{"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/220","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":220,"pages_in_order":244,"rows_per_page":100,"rows":[21901,22000],"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/219","next":"/method/adam/papers/221","papers":[{"paper":null,"slug":"the-afrl-iwslt-2020-systems-work-from-home","title":"The AFRL IWSLT 2020 Systems: Work-From-Home Edition","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-hw-tsc-video-speech-translation-system-at","title":"The HW-TSC Video Speech Translation System at IWSLT 2020","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/towards-holistic-and-automatic-evaluation-of-1","slug":"towards-holistic-and-automatic-evaluation-of-1","title":"Towards Holistic and Automatic Evaluation of Open-Domain Dialogue Generation","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-stream-translation-adaptive","title":"Towards Stream Translation: Adaptive Computation Time for Simultaneous Machine Translation","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"training-and-inference-methods-for-high","title":"Training and Inference Methods for High-Coverage Neural Machine Translation","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-on-sarcasm-detection-with","title":"Transformers on Sarcasm Detection with Context","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/transition-based-semantic-dependency-parsing-1","slug":"transition-based-semantic-dependency-parsing-1","title":"Transition-based Semantic Dependency Parsing with Pointer Networks","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"turku-enhanced-parser-pipeline-from-raw-text","title":"Turku Enhanced Parser Pipeline: From Raw Text to Enhanced Graphs in the IWPT 2020 Shared Task","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-advertisements-with-bert","title":"Understanding Advertisements with BERT","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"university-of-tsukuba-s-machine-translation","title":"University of Tsukuba's Machine Translation System for IWSLT20 Open Domain Translation Task","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-faq-retrieval-with-question","title":"Unsupervised FAQ Retrieval with Question Generation and BERT","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"why-is-penguin-more-similar-to-polar-bear","title":"Why is penguin more similar to polar bear than to sea gull? Analyzing conceptual knowledge in distributional models","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"would-you-rather-a-new-benchmark-for-learning","title":"Would you Rather? A New Benchmark for Learning Machine Alignment with Cultural Values and Social Preferences","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"xiaomi-s-submissions-for-iwslt-2020-open","title":"Xiaomi's Submissions for IWSLT 2020 Open Domain Translation Task","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adasgd-bridging-the-gap-between-sgd-and-adam","title":"AdaSGD: Bridging the gap between SGD and Adam","date":"2020-06-30","arxiv_id":"2006.16541","n_code_links":0,"syntology":null},{"paper":null,"slug":"berters-multimodal-representation-learning","title":"BERTERS: Multimodal Representation Learning for Expert Recommendation System with Transformer","date":"2020-06-30","arxiv_id":"2007.07229","n_code_links":0,"syntology":null},{"paper":null,"slug":"correction-of-faulty-background-knowledge","title":"Correction of Faulty Background Knowledge based on Condition Aware and Revise Transformer for Question Answering","date":"2020-06-30","arxiv_id":"2006.16722","n_code_links":0,"syntology":null},{"paper":"/paper/data-movement-is-all-you-need-a-case-study-of","slug":"data-movement-is-all-you-need-a-case-study-of","title":"Data Movement Is All You Need: A Case Study on Optimizing Transformers","date":"2020-06-30","arxiv_id":"2007.00072","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["spcl/substation"],"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":["official"]}}},{"paper":"/paper/gshard-scaling-giant-models-with-conditional","slug":"gshard-scaling-giant-models-with-conditional","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","date":"2020-06-30","arxiv_id":"2006.16668","n_code_links":2,"syntology":{"ran":9,"of":10,"n_ran_checked":4,"n_instrument":5,"unverified":1,"pointer_only":1,"phrase":"9 