{"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/adam/papers/229","list_of":"/method/adam","method":"Adam","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":229,"pages_in_order":244,"rows_per_page":100,"rows":[22801,22900],"of":24390,"counts":{"archive_papers_tagged":24390,"with_a_code_link":10944,"where_syntology_ran_a_sample":3424,"not_listed_spam_title":0,"listed":24390,"listed_where_code_ran":3424,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2899,"every_run_a_failure_of_syntologys_instrument":525,"listed_with_a_run_with_no_instrument_failure":2899,"listed_every_run_a_failure_of_syntologys_instrument":525,"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/adam","prev":"/method/adam/papers/228","next":"/method/adam/papers/230","papers":[{"paper":"/paper/pretrained-transformers-for-simple-question","slug":"pretrained-transformers-for-simple-question","title":"Pretrained Transformers for Simple Question Answering over Knowledge Graphs","date":"2020-01-31","arxiv_id":"2001.11985","n_code_links":1,"syntology":null},{"paper":null,"slug":"reconstructing-natural-scenes-from-fmri","title":"Reconstructing Natural Scenes from fMRI Patterns using BigBiGAN","date":"2020-01-31","arxiv_id":"2001.11761","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-training-for-aspect-based","slug":"adversarial-training-for-aspect-based","title":"Adversarial Training for Aspect-Based Sentiment Analysis with BERT","date":"2020-01-30","arxiv_id":"2001.11316","n_code_links":4,"syntology":null},{"paper":null,"slug":"do-we-need-word-order-information-for-cross","title":"On the Importance of Word Order Information in Cross-lingual Sequence Labeling","date":"2020-01-30","arxiv_id":"2001.11164","n_code_links":0,"syntology":null},{"paper":"/paper/interpretable-rumor-detection-in-microblogs","slug":"interpretable-rumor-detection-in-microblogs","title":"Interpretable Rumor Detection in Microblogs by Attending to User Interactions","date":"2020-01-29","arxiv_id":"2001.10667","n_code_links":1,"syntology":null},{"paper":null,"slug":"joint-contextual-modeling-for-asr-correction","title":"Joint Contextual Modeling for ASR Correction and Language Understanding","date":"2020-01-28","arxiv_id":"2002.00750","n_code_links":0,"syntology":null},{"paper":null,"slug":"pel-bert-a-joint-model-for-protocol-entity","title":"PEL-BERT: A Joint Model for Protocol Entity Linking","date":"2020-01-28","arxiv_id":"2002.00744","n_code_links":0,"syntology":null},{"paper":"/paper/retrospective-reader-for-machine-reading","slug":"retrospective-reader-for-machine-reading","title":"Retrospective Reader for Machine Reading Comprehension","date":"2020-01-27","arxiv_id":"2001.09694","n_code_links":2,"syntology":null},{"paper":"/paper/artificial-neural-networks-for-cloud-masking","slug":"artificial-neural-networks-for-cloud-masking","title":"Artificial neural networks for cloud masking of Sentinel-2 ocean images with noise and sunglint","date":"2020-01-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"further-boosting-bert-based-models-by","title":"BERT's output layer recognizes all hidden layers? Some Intriguing Phenomena and a simple way to boost BERT","date":"2020-01-25","arxiv_id":"2001.09309","n_code_links":0,"syntology":null},{"paper":null,"slug":"generation-distillation-for-efficient-natural-1","title":"Generation-Distillation for Efficient Natural Language Understanding in Low-Data Settings","date":"2020-01-25","arxiv_id":"2002.00733","n_code_links":0,"syntology":null},{"paper":"/paper/gesticulator-a-framework-for-semantically","slug":"gesticulator-a-framework-for-semantically","title":"Gesticulator: A framework for semantically-aware speech-driven gesture generation","date":"2020-01-25","arxiv_id":"2001.09326","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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":["Svito-zar/gesticulator"],"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/a-branching-and-merging-convolutional-network","slug":"a-branching-and-merging-convolutional-network","title":"No Routing Needed Between Capsules","date":"2020-01-24","arxiv_id":"2001.09136","n_code_links":1,"syntology":null},{"paper":null,"slug":"low-rank-gradient-approximation-for-memory","title":"Low-rank Gradient Approximation For Memory-Efficient On-device Training of Deep Neural Network","date":"2020-01-24","arxiv_id":"2001.08885","n_code_links":0,"syntology":null},{"paper":"/paper/power-bert-accelerating-bert-inference-for","slug":"power-bert-accelerating-bert-inference-for","title":"PoWER-BERT: