{"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/191","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":191,"pages_in_order":244,"rows_per_page":100,"rows":[19001,19100],"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/190","next":"/method/adam/papers/192","papers":[{"paper":null,"slug":"arabic-aspect-based-sentiment-analysis-using-1","title":"Arabic aspect sentiment polarity classification using BERT","date":"2021-07-28","arxiv_id":"2107.13290","n_code_links":0,"syntology":null},{"paper":"/paper/bi-bimodal-modality-fusion-for-correlation","slug":"bi-bimodal-modality-fusion-for-correlation","title":"Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis","date":"2021-07-28","arxiv_id":"2107.13669","n_code_links":2,"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, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["declare-lab/multimodal-deep-learning"],"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/goal-oriented-script-construction","slug":"goal-oriented-script-construction","title":"Goal-Oriented Script Construction","date":"2021-07-28","arxiv_id":"2107.13189","n_code_links":1,"syntology":null},{"paper":null,"slug":"value-based-reinforcement-learning-for","title":"Value-Based Reinforcement Learning for Continuous Control Robotic Manipulation in Multi-Task Sparse Reward Settings","date":"2021-07-28","arxiv_id":"2107.13356","n_code_links":0,"syntology":null},{"paper":"/paper/gabert-an-irish-language-model","slug":"gabert-an-irish-language-model","title":"gaBERT -- an Irish Language Model","date":"2021-07-27","arxiv_id":"2107.12930","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-rule-execution-tracking-machine-for","title":"Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation","date":"2021-07-27","arxiv_id":"2107.13077","n_code_links":0,"syntology":null},{"paper":null,"slug":"pisltrc-position-informed-sign-language","title":"PiSLTRc: Position-informed Sign Language Transformer with Content-aware Convolution","date":"2021-07-27","arxiv_id":"2107.12600","n_code_links":0,"syntology":null},{"paper":"/paper/contextnet-a-click-through-rate-prediction","slug":"contextnet-a-click-through-rate-prediction","title":"ContextNet: A Click-Through Rate Prediction Framework Using Contextual information to Refine Feature Embedding","date":"2021-07-26","arxiv_id":"2107.12025","n_code_links":4,"syntology":null},{"paper":"/paper/contextual-transformer-networks-for-visual","slug":"contextual-transformer-networks-for-visual","title":"Contextual Transformer Networks for Visual Recognition","date":"2021-07-26","arxiv_id":"2107.12292","n_code_links":7,"syntology":null},{"paper":"/paper/go-wider-instead-of-deeper","slug":"go-wider-instead-of-deeper","title":"Go Wider Instead of Deeper","date":"2021-07-25","arxiv_id":"2107.11817","n_code_links":1,"syntology":null},{"paper":"/paper/h-transformer-1d-fast-one-dimensional","slug":"h-transformer-1d-fast-one-dimensional","title":"H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences","date":"2021-07-25","arxiv_id":"2107.11906","n_code_links":2,"syntology":{"ran":9,"of":10,"n_ran_checked":6,"n_instrument":3,"unverified":1,"pointer_only":1,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"context-aware-adversarial-training-for-name","title":"Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition","date":"2021-07-24","arxiv_id":"2107.11610","n_code_links":0,"syntology":null},{"paper":null,"slug":"mdqe-a-more-accurate-direct-pretraining-for","title":"MDQE: A More Accurate Direct Pretraining for Machine Translation Quality Estimation","date":"2021-07-24","arxiv_id":"2107.14600","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-early-sepsis-prediction-with-multi","title":"Improving Early Sepsis Prediction with Multi Modal Learning","date":"2021-07-23","arxiv_id":"2107.11094","n_code_links":0,"syntology":null},{"paper":null,"slug":"unrealistic-feature-suppression-for","title":"Unrealistic Feature Suppression for Generative Adversarial Networks","date":"2021-07-23","arxiv_id":"2107.11047","n_code_links":0,"syntology":null},{"paper":"/paper/confidence-aware-scheduled-sampling-for","slug":"confidence-aware-scheduled-sampling-for","title":"Confidence-Aware