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/image-level-harmonization-of-multi-site-data","slug":"image-level-harmonization-of-multi-site-data","title":"Image-level Harmonization of Multi-Site Data using Image-and-Spatial Transformer Networks","date":"2020-06-30","arxiv_id":"2006.16741","n_code_links":1,"syntology":null},{"paper":null,"slug":"se3m-a-model-for-software-effort-estimation","title":"SE3M: A Model for Software Effort Estimation Using Pre-trained Embedding Models","date":"2020-06-30","arxiv_id":"2006.16831","n_code_links":0,"syntology":null},{"paper":null,"slug":"segmentation-approach-for-coreference","title":"Segmentation Approach for Coreference Resolution Task","date":"2020-06-30","arxiv_id":"2007.04301","n_code_links":0,"syntology":null},{"paper":"/paper/a-transformer-based-joint-encoding-for-1","slug":"a-transformer-based-joint-encoding-for-1","title":"A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis","date":"2020-06-29","arxiv_id":"2006.15955","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/adai-separating-the-effects-of-adaptive","slug":"adai-separating-the-effects-of-adaptive","title":"Adai: Separating the Effects of Adaptive Learning Rate and Momentum Inertia","date":"2020-06-29","arxiv_id":"2006.15815","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":{"repos":["zeke-xie/adaptive-inertia-adai"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/gradient-only-line-searches-to-automatically","slug":"gradient-only-line-searches-to-automatically","title":"Gradient-only line searches to automatically determine learning rates for a variety of stochastic training algorithms","date":"2020-06-29","arxiv_id":"2007.01054","n_code_links":1,"syntology":null},{"paper":"/paper/improving-sequence-tagging-for-vietnamese","slug":"improving-sequence-tagging-for-vietnamese","title":"Improving Sequence Tagging for Vietnamese Text Using Transformer-based Neural Models","date":"2020-06-29","arxiv_id":"2006.15994","n_code_links":2,"syntology":null},{"paper":null,"slug":"interpreting-hierarchical-linguistic","title":"Building Interpretable Interaction Trees for Deep NLP Models","date":"2020-06-29","arxiv_id":"2007.04298","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-aware-language-model-pretraining","title":"Knowledge-Aware Language Model Pretraining","date":"2020-06-29","arxiv_id":"2007.00655","n_code_links":0,"syntology":null},{"paper":"/paper/multi-head-attention-collaborate-instead-of","slug":"multi-head-attention-collaborate-instead-of","title":"Multi-Head Attention: Collaborate Instead of Concatenate","date":"2020-06-29","arxiv_id":"2006.16362","n_code_links":2,"syntology":null},{"paper":"/paper/predicting-length-of-stay-in-the-intensive","slug":"predicting-length-of-stay-in-the-intensive","title":"Predicting Length of Stay in the Intensive Care Unit with Temporal Pointwise Convolutional Networks","date":"2020-06-29","arxiv_id":"2006.16109","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["EmmaRocheteau/eICU-LoS-prediction"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"paper":"/paper/simplifying-models-with-unlabeled-output-data","slug":"simplifying-models-with-unlabeled-output-data","title":"Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization","date":"2020-06-29","arxiv_id":"2006.16205","n_code_links":2,"syntology":{"ran":14,"of":14,"n_ran_checked":12,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["p-lambda/composed_finetuning","p-lambda/unlabeled_outputs"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"want-to-identify-extract-and-normalize","title":"Want to Identify, Extract and Normalize Adverse Drug Reactions in Tweets? Use RoBERTa","date":"2020-06-29","arxiv_id":"2006.16146","n_code_links":0,"syntology":null},{"paper":"/paper/bond-bert-assisted-open-domain-named-entity","slug":"bond-bert-assisted-open-domain-named-entity","title":"BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision","date":"2020-06-28","arxiv_id":"2006.15509","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cliang1453/BOND"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/bottom-up-human-pose-estimation-by-ranking","slug":"bottom-up-human-pose-estimation-by-ranking","title":"Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint Estimates","date":"2020-06-28","arxiv_id":"2006.15480","n_code_links":1,"syntology":null},{"paper":"/paper/progressive-generation-of-long-text","slug":"progressive-generation-of-long-text","title":"Progressive Generation of Long Text with Pretrained Language Models","date":"2020-06-28","arxiv_id":"2006.15720","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tanyuqian/progressive-generation"],"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/rethinking-the-positional-encoding-in","slug":"rethinking-the-positional-encoding-in","title":"Rethinking Positional Encoding in Language Pre-training","date":"2020-06-28","arxiv_id":"2006.15595","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["guolinke/TUPE"],"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":["listed","official"]}}},{"paper":null,"slug":"self-attention-networks-for-intent-detection-1","title":"Self-Attention Networks for Intent Detection","date":"2020-06-28","arxiv_id":"2006.15585","n_code_links":0,"syntology":null},{"paper":null,"slug":"mind-the-facts-knowledge-boosted-coherent","title":"Mind The Facts: Knowledge-Boosted Coherent Abstractive Text Summarization","date":"2020-06-27","arxiv_id":"2006.15435","n_code_links":0,"syntology":null},{"paper":null,"slug":"video-grounded-dialogues-with-pretrained-1","title":"Video-Grounded Dialogues with Pretrained Generation Language Models","date":"2020-06-27","arxiv_id":"2006.15319","n_code_links":0,"syntology":null},{"paper":"/paper/bertology-meets-biology-interpreting","slug":"bertology-meets-biology-interpreting","title":"BERTology Meets Biology: Interpreting Attention in Protein Language Models","date":"2020-06-26","arxiv_id":"2006.15222","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 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":["salesforce/provis"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/conditional-set-generation-with-transformers","slug":"conditional-set-generation-with-transformers","title":"Conditional Set Generation with Transformers","date":"2020-06-26","arxiv_id":"2006.16841","n_code_links":1,"syntology":null},{"paper":null,"slug":"distributed-uplink-beamforming-in-cell-free","title":"Distributed Uplink Beamforming in Cell-Free Networks Using Deep Reinforcement Learning","date":"2020-06-26","arxiv_id":"2006.15138","n_code_links":0,"syntology":null},{"paper":"/paper/turl-table-understanding-through","slug":"turl-table-understanding-through","title":"TURL: Table Understanding through Representation Learning","date":"2020-06-26","arxiv_id":"2006.14806","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":["sunlab-osu/TURL"],"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/what-they-do-when-in-doubt-a-study-of","slug":"what-they-do-when-in-doubt-a-study-of","title":"What they do when in doubt: a study of inductive biases in seq2seq learners","date":"2020-06-26","arxiv_id":"2006.14953","n_code_links":1,"syntology":null},{"paper":"/paper/fastspec-scalable-generation-and-detection-of","slug":"fastspec-scalable-generation-and-detection-of","title":"FastSpec: Scalable Generation and Detection of Spectre Gadgets Using Neural Embeddings","date":"2020-06-25","arxiv_id":"2006.14147","n_code_links":1,"syntology":null},{"paper":"/paper/learning-compositional-functions-via","slug":"learning-compositional-functions-via","title":"Learning compositional functions via multiplicative weight updates","date":"2020-06-25","arxiv_id":"2006.14560","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-source-phrase-representations-for-1","title":"Learning Source Phrase Representations for Neural Machine Translation","date":"2020-06-25","arxiv_id":"2006.14405","n_code_links":0,"syntology":null},{"paper":"/paper/lsbert-a-simple-framework-for-lexical","slug":"lsbert-a-simple-framework-for-lexical","title":"LSBert: A Simple Framework for Lexical Simplification","date":"2020-06-25","arxiv_id":"2006.14939","n_code_links":1,"syntology":null},{"paper":"/paper/mtadam-automatic-balancing-of-multiple","slug":"mtadam-automatic-balancing-of-multiple","title":"MTAdam: Automatic Balancing of Multiple Training Loss Terms","date":"2020-06-25","arxiv_id":"2006.14683","n_code_links":1,"syntology":null},{"paper":null,"slug":"noise-overestimation-and-exploration-in-deep","title":"Some approaches used to overcome overestimation in Deep Reinforcement Learning algorithms","date":"2020-06-25","arxiv_id":"2006.14167","n_code_links":0,"syntology":null},{"paper":null,"slug":"normalizing-text-using-language-modelling","title":"Normalizing