Accelerating BERT Inference via Progressive Word-vector Elimination","date":"2020-01-24","arxiv_id":"2001.08950","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 2 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) · 0 unverified","official":{"repos":["IBM/PoWER-BERT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"applying-recent-innovations-from-nlp-to-mooc","title":"Applying Recent Innovations from NLP to MOOC Student Course Trajectory Modeling","date":"2020-01-23","arxiv_id":"2001.08333","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-a-transformer-based-language","title":"Reducing Non-Normative Text Generation from Language Models","date":"2020-01-23","arxiv_id":"2001.08764","n_code_links":0,"syntology":null},{"paper":"/paper/interpretable-end-to-end-urban-autonomous","slug":"interpretable-end-to-end-urban-autonomous","title":"Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning","date":"2020-01-23","arxiv_id":"2001.08726","n_code_links":4,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["cjy1992/interp-e2e-driving"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"navigation-based-candidate-expansion-and","title":"Navigation-Based Candidate Expansion and Pretrained Language Models for Citation Recommendation","date":"2020-01-23","arxiv_id":"2001.08687","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-denoising-pre-training-for","slug":"multilingual-denoising-pre-training-for","title":"Multilingual Denoising Pre-training for Neural Machine Translation","date":"2020-01-22","arxiv_id":"2001.08210","n_code_links":8,"syntology":null},{"paper":null,"slug":"a-hybrid-model-based-on-deep-lstm-for","title":"A hybrid model based on deep LSTM for predicting high-dimensional chaotic systems","date":"2020-01-21","arxiv_id":"2002.00799","n_code_links":0,"syntology":null},{"paper":null,"slug":"cooperative-highway-work-zone-merge-control","title":"Cooperative Highway Work Zone Merge Control based on Reinforcement Learning in A Connected and Automated Environment","date":"2020-01-21","arxiv_id":"2001.08581","n_code_links":0,"syntology":null},{"paper":null,"slug":"generate-high-resolution-adversarial-samples","title":"HRFA: High-Resolution Feature-based Attack","date":"2020-01-21","arxiv_id":"2001.07631","n_code_links":0,"syntology":null},{"paper":null,"slug":"random-matrix-theory-proves-that-deep-1","title":"Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures","date":"2020-01-21","arxiv_id":"2001.08370","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-level-head-wise-match-and-aggregation","title":"Multi-level Head-wise Match and Aggregation in Transformer for Textual Sequence Matching","date":"2020-01-20","arxiv_id":"2001.07234","n_code_links":0,"syntology":null},{"paper":"/paper/recommending-themes-for-ad-creative-design","slug":"recommending-themes-for-ad-creative-design","title":"Recommending Themes for Ad Creative Design via Visual-Linguistic Representations","date":"2020-01-20","arxiv_id":"2001.07194","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multimodal-deep-learning-approach-for-named","title":"A multimodal deep learning approach for named entity recognition from social media","date":"2020-01-19","arxiv_id":"2001.06888","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-for-hindi-text-classification-a","title":"Deep Learning for Hindi Text Classification: A Comparison","date":"2020-01-19","arxiv_id":"2001.10340","n_code_links":0,"syntology":null},{"paper":"/paper/discriminator-soft-actor-critic-without","slug":"discriminator-soft-actor-critic-without","title":"Discriminator Soft Actor Critic without Extrinsic Rewards","date":"2020-01-19","arxiv_id":"2001.06808","n_code_links":1,"syntology":null},{"paper":"/paper/mti-net-multi-scale-task-interaction-networks","slug":"mti-net-multi-scale-task-interaction-networks","title":"MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning","date":"2020-01-19","arxiv_id":"2001.06902","n_code_links":1,"syntology":null},{"paper":null,"slug":"capturing-evolution-in-word-usage-just-add","title":"Capturing Evolution in Word Usage: Just Add More Clusters?","date":"2020-01-18","arxiv_id":"2001.06629","n_code_links":0,"syntology":null},{"paper":null,"slug":"adamt-a-stochastic-optimization-with-trend-1","title":"On the Trend-corrected Variant of Adaptive Stochastic Optimization Methods","date":"2020-01-17","arxiv_id":"2001.06130","n_code_links":0,"syntology":null},{"paper":null,"slug":"gradient-descent-with-momentum-to-accelerate","title":"Gradient