Scheduled Sampling for Neural Machine Translation","date":"2021-07-22","arxiv_id":"2107.10427","n_code_links":1,"syntology":null},{"paper":"/paper/ean-event-adaptive-network-for-enhanced","slug":"ean-event-adaptive-network-for-enhanced","title":"EAN: Event Adaptive Network for Enhanced Action Recognition","date":"2021-07-22","arxiv_id":"2107.10771","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-extractive-summarization","slug":"evaluating-extractive-summarization","title":"Evaluating Extractive Summarization Techniques on News Articles","date":"2021-07-22","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-extractive-summarization-1","slug":"evaluating-extractive-summarization-1","title":"Evaluating Extractive Summarization Techniques on News Articles","date":"2021-07-22","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-contextual-embeddings-on-less","title":"Evaluation of contextual embeddings on less-resourced languages","date":"2021-07-22","arxiv_id":"2107.10614","n_code_links":0,"syntology":null},{"paper":"/paper/fnetar-mixing-tokens-with-autoregressive","slug":"fnetar-mixing-tokens-with-autoregressive","title":"FNetAR: Mixing Tokens with Autoregressive Fourier Transforms","date":"2021-07-22","arxiv_id":"2107.10932","n_code_links":1,"syntology":null},{"paper":"/paper/query2label-a-simple-transformer-way-to-multi","slug":"query2label-a-simple-transformer-way-to-multi","title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","date":"2021-07-22","arxiv_id":"2107.10834","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: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["SlongLiu/query2labels"],"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"]}}},{"paper":null,"slug":"semantic-text-to-face-gan-st-2fg","title":"Semantic Text-to-Face GAN -ST^2FG","date":"2021-07-22","arxiv_id":"2107.10756","n_code_links":0,"syntology":null},{"paper":null,"slug":"spinning-sequence-to-sequence-models-with","title":"Spinning Sequence-to-Sequence Models with Meta-Backdoors","date":"2021-07-22","arxiv_id":"2107.10443","n_code_links":0,"syntology":null},{"paper":null,"slug":"tsformer-time-series-transformer-for-tourism","title":"Tsformer: Time series Transformer for tourism demand forecasting","date":"2021-07-22","arxiv_id":"2107.10977","n_code_links":0,"syntology":null},{"paper":"/paper/audio-captioning-transformer","slug":"audio-captioning-transformer","title":"Audio Captioning Transformer","date":"2021-07-21","arxiv_id":"2107.09817","n_code_links":1,"syntology":null},{"paper":null,"slug":"causalbert-injecting-causal-knowledge-into","title":"CausalBERT: Injecting Causal Knowledge Into Pre-trained Models with Minimal Supervision","date":"2021-07-21","arxiv_id":"2107.09852","n_code_links":0,"syntology":null},{"paper":"/paper/cyclemlp-a-mlp-like-architecture-for-dense","slug":"cyclemlp-a-mlp-like-architecture-for-dense","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","date":"2021-07-21","arxiv_id":"2107.10224","n_code_links":8,"syntology":{"ran":10,"of":15,"n_ran_checked":10,"n_instrument":0,"unverified":5,"pointer_only":2,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["ShoufaChen/CycleMLP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"digital-einstein-experience-fast-text-to","title":"Digital Einstein Experience: Fast Text-to-Speech for Conversational AI","date":"2021-07-21","arxiv_id":"2107.10658","n_code_links":0,"syntology":null},{"paper":null,"slug":"drdf-determining-the-importance-of-different","title":"DRDF: Determining the Importance of Different Multimodal Information with Dual-Router Dynamic Framework","date":"2021-07-21","arxiv_id":"2107.09909","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-text-classification-via-contrastive","title":"Improved Text Classification via Contrastive Adversarial Training","date":"2021-07-21","arxiv_id":"2107.10137","n_code_links":0,"syntology":null},{"paper":"/paper/multi-stream-transformers","slug":"multi-stream-transformers","title":"Multi-Stream Transformers","date":"2021-07-21","arxiv_id":"2107.10342","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-scale-graph-network-with-multi-head","title":"A Multi-scale Graph Network with