiv_id":"2010.09535","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":["forest-snow/alps"],"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/colloql-robust-cross-domain-text-to-sql-over","slug":"colloql-robust-cross-domain-text-to-sql-over","title":"ColloQL: Robust Cross-Domain Text-to-SQL Over Search Queries","date":"2020-10-19","arxiv_id":"2010.09927","n_code_links":1,"syntology":null},{"paper":"/paper/cross-lingual-transfer-in-zero-shot-cross","slug":"cross-lingual-transfer-in-zero-shot-cross","title":"Cross-Lingual Transfer in Zero-Shot Cross-Language Entity Linking","date":"2020-10-19","arxiv_id":"2010.09828","n_code_links":1,"syntology":null},{"paper":"/paper/dimsum-laysumm-20-bart-based-approach-for","slug":"dimsum-laysumm-20-bart-based-approach-for","title":"Dimsum @LaySumm 20: BART-based Approach for Scientific Document Summarization","date":"2020-10-19","arxiv_id":"2010.09252","n_code_links":1,"syntology":null},{"paper":"/paper/drug-repurposing-for-covid-19-via-knowledge","slug":"drug-repurposing-for-covid-19-via-knowledge","title":"Drug Repurposing for COVID-19 via Knowledge Graph Completion","date":"2020-10-19","arxiv_id":"2010.09600","n_code_links":1,"syntology":null},{"paper":"/paper/infusing-sequential-information-into","slug":"infusing-sequential-information-into","title":"Infusing Sequential Information into Conditional Masked Translation Model with Self-Review Mechanism","date":"2020-10-19","arxiv_id":"2010.09194","n_code_links":1,"syntology":null},{"paper":"/paper/mimicnorm-weight-mean-and-last-bn-layer-mimic","slug":"mimicnorm-weight-mean-and-last-bn-layer-mimic","title":"MimicNorm: Weight Mean and Last BN Layer Mimic the Dynamic of Batch Normalization","date":"2020-10-19","arxiv_id":"2010.09278","n_code_links":1,"syntology":null},{"paper":"/paper/parameter-norm-growth-during-training-of","slug":"parameter-norm-growth-during-training-of","title":"Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent","date":"2020-10-19","arxiv_id":"2010.09697","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":1,"n_instrument":5,"unverified":1,"pointer_only":7,"phrase":"6 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; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["viking-sudo-rm/norm-growth"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"query-aware-tip-generation-for-vertical","title":"Query-aware Tip Generation for Vertical Search","date":"2020-10-19","arxiv_id":"2010.09254","n_code_links":0,"syntology":null},{"paper":null,"slug":"robustness-aware-2-bit-quantization-with-real","title":"Robustness-aware 2-bit quantization with real-time performance for neural network","date":"2020-10-19","arxiv_id":"2010.11271","n_code_links":0,"syntology":null},{"paper":"/paper/saint-integrating-temporal-features-for-ednet","slug":"saint-integrating-temporal-features-for-ednet","title":"SAINT+: Integrating Temporal Features for EdNet Correctness Prediction","date":"2020-10-19","arxiv_id":"2010.12042","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/the-relx-dataset-and-matching-the","slug":"the-relx-dataset-and-matching-the","title":"The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification","date":"2020-10-19","arxiv_id":"2010.09381","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["boun-tabi/RELX"],"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/capturing-longer-context-for-document-level","slug":"capturing-longer-context-for-document-level","title":"Rethinking Document-level Neural Machine Translation","date":"2020-10-18","arxiv_id":"2010.08961","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sunzewei2715/Doc2Doc_NMT"],"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/disguising-personal-identity-information-in","slug":"disguising-personal-identity-information-in","title":"Disguising Personal Identity Information in EEG Signals","date":"2020-10-18","arxiv_id":"2010.08915","n_code_links":1,"syntology":null},{"paper":null,"slug":"explaining-and-improving-model-behavior-with","title":"Explaining and Improving Model Behavior with k Nearest Neighbor Representations","date":"2020-10-18","arxiv_id":"2010.09030","n_code_links":0,"syntology":null},{"paper":"/paper/towards-interpreting-bert-for-reading","slug":"towards-interpreting-bert-for-reading","title":"Towards Interpreting BERT for Reading Comprehension Based QA","date":"2020-10-18","arxiv_id":"2010.08983","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["iitmnlp/BERT-Analysis-RCQA"],"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","unlocated"]}}},{"paper":null,"slug":"answer-checking-in-context-a-multi-modal","title":"Answer-checking in Context: A Multi-modal FullyAttention Network for Visual Question Answering","date":"2020-10-17","arxiv_id":"2010.08708","n_code_links":0,"syntology":null},{"paper":null,"slug":"habertor-an-efficient-and-effective-deep","title":"HABERTOR: An Efficient and Effective Deep Hatespeech Detector","date":"2020-10-17","arxiv_id":"2010.08865","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-multitask-learning-approach-for","title":"Hierarchical Multitask Learning Approach for BERT","date":"2020-10-17","arxiv_id":"2011.04451","n_code_links":0,"syntology":null},{"paper":null,"slug":"question-answering-over-knowledge-base-using-1","title":"Question Answering over Knowledge Base using Language Model Embeddings","date":"2020-10-17","arxiv_id":"2010.08883","n_code_links":0,"syntology":null},{"paper":"/paper/tweetbert-a-pretrained-language","slug":"tweetbert-a-pretrained-language","title":"TweetBERT: A Pretrained Language Representation Model for Twitter Text Analysis","date":"2020-10-17","arxiv_id":"2010.11091","n_code_links":1,"syntology":null}],"record_sha256":"a5dcfca24dc9ebf817aedce7b92f53dd724318280d0a14cce6ebb33412ddf445","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}