Text using Language Modelling based on Phonetics and String Similarity","date":"2020-06-25","arxiv_id":"2006.14116","n_code_links":0,"syntology":null},{"paper":null,"slug":"sact-self-aware-multi-space-feature","title":"SACT: Self-Aware Multi-Space Feature Composition Transformer for Multinomial Attention for Video Captioning","date":"2020-06-25","arxiv_id":"2006.14262","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-segregating-and-coordinated-segregating","title":"Self-Segregating and Coordinated-Segregating Transformer for Focused Deep Multi-Modular Network for Visual Question Answering","date":"2020-06-25","arxiv_id":"2006.14264","n_code_links":0,"syntology":null},{"paper":"/paper/taming-gans-with-lookahead","slug":"taming-gans-with-lookahead","title":"Taming GANs with Lookahead-Minmax","date":"2020-06-25","arxiv_id":"2006.14567","n_code_links":1,"syntology":null},{"paper":"/paper/accelerated-large-batch-optimization-of-bert","slug":"accelerated-large-batch-optimization-of-bert","title":"Accelerated Large Batch Optimization of BERT Pretraining in 54 minutes","date":"2020-06-24","arxiv_id":"2006.13484","n_code_links":1,"syntology":null},{"paper":null,"slug":"differentiable-window-for-dynamic-local-1","title":"Differentiable Window for Dynamic Local Attention","date":"2020-06-24","arxiv_id":"2006.13561","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-constituency-parsing-by-pointing-1","title":"Efficient Constituency Parsing by Pointing","date":"2020-06-24","arxiv_id":"2006.13557","n_code_links":0,"syntology":null},{"paper":null,"slug":"private-stochastic-non-convex-optimization","title":"Private Stochastic Non-Convex Optimization: Adaptive Algorithms and Tighter Generalization Bounds","date":"2020-06-24","arxiv_id":"2006.13501","n_code_links":0,"syntology":null},{"paper":"/paper/bach-or-mock-a-grading-function-for-chorales","slug":"bach-or-mock-a-grading-function-for-chorales","title":"Bach or Mock? A Grading Function for Chorales in the Style of J.S. Bach","date":"2020-06-23","arxiv_id":"2006.13329","n_code_links":1,"syntology":null},{"paper":"/paper/experience-replay-with-likelihood-free","slug":"experience-replay-with-likelihood-free","title":"Experience Replay with Likelihood-free Importance Weights","date":"2020-06-23","arxiv_id":"2006.13169","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/gaining-insight-into-sars-cov-2-infection-and","slug":"gaining-insight-into-sars-cov-2-infection-and","title":"Gaining Insight into SARS-CoV-2 Infection and COVID-19 Severity Using Self-supervised Edge Features and Graph Neural Networks","date":"2020-06-23","arxiv_id":"2006.12971","n_code_links":1,"syntology":null},{"paper":null,"slug":"hybrid-spatio-temporal-graph-convolutional","title":"Hybrid Spatio-Temporal Graph Convolutional Network: Improving Traffic Prediction with Navigation Data","date":"2020-06-23","arxiv_id":"2006.12715","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-edge-features-for-improved","slug":"self-supervised-edge-features-for-improved","title":"Self-supervised edge features for improved Graph Neural Network training","date":"2020-06-23","arxiv_id":"2007.04777","n_code_links":1,"syntology":null},{"paper":"/paper/spherical-perspective-on-learning-with-batch","slug":"spherical-perspective-on-learning-with-batch","title":"Spherical Perspective on Learning with Normalization Layers","date":"2020-06-23","arxiv_id":"2006.13382","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-effect-of-multi-step-methods-on","title":"The Effect of Multi-step Methods on Overestimation in Deep Reinforcement Learning","date":"2020-06-23","arxiv_id":"2006.12692","n_code_links":0,"syntology":null},{"paper":"/paper/a-self-attention-network-based-node-embedding","slug":"a-self-attention-network-based-node-embedding","title":"A Self-Attention Network based Node Embedding Model","date":"2020-06-22","arxiv_id":"2006.12100","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-software-naturalness-throughneural","title":"Exploring Software Naturalness through Neural Language Models","date":"2020-06-22","arxiv_id":"2006.12641","n_code_links":0,"syntology":null},{"paper":"/paper/reco-a-large-scale-chinese-reading","slug":"reco-a-large-scale-chinese-reading","title":"ReCO: A Large Scale Chinese Reading