Multi-head Attention for Histopathology Image Diagnosis","date":"2021-07-20","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"canita-faster-rates-for-distributed-convex","title":"CANITA: Faster Rates for Distributed Convex Optimization with Communication Compression","date":"2021-07-20","arxiv_id":"2107.09461","n_code_links":0,"syntology":null},{"paper":null,"slug":"crew-computation-reuse-and-efficient-weight","title":"CREW: Computation Reuse and Efficient Weight Storage for Hardware-accelerated MLPs and RNNs","date":"2021-07-20","arxiv_id":"2107.09408","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-video-transformer-can-objects-be","title":"Generative Video Transformer: Can Objects be the Words?","date":"2021-07-20","arxiv_id":"2107.09240","n_code_links":0,"syntology":null},{"paper":"/paper/linked-data-triples-enhance-document","slug":"linked-data-triples-enhance-document","title":"Linked Data Triples Enhance Document Relevance Classification","date":"2021-07-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"weakly-supervised-global-local-feature","title":"Weakly Supervised Global-Local Feature Learning for Cervical Cytology Image Analysis","date":"2021-07-20","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/clinical-relation-extraction-using","slug":"clinical-relation-extraction-using","title":"Clinical Relation Extraction Using Transformer-based Models","date":"2021-07-19","arxiv_id":"2107.08957","n_code_links":1,"syntology":null},{"paper":"/paper/image-fusion-transformer","slug":"image-fusion-transformer","title":"Image Fusion Transformer","date":"2021-07-19","arxiv_id":"2107.09011","n_code_links":1,"syntology":null},{"paper":"/paper/learning-attributed-graph-representations","slug":"learning-attributed-graph-representations","title":"Learning Attributed Graph Representations with Communicative Message Passing Transformer","date":"2021-07-19","arxiv_id":"2107.08773","n_code_links":1,"syntology":null},{"paper":"/paper/levit-unet-make-faster-encoders-with","slug":"levit-unet-make-faster-encoders-with","title":"LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation","date":"2021-07-19","arxiv_id":"2107.08623","n_code_links":2,"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":["apple1986/LeViT_UNet"],"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/long-term-series-forecasting-with-query","slug":"long-term-series-forecasting-with-query","title":"Long-term series forecasting with Query Selector -- efficient model of sparse attention","date":"2021-07-19","arxiv_id":"2107.08687","n_code_links":2,"syntology":null},{"paper":null,"slug":"residual-tree-aggregation-of-layers-for","title":"Residual Tree Aggregation of Layers for Neural Machine Translation","date":"2021-07-19","arxiv_id":"2107.14590","n_code_links":0,"syntology":null},{"paper":"/paper/sequence-to-sequence-piano-transcription-with","slug":"sequence-to-sequence-piano-transcription-with","title":"Sequence-to-Sequence Piano Transcription with Transformers","date":"2021-07-19","arxiv_id":"2107.09142","n_code_links":2,"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":null}},{"paper":null,"slug":"a-discriminative-semantic-ranker-for-question","title":"A Discriminative Semantic Ranker for Question Retrieval","date":"2021-07-18","arxiv_id":"2107.08345","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-new-adaptive-gradient-method-with-gradient","title":"A New Adaptive Gradient Method with Gradient Decomposition","date":"2021-07-18","arxiv_id":"2107.08377","n_code_links":0,"syntology":null},{"paper":"/paper/aspect-based-sentiment-analysis-using-bert","slug":"aspect-based-sentiment-analysis-using-bert","title":"Aspect-based Sentiment Analysis using BERT with Disentangled Attention","date":"2021-07-18","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"stock-price-prediction-using-bert-and-gan","title":"Stock price prediction using BERT and GAN","date":"2021-07-18","arxiv_id":"2107.09055","n_code_links":0,"syntology":null},{"paper":"/paper/tfix-learning-to-fix-coding-errors-with-a","slug":"tfix-learning-to-fix-coding-errors-with-a","title":"TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer","date":"2021-07-18","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"a-vector-based-approach-to-few-shot-veracity","title":"A