descent with momentum --- to accelerate or to super-accelerate?","date":"2020-01-17","arxiv_id":"2001.06472","n_code_links":0,"syntology":null},{"paper":"/paper/robbert-a-dutch-roberta-based-language-model","slug":"robbert-a-dutch-roberta-based-language-model","title":"RobBERT: a Dutch RoBERTa-based Language Model","date":"2020-01-17","arxiv_id":"2001.06286","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: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["iPieter/RobBERT"],"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/schema2qa-answering-complex-queries-on-the","slug":"schema2qa-answering-complex-queries-on-the","title":"Schema2QA: High-Quality and Low-Cost Q&A Agents for the Structured Web","date":"2020-01-16","arxiv_id":"2001.05609","n_code_links":3,"syntology":null},{"paper":null,"slug":"shifted-and-squeezed-8-bit-floating-point-1","title":"Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural Networks","date":"2020-01-16","arxiv_id":"2001.05674","n_code_links":0,"syntology":null},{"paper":"/paper/fgn-fusion-glyph-network-for-chinese-named","slug":"fgn-fusion-glyph-network-for-chinese-named","title":"FGN: Fusion Glyph Network for Chinese Named Entity Recognition","date":"2020-01-15","arxiv_id":"2001.05272","n_code_links":1,"syntology":null},{"paper":null,"slug":"insertion-deletion-transformer","title":"Insertion-Deletion Transformer","date":"2020-01-15","arxiv_id":"2001.05540","n_code_links":0,"syntology":null},{"paper":"/paper/parallel-machine-translation-with","slug":"parallel-machine-translation-with","title":"Non-Autoregressive Machine Translation with Disentangled Context Transformer","date":"2020-01-15","arxiv_id":"2001.05136","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-online-ctcattention-end-to","title":"Transformer-based Online CTC/attention End-to-End Speech Recognition Architecture","date":"2020-01-15","arxiv_id":"2001.08290","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-bert-based-sentiment-analysis-and-key","title":"A BERT based Sentiment Analysis and Key Entity Detection Approach for Online Financial Texts","date":"2020-01-14","arxiv_id":"2001.05326","n_code_links":0,"syntology":null},{"paper":null,"slug":"auto-completion-of-user-interface-layout-1","title":"Auto Completion of User Interface Layout Design Using Transformer-Based Tree Decoders","date":"2020-01-14","arxiv_id":"2001.05308","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-problems-with-using-stns-to-align-cnn","title":"The problems with using STNs to align CNN feature maps","date":"2020-01-14","arxiv_id":"2001.05858","n_code_links":0,"syntology":null},{"paper":"/paper/adabert-task-adaptive-bert-compression-with","slug":"adabert-task-adaptive-bert-compression-with","title":"AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search","date":"2020-01-13","arxiv_id":"2001.04246","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":null}},{"paper":"/paper/reformer-the-efficient-transformer-1","slug":"reformer-the-efficient-transformer-1","title":"Reformer: The Efficient Transformer","date":"2020-01-13","arxiv_id":"2001.04451","n_code_links":10,"syntology":{"ran":6,"of":8,"n_ran_checked":1,"n_instrument":5,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","official":{"repos":["google/trax"],"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/representations-lexicales-pour-la-detection","slug":"representations-lexicales-pour-la-detection","title":"Représentations lexicales pour la détection non supervisée d'événements dans un flux de tweets : étude sur des corpus français et anglais","date":"2020-01-13","arxiv_id":"2001.04139","n_code_links":1,"syntology":null},{"paper":null,"slug":"urdu-english-machine-transliteration-using","title":"Urdu-English Machine Transliteration using Neural Networks","date":"2020-01-12","arxiv_id":"2001.05296","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-and-improving-robustness-of-multi","slug":"exploring-and-improving-robustness-of-multi","title":"Exploring and Improving Robustness of Multi Task Deep Neural Networks via Domain Agnostic Defenses","date":"2020-01-11","arxiv_id":"2001.05286","n_code_links":1,"syntology":null},{"paper":null,"slug":"patenttransformer-2-controlling-patent-text","title":"PatentTransformer-2: Controlling Patent Text Generation by Structural Metadata","date":"2020-01-11","arxiv_id":"2001.03708","n_code_links":0,"syntology":null},{"paper":"/paper/tangent-space-gradient-optimization-of-tensor","slug":"tangent-space-gradient-optimization-of-tensor","title":"Tangent-Space