Comprehension Dataset on Opinion","date":"2020-06-22","arxiv_id":"2006.12146","n_code_links":1,"syntology":null},{"paper":"/paper/students-need-more-attention-bert-based","slug":"students-need-more-attention-bert-based","title":"Students Need More Attention: BERT-based AttentionModel for Small Data with Application to AutomaticPatient Message Triage","date":"2020-06-22","arxiv_id":"2006.11991","n_code_links":1,"syntology":null},{"paper":"/paper/a-universal-representation-transformer-layer","slug":"a-universal-representation-transformer-layer","title":"A Universal Representation Transformer Layer for Few-Shot Image Classification","date":"2020-06-21","arxiv_id":"2006.11702","n_code_links":1,"syntology":null},{"paper":"/paper/adaptive-learning-rates-with-maximum","slug":"adaptive-learning-rates-with-maximum","title":"MaxVA: Fast Adaptation of Step Sizes by Maximizing Observed Variance of Gradients","date":"2020-06-21","arxiv_id":"2006.11918","n_code_links":1,"syntology":null},{"paper":"/paper/advaug-robust-adversarial-augmentation-for-1","slug":"advaug-robust-adversarial-augmentation-for-1","title":"AdvAug: Robust Adversarial Augmentation for Neural Machine Translation","date":"2020-06-21","arxiv_id":"2006.11834","n_code_links":0,"syntology":null},{"paper":null,"slug":"off-policy-self-critical-training-for","title":"Off-Policy Self-Critical Training for Transformer in Visual Paragraph Generation","date":"2020-06-21","arxiv_id":"2006.11714","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-nyu-cuboulder-systems-for-sigmorphon-2020-1","title":"The NYU-CUBoulder Systems for SIGMORPHON 2020 Task 0 and Task 2","date":"2020-06-21","arxiv_id":"2006.11830","n_code_links":0,"syntology":null},{"paper":"/paper/memory-transformer","slug":"memory-transformer","title":"Memory Transformer","date":"2020-06-20","arxiv_id":"2006.11527","n_code_links":1,"syntology":null},{"paper":null,"slug":"sarcasm-detection-in-tweets-with-bert-and-1","title":"Sarcasm Detection in Tweets with BERT and GloVe Embeddings","date":"2020-06-20","arxiv_id":"2006.11512","n_code_links":0,"syntology":null},{"paper":"/paper/wav2vec-2-0-a-framework-for-self-supervised","slug":"wav2vec-2-0-a-framework-for-self-supervised","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","date":"2020-06-20","arxiv_id":"2006.11477","n_code_links":25,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/a-qualitative-evaluation-of-language-models","slug":"a-qualitative-evaluation-of-language-models","title":"A Qualitative Evaluation of Language Models on Automatic Question-Answering for COVID-19","date":"2020-06-19","arxiv_id":"2006.10964","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-deep-metamodeling-to-calibrate-and","title":"End-to-end deep metamodeling to calibrate and optimize energy loads","date":"2020-06-19","arxiv_id":"2006.12390","n_code_links":0,"syntology":null},{"paper":"/paper/new-vietnamese-corpus-for-machine","slug":"new-vietnamese-corpus-for-machine","title":"New Vietnamese Corpus for Machine Reading Comprehension of Health News Articles","date":"2020-06-19","arxiv_id":"2006.11138","n_code_links":0,"syntology":null},{"paper":"/paper/squeezebert-what-can-computer-vision-teach","slug":"squeezebert-what-can-computer-vision-teach","title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","date":"2020-06-19","arxiv_id":"2006.11316","n_code_links":6,"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":["huggingface/transformers"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"boosting-objective-scores-of-speech","title":"Boosting Objective Scores of a Speech Enhancement Model by MetricGAN Post-processing","date":"2020-06-18","arxiv_id":"2006.10296","n_code_links":0,"syntology":null},{"paper":"/paper/deep-learning-enabled-semantic-communication","slug":"deep-learning-enabled-semantic-communication","title":"Deep Learning Enabled Semantic Communication Systems","date":"2020-06-18","arxiv_id":"2006.10685","n_code_links":1,"syntology":null},{"paper":"/paper/differentiable-augmentation-for-data","slug":"differentiable-augmentation-for-data","title":"Differentiable Augmentation for Data-Efficient GAN Training","date":"2020-06-18","arxiv_id":"2006.10738","n_code_links":13,"syntology":{"ran":49,"of":58,"n_ran_checked":19,"n_instrument":30,"unverified":9,"pointer_only":15,"phrase":"49 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 