Vector-Based Approach to Few-Shot Veracity Classification for Automated Fact-Checking","date":"2021-07-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-transformer-for-efficient-machine","title":"Dynamic Transformer for Efficient Machine Translation on Embedded Devices","date":"2021-07-17","arxiv_id":"2107.08199","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-search-learning-query-and-product","title":"Neural Search: Learning Query and Product Representations in Fashion E-commerce","date":"2021-07-17","arxiv_id":"2107.08291","n_code_links":0,"syntology":null},{"paper":"/paper/is-attention-to-bounding-boxes-all-you-need","slug":"is-attention-to-bounding-boxes-all-you-need","title":"Is attention to bounding boxes all you need for pedestrian action prediction?","date":"2021-07-16","arxiv_id":"2107.08031","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-law-of-large-documents-understanding-the","title":"The Law of Large Documents: Understanding the Structure of Legal Contracts Using Visual Cues","date":"2021-07-16","arxiv_id":"2107.08128","n_code_links":0,"syntology":null},{"paper":"/paper/autobert-zero-evolving-bert-backbone-from","slug":"autobert-zero-evolving-bert-backbone-from","title":"AutoBERT-Zero: Evolving BERT Backbone from Scratch","date":"2021-07-15","arxiv_id":"2107.07445","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-task-requirements-writing","slug":"automatic-task-requirements-writing","title":"Automatic Task Requirements Writing Evaluation via Machine Reading Comprehension","date":"2021-07-15","arxiv_id":"2107.07957","n_code_links":1,"syntology":null},{"paper":"/paper/fewclue-a-chinese-few-shot-learning","slug":"fewclue-a-chinese-few-shot-learning","title":"FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark","date":"2021-07-15","arxiv_id":"2107.07498","n_code_links":1,"syntology":null},{"paper":"/paper/learning-sparse-interaction-graphs-of","slug":"learning-sparse-interaction-graphs-of","title":"Learning Sparse Interaction Graphs of Partially Detected Pedestrians for Trajectory Prediction","date":"2021-07-15","arxiv_id":"2107.07056","n_code_links":1,"syntology":null},{"paper":"/paper/only-train-once-a-one-shot-neural-network","slug":"only-train-once-a-one-shot-neural-network","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","date":"2021-07-15","arxiv_id":"2107.07467","n_code_links":1,"syntology":null},{"paper":"/paper/self-supervised-contrastive-learning-with","slug":"self-supervised-contrastive-learning-with","title":"Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based Attacks","date":"2021-07-15","arxiv_id":"2107.07610","n_code_links":1,"syntology":null},{"paper":"/paper/star-sparse-transformer-based-action","slug":"star-sparse-transformer-based-action","title":"STAR: Sparse Transformer-based Action Recognition","date":"2021-07-15","arxiv_id":"2107.07089","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-based-machine-learning-for-fast","slug":"transformer-based-machine-learning-for-fast","title":"Transformer-based Machine Learning for Fast SAT Solvers and Logic Synthesis","date":"2021-07-15","arxiv_id":"2107.07116","n_code_links":1,"syntology":null},{"paper":"/paper/trusting-roberta-over-bert-insights-from","slug":"trusting-roberta-over-bert-insights-from","title":"Trusting RoBERTa over BERT: Insights from CheckListing the Natural Language Inference Task","date":"2021-07-15","arxiv_id":"2107.07229","n_code_links":1,"syntology":null},{"paper":"/paper/a-note-on-learning-rare-events-in-molecular","slug":"a-note-on-learning-rare-events-in-molecular","title":"A Note on Learning Rare Events in Molecular Dynamics using LSTM and Transformer","date":"2021-07-14","arxiv_id":"2107.06573","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-fine-tuning-for-sentiment-analysis-on","title":"BERT Fine-Tuning for Sentiment Analysis on Indonesian Mobile Apps