Gradient Optimization of Tensor Network for Machine Learning","date":"2020-01-10","arxiv_id":"2001.04029","n_code_links":1,"syntology":null},{"paper":"/paper/matrixnets-a-new-scale-and-aspect-ratio-aware","slug":"matrixnets-a-new-scale-and-aspect-ratio-aware","title":"MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection","date":"2020-01-09","arxiv_id":"2001.03194","n_code_links":1,"syntology":null},{"paper":"/paper/resolving-the-scope-of-speculation-and","slug":"resolving-the-scope-of-speculation-and","title":"Resolving the Scope of Speculation and Negation using Transformer-Based Architectures","date":"2020-01-09","arxiv_id":"2001.02885","n_code_links":1,"syntology":null},{"paper":"/paper/spatial-temporal-transformer-networks-for","slug":"spatial-temporal-transformer-networks-for","title":"Spatial-Temporal Transformer Networks for Traffic Flow Forecasting","date":"2020-01-09","arxiv_id":"2001.02908","n_code_links":1,"syntology":null},{"paper":null,"slug":"sample-based-distributional-policy-gradient","title":"Sample-based Distributional Policy Gradient","date":"2020-01-08","arxiv_id":"2001.02652","n_code_links":0,"syntology":null},{"paper":null,"slug":"streaming-automatic-speech-recognition-with","title":"Streaming automatic speech recognition with the transformer model","date":"2020-01-08","arxiv_id":"2001.02674","n_code_links":0,"syntology":null},{"paper":null,"slug":"to-transfer-or-not-to-transfer","title":"To Transfer or Not to Transfer: Misclassification Attacks Against Transfer Learned Text Classifiers","date":"2020-01-08","arxiv_id":"2001.02438","n_code_links":0,"syntology":null},{"paper":null,"slug":"recast-interactive-auditing-of-automatic","title":"RECAST: Interactive Auditing of Automatic Toxicity Detection Models","date":"2020-01-07","arxiv_id":"2001.01819","n_code_links":0,"syntology":null},{"paper":"/paper/improving-entity-linking-by-modeling-latent-2","slug":"improving-entity-linking-by-modeling-latent-2","title":"Improving Entity Linking by Modeling Latent Entity Type Information","date":"2020-01-06","arxiv_id":"2001.01447","n_code_links":0,"syntology":null},{"paper":"/paper/fdftnet-facing-off-fake-images-using-fake","slug":"fdftnet-facing-off-fake-images-using-fake","title":"FDFtNet: Facing Off Fake Images using Fake Detection Fine-tuning Network","date":"2020-01-05","arxiv_id":"2001.01265","n_code_links":2,"syntology":{"ran":8,"of":13,"n_ran_checked":8,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["cutz-j/FDFtNet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/scalable-gradients-for-stochastic","slug":"scalable-gradients-for-stochastic","title":"Scalable Gradients for Stochastic Differential Equations","date":"2020-01-05","arxiv_id":"2001.01328","n_code_links":4,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"pointer_only":2,"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) · 4 unverified","official":{"repos":["google-research/torchsde"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"learning-accurate-integer-transformer-machine","title":"Learning Accurate Integer Transformer Machine-Translation Models","date":"2020-01-03","arxiv_id":"2001.00926","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-layer-content-interaction-through","title":"Multi-Layer Content Interaction Through Quaternion Product For Visual Question Answering","date":"2020-01-03","arxiv_id":"2001.05840","n_code_links":0,"syntology":null},{"paper":"/paper/two-level-transformer-and-auxiliary-coherence","slug":"two-level-transformer-and-auxiliary-coherence","title":"Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation","date":"2020-01-03","arxiv_id":"2001.00891","n_code_links":1,"syntology":null},{"paper":null,"slug":"representing-unordered-data-using-multiset-1","title":"Representing Unordered Data Using Complex-Weighted Multiset Automata","date":"2020-01-02","arxiv_id":"2001.00610","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-al-bert-for-arbitrarily-long-document","title":"BERT-AL: BERT for Arbitrarily Long Document Understanding","date":"2020-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-execution-engines","title":"NEURAL EXECUTION ENGINES","date":"2020-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/poly-encoders-architectures-and-pre-training","slug":"poly-encoders-architectures-and-pre-training","title":"Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring","date":"2020-01-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/stacked-debert-all-attention-in-incomplete","slug":"stacked-debert-all-attention-in-incomplete","title":"Stacked