1 violated, 16 with no contract checked; 30 where Syntology's instrument failed) · 9 unverified","official":{"repos":["mit-han-lab/data-efficient-gans"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/i-bert-inductive-generalization-of","slug":"i-bert-inductive-generalization-of","title":"I-BERT: Inductive Generalization of Transformer to Arbitrary Context Lengths","date":"2020-06-18","arxiv_id":"2006.10220","n_code_links":1,"syntology":null},{"paper":"/paper/multi-branch-attentive-transformer","slug":"multi-branch-attentive-transformer","title":"Multi-branch Attentive Transformer","date":"2020-06-18","arxiv_id":"2006.10270","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"reducing-estimation-bias-via-weighted-delayed","title":"WD3: Taming the Estimation Bias in Deep Reinforcement Learning","date":"2020-06-18","arxiv_id":"2006.12622","n_code_links":0,"syntology":null},{"paper":null,"slug":"seal-segment-wise-extractive-abstractive-long","title":"SEAL: Segment-wise Extractive-Abstractive Long-form Text Summarization","date":"2020-06-18","arxiv_id":"2006.10213","n_code_links":0,"syntology":null},{"paper":"/paper/senwave-monitoring-the-global-sentiments","slug":"senwave-monitoring-the-global-sentiments","title":"SenWave: Monitoring the Global Sentiments under the COVID-19 Pandemic","date":"2020-06-18","arxiv_id":"2006.10842","n_code_links":2,"syntology":null},{"paper":"/paper/sparse-gpu-kernels-for-deep-learning","slug":"sparse-gpu-kernels-for-deep-learning","title":"Sparse GPU Kernels for Deep Learning","date":"2020-06-18","arxiv_id":"2006.10901","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatically-ranked-russian-paraphrase","title":"Automatically Ranked Russian Paraphrase Corpus for Text Generation","date":"2020-06-17","arxiv_id":"2006.09719","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-bert-cross-lingual","title":"Exploring the BERT Cross-Lingual Transferability: a Case Study in Reading Comprehension","date":"2020-06-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"intelligent-protection-classification-of","title":"Intelligent Protection & Classification of Transients in Two-Core Symmetric Phase Angle Regulating Transformers","date":"2020-06-17","arxiv_id":"2006.09865","n_code_links":0,"syntology":null},{"paper":"/paper/learning-visual-commonsense-for-robust-scene","slug":"learning-visual-commonsense-for-robust-scene","title":"Learning Visual Commonsense for Robust Scene Graph Generation","date":"2020-06-17","arxiv_id":"2006.09623","n_code_links":2,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/tagging-and-parsing-of-multidomain","slug":"tagging-and-parsing-of-multidomain","title":"Tagging and parsing of multidomain collections","date":"2020-06-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/cross-lingual-retrieval-for-iterative-self","slug":"cross-lingual-retrieval-for-iterative-self","title":"Cross-lingual Retrieval for Iterative Self-Supervised Training","date":"2020-06-16","arxiv_id":"2006.09526","n_code_links":1,"syntology":null},{"paper":"/paper/curvature-is-key-sub-sampled-loss-surfaces","slug":"curvature-is-key-sub-sampled-loss-surfaces","title":"Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training","date":"2020-06-16","arxiv_id":"2006.09092","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-code-switching-language-models-for","title":"End-to-End Code Switching Language Models for Automatic Speech Recognition","date":"2020-06-16","arxiv_id":"2006.08870","n_code_links":0,"syntology":null},{"paper":"/paper/improving-accuracy-and-speeding-up-document","slug":"improving-accuracy-and-speeding-up-document","title":"Improving accuracy and speeding up Document Image Classification through parallel systems","date":"2020-06-16","arxiv_id":"2006.09141","n_code_links":1,"syntology":null},{"paper":"/paper/memory-efficient-pipeline-parallel-dnn","slug":"memory-efficient-pipeline-parallel-dnn","title":"Memory-Efficient Pipeline-Parallel DNN Training","date":"2020-06-16","arxiv_id":"2006.09503","n_code_links":1,"syntology":{"ran":2,"of":10,"n_ran_checked":2,"n_instrument":0,"unverified":8,"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) · 8 unverified","official":null}}],"record_sha256":"51087a2f824312c9e4e712fcd0fd14004ee7d128ae0b4d107dc0fa5d0ae6dcc5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}