DeBERT: All Attention in Incomplete Data for Text Classification","date":"2020-01-01","arxiv_id":"2001.00137","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gcunhase/StackedDeBERT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"training-deep-networks-with-stochastic","title":"Training Deep Networks with Stochastic Gradient Normalized by Layerwise Adaptive Second Moments","date":"2020-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-dynamic-sampling-adaptive-sgd-method-for","title":"A Dynamic Sampling Adaptive-SGD Method for Machine Learning","date":"2019-12-31","arxiv_id":"1912.13357","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-attentive-ranking-networks-for-learning","title":"Deep Attentive Ranking Networks for Learning to Order Sentences","date":"2019-12-31","arxiv_id":"2001.00056","n_code_links":0,"syntology":null},{"paper":null,"slug":"eeg-based-continuous-speech-recognition-using","title":"EEG based Continuous Speech Recognition using Transformers","date":"2019-12-31","arxiv_id":"2001.00501","n_code_links":0,"syntology":null},{"paper":"/paper/olmpics-on-what-language-model-pre-training","slug":"olmpics-on-what-language-model-pre-training","title":"oLMpics -- On what Language Model Pre-training Captures","date":"2019-12-31","arxiv_id":"1912.13283","n_code_links":2,"syntology":null},{"paper":"/paper/oteann-estimating-the-transparency-of","slug":"oteann-estimating-the-transparency-of","title":"OTEANN: Estimating the Transparency of Orthographies with an Artificial Neural Network","date":"2019-12-31","arxiv_id":"1912.13321","n_code_links":2,"syntology":null},{"paper":"/paper/aranet-a-deep-learning-toolkit-for-arabic","slug":"aranet-a-deep-learning-toolkit-for-arabic","title":"AraNet: A Deep Learning Toolkit for Arabic Social Media","date":"2019-12-30","arxiv_id":"1912.13072","n_code_links":1,"syntology":null},{"paper":"/paper/autodiscern-rating-the-quality-of-online","slug":"autodiscern-rating-the-quality-of-online","title":"AutoDiscern: Rating the Quality of Online Health Information with Hierarchical Encoder Attention-based Neural Networks","date":"2019-12-30","arxiv_id":"1912.12999","n_code_links":1,"syntology":null},{"paper":null,"slug":"all-in-one-image-grounded-conversational","title":"All-in-One Image-Grounded Conversational Agents","date":"2019-12-28","arxiv_id":"1912.12394","n_code_links":0,"syntology":null},{"paper":"/paper/slm-lab-a-comprehensive-benchmark-and-modular-1","slug":"slm-lab-a-comprehensive-benchmark-and-modular-1","title":"SLM Lab: A Comprehensive Benchmark and Modular Software Framework for Reproducible Deep Reinforcement Learning","date":"2019-12-28","arxiv_id":"1912.12482","n_code_links":1,"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":["kengz/SLM-Lab"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/clinical-xlnet-modeling-sequential-clinical","slug":"clinical-xlnet-modeling-sequential-clinical","title":"Clinical XLNet: Modeling Sequential Clinical Notes and Predicting Prolonged Mechanical Ventilation","date":"2019-12-27","arxiv_id":"1912.11975","n_code_links":3,"syntology":null},{"paper":"/paper/encoding-word-order-in-complex-embeddings-1","slug":"encoding-word-order-in-complex-embeddings-1","title":"Encoding word order in complex embeddings","date":"2019-12-27","arxiv_id":"1912.12333","n_code_links":1,"syntology":null},{"paper":"/paper/is-attention-all-what-you-need-an-empirical","slug":"is-attention-all-what-you-need-an-empirical","title":"Is Attention All What You Need? -- An Empirical Investigation on Convolution-Based Active Memory and Self-Attention","date":"2019-12-27","arxiv_id":"1912.11959","n_code_links":1,"syntology":null},{"paper":"/paper/explicit-sparse-transformer-concentrated","slug":"explicit-sparse-transformer-concentrated","title":"Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection","date":"2019-12-25","arxiv_id":"1912.11637","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 1 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":["lancopku/Explicit-Sparse-Transformer"],"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":["unlocated"]}}},{"paper":null,"slug":"make-lead-bias-in-your-favor-a-simple-and-2","title":"Leveraging Lead Bias for Zero-shot Abstractive News Summarization","date":"2019-12-25","arxiv_id":"1912.11602","n_code_links":0,"syntology":null},{"paper":"/paper/cprop-adaptive-learning-rate-scaling-from","slug":"cprop-adaptive-learning-rate-scaling-from","title":"CProp: Adaptive Learning Rate Scaling from Past Gradient Conformity","date":"2019-12-24","arxiv_id":"1912.11493","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-abstractive-text-summarization-with","title":"Improving Abstractive Text Summarization with History Aggregation","date":"2019-12-24","arxiv_id":"1912.11046","n_code_links":0,"syntology":null},{"paper":"/paper/multi-graph-transformer-for-free-hand-sketch","slug":"multi-graph-transformer-for-free-hand-sketch","title":"Multi-Graph Transformer for Free-Hand Sketch Recognition","date":"2019-12-24","arxiv_id":"1912.11258","n_code_links":1,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"0 ran · 4 unverified","official":{"repos":["PengBoXiangShang/multigraph_transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":"/paper/cnn-generated-images-are-surprisingly-easy-to","slug":"cnn-generated-images-are-surprisingly-easy-to","title":"CNN-generated images are surprisingly easy to spot... for now","date":"2019-12-23","arxiv_id":"1912.11035","n_code_links":5,"syntology":null},{"paper":"/paper/discrete-and-continuous-action-representation","slug":"discrete-and-continuous-action-representation","title":"Discrete and Continuous Action Representation for Practical RL in Video Games","date":"2019-12-23","arxiv_id":"1912.11077","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 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) · 0 unverified","official":null}},{"paper":"/paper/probing-the-phonetic-and-phonological","slug":"probing-the-phonetic-and-phonological","title":"Probing the phonetic and phonological knowledge of tones in Mandarin TTS models","date":"2019-12-23","arxiv_id":"1912.10915","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-training-of-a-large-vocabulary-end","title":"end-to-end training of a large vocabulary end-to-end speech recognition system","date":"2019-12-22","arxiv_id":"1912.11040","n_code_links":0,"syntology":null},{"paper":"/paper/harnessing-evolution-of-multi-turn","slug":"harnessing-evolution-of-multi-turn","title":"Harnessing Evolution of Multi-Turn Conversations for Effective Answer Retrieval","date":"2019-12-22","arxiv_id":"1912.10554","n_code_links":1,"syntology":null},{"paper":"/paper/pre-trained-contextual-embedding-of-source-1","slug":"pre-trained-contextual-embedding-of-source-1","title":"Learning and Evaluating Contextual Embedding of Source Code","date":"2019-12-21","arxiv_id":"2001.00059","n_code_links":2,"syntology":null},{"paper":null,"slug":"are-transformers-universal-approximators-of-1","title":"Are Transformers universal approximators of sequence-to-sequence functions?","date":"2019-12-20","arxiv_id":"1912.10077","n_code_links":0,"syntology":null},{"paper":"/paper/axial-attention-in-multidimensional-1","slug":"axial-attention-in-multidimensional-1","title":"Axial Attention in Multidimensional Transformers","date":"2019-12-20","arxiv_id":"1912.12180","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"et-usb-transformer-based-sequential-behavior","title":"ET-USB: Transformer-Based Sequential Behavior Modeling for Inbound Customer Service","date":"2019-12-20","arxiv_id":"1912.10852","n_code_links":0,"syntology":null},{"paper":null,"slug":"pretrained-encyclopedia-weakly-supervised-1","title":"Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model","date":"2019-12-20","arxiv_id":"1912.09637","n_code_links":0,"syntology":null},{"paper":null,"slug":"second-order-information-in-first-order","title":"Second-order Information in First-order Optimization Methods","date":"2019-12-20","arxiv_id":"1912.09926","n_code_links":0,"syntology":null},{"paper":null,"slug":"shareable-representations-for-search-query","title":"Shareable Representations for Search Query Understanding","date":"2019-12-20","arxiv_id":"2001.04345","n_code_links":0,"syntology":null},{"paper":"/paper/bertje-a-dutch-bert-model","slug":"bertje-a-dutch-bert-model","title":"BERTje: A Dutch BERT Model","date":"2019-12-19","arxiv_id":"1912.09582","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["wietsedv/bertje"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/cjrc-a-reliable-human-annotated-benchmark","slug":"cjrc-a-reliable-human-annotated-benchmark","title":"CJRC: A Reliable Human-Annotated Benchmark DataSet for Chinese Judicial Reading Comprehension","date":"2019-12-19","arxiv_id":"1912.09156","n_code_links":0,"syntology":null}],"record_sha256":"e9fafde83d1acd87f598c62979818f922512ebd07ae0ffadcf3f5b183e4aac4c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}