Reviews","date":"2021-07-14","arxiv_id":"2107.06802","n_code_links":0,"syntology":null},{"paper":"/paper/chimera-efficiently-training-large-scale","slug":"chimera-efficiently-training-large-scale","title":"Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelines","date":"2021-07-14","arxiv_id":"2107.06925","n_code_links":1,"syntology":null},{"paper":"/paper/indonesia-s-fake-news-detection-using","slug":"indonesia-s-fake-news-detection-using","title":"Indonesia's Fake News Detection using Transformer Network","date":"2021-07-14","arxiv_id":"2107.06796","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-scale-news-classification-using-bert","title":"Large-Scale News Classification using BERT Language Model: Spark NLP Approach","date":"2021-07-14","arxiv_id":"2107.06785","n_code_links":0,"syntology":null},{"paper":"/paper/scalable-memory-protection-in-the-penglai","slug":"scalable-memory-protection-in-the-penglai","title":"Scalable Memory Protection in the PENGLAI Enclave","date":"2021-07-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"serialized-multi-layer-multi-head-attention","title":"Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding","date":"2021-07-14","arxiv_id":"2107.06493","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-deep-reinforcement-learning-approach-for-6","title":"A Deep Reinforcement Learning Approach for Traffic Signal Control Optimization","date":"2021-07-13","arxiv_id":"2107.06115","n_code_links":0,"syntology":null},{"paper":"/paper/automated-learning-rate-scheduler-for-large","slug":"automated-learning-rate-scheduler-for-large","title":"Automated Learning Rate Scheduler for Large-batch Training","date":"2021-07-13","arxiv_id":"2107.05855","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 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["kakaobrain/autowu"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploiting-network-structures-to-improve","title":"Exploiting Network Structures to Improve Semantic Representation for the Financial Domain","date":"2021-07-13","arxiv_id":"2107.05885","n_code_links":0,"syntology":null},{"paper":"/paper/hat-hierarchical-aggregation-transformers-for","slug":"hat-hierarchical-aggregation-transformers-for","title":"HAT: Hierarchical Aggregation Transformers for Person Re-identification","date":"2021-07-13","arxiv_id":"2107.05946","n_code_links":1,"syntology":null},{"paper":null,"slug":"rating-facts-under-coarse-to-fine-regimes","title":"Rating Facts under Coarse-to-fine Regimes","date":"2021-07-13","arxiv_id":"2107.06051","n_code_links":0,"syntology":null},{"paper":"/paper/the-piano-inpainting-application","slug":"the-piano-inpainting-application","title":"The Piano Inpainting Application","date":"2021-07-13","arxiv_id":"2107.05944","n_code_links":2,"syntology":null},{"paper":null,"slug":"tscan-dialog-structure-discovery-using-scan","title":"TSCAN : Dialog Structure discovery using SCAN","date":"2021-07-13","arxiv_id":"2107.06426","n_code_links":0,"syntology":null},{"paper":"/paper/using-bert-encoding-to-tackle-the-mad-lib","slug":"using-bert-encoding-to-tackle-the-mad-lib","title":"Using BERT Encoding to Tackle the Mad-lib Attack in SMS Spam Detection","date":"2021-07-13","arxiv_id":"2107.06400","n_code_links":1,"syntology":null},{"paper":"/paper/what-do-writing-features-tell-us-about-ai","slug":"what-do-writing-features-tell-us-about-ai","title":"What do writing features tell us about AI papers?","date":"2021-07-13","arxiv_id":"2107.06310","n_code_links":1,"syntology":null},{"paper":"/paper/a-flexible-multi-task-model-for-bert-serving","slug":"a-flexible-multi-task-model-for-bert-serving","title":"A Flexible Multi-Task Model for BERT Serving","date":"2021-07-12","arxiv_id":"2107.05377","n_code_links":1,"syntology":null},{"paper":null,"slug":"asking-clarifying-questions-based-on-negative","title":"Asking Clarifying Questions Based on Negative Feedback in Conversational Search","date":"2021-07-12","arxiv_id":"2107.05760","n_code_links":0,"syntology":null},{"paper":"/paper/coberl-contrastive-bert-for-reinforcement","slug":"coberl-contrastive-bert-for-reinforcement","title":"CoBERL: Contrastive BERT for Reinforcement Learning","date":"2021-07-12","arxiv_id":"2107.05431","n_code_links":2,"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":{"repos":["deepmind/dm_control"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/coper-a-query-adaptable-semantics-based","slug":"coper-a-query-adaptable-semantics-based","title":"COPER: a Query-adaptable Semantics-based Search Engine for Persian COVID-19 Articles","date":"2021-07-12","arxiv_id":"2107.05722","n_code_links":1,"syntology":null},{"paper":"/paper/mect-multi-metadata-embedding-based-cross","slug":"mect-multi-metadata-embedding-based-cross","title":"MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition","date":"2021-07-12","arxiv_id":"2107.05418","n_code_links":1,"syntology":null},{"paper":"/paper/midibert-piano-large-scale-pre-training-for","slug":"midibert-piano-large-scale-pre-training-for","title":"BERT-like Pre-training for Symbolic Piano Music Classification Tasks","date":"2021-07-12","arxiv_id":"2107.05223","n_code_links":1,"syntology":null},{"paper":"/paper/moocrep-a-unified-pre-trained-embedding-of","slug":"moocrep-a-unified-pre-trained-embedding-of","title":"MOOCRep: A Unified Pre-trained Embedding of MOOC Entities","date":"2021-07-12","arxiv_id":"2107.05154","n_code_links":1,"syntology":null},{"paper":"/paper/quantifying-explainability-in-nlp-and","slug":"quantifying-explainability-in-nlp-and","title":"Quantifying Explainability in NLP and Analyzing Algorithms for Performance-Explainability Tradeoff","date":"2021-07-12","arxiv_id":"2107.05693","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mnaylor5/quantifying-explainability"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/split-embed-and-merge-an-accurate-table","slug":"split-embed-and-merge-an-accurate-table","title":"Split, embed and merge: An accurate table structure recognizer","date":"2021-07-12","arxiv_id":"2107.05214","n_code_links":0,"syntology":null},{"paper":"/paper/transattunet-multi-level-attention-guided-u","slug":"transattunet-multi-level-attention-guided-u","title":"TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation","date":"2021-07-12","arxiv_id":"2107.05274","n_code_links":1,"syntology":null},{"paper":null,"slug":"visual-transformer-with-statistical-test-for","title":"Visual Transformer with Statistical Test for COVID-19 Classification","date":"2021-07-12","arxiv_id":"2107.05334","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-with-multi-modal-features-and","slug":"transformers-with-multi-modal-features-and","title":"Transformers with multi-modal features and post-fusion context for e-commerce session-based recommendation","date":"2021-07-11","arxiv_id":"2107.05124","n_code_links":0,"syntology":null},{"paper":"/paper/consensual-collaborative-training-and","slug":"consensual-collaborative-training-and","title":"Consensual Collaborative Training And Knowledge Distillation Based Facial Expression Recognition Under Noisy Annotations","date":"2021-07-10","arxiv_id":"2107.04746","n_code_links":3,"syntology":null},{"paper":"/paper/few-shot-domain-adaptation-with-polymorphic","slug":"few-shot-domain-adaptation-with-polymorphic","title":"Few-Shot Domain Adaptation with Polymorphic Transformers","date":"2021-07-10","arxiv_id":"2107.04805","n_code_links":1,"syntology":null},{"paper":null,"slug":"local-to-global-self-attention-in-vision","title":"Local-to-Global Self-Attention in Vision Transformers","date":"2021-07-10","arxiv_id":"2107.04735","n_code_links":0,"syntology":null},{"paper":null,"slug":"noise-stability-regularization-for-improving-1","title":"Noise Stability Regularization for Improving BERT Fine-tuning","date":"2021-07-10","arxiv_id":"2107.04835","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-initial-investigation-of-non-native-spoken","title":"An Initial Investigation of Non-Native Spoken Question-Answering","date":"2021-07-09","arxiv_id":"2107.04691","n_code_links":0,"syntology":null},{"paper":"/paper/can-deep-neural-networks-predict-data","slug":"can-deep-neural-networks-predict-data","title":"Can Deep Neural Networks Predict Data Correlations from Column Names?","date":"2021-07-09","arxiv_id":"2107.04553","n_code_links":1,"syntology":null},{"paper":null,"slug":"l2m-practical-posterior-laplace-approximation","title":"L2M: Practical posterior Laplace approximation with optimization-driven second moment estimation","date":"2021-07-09","arxiv_id":"2107.04695","n_code_links":0,"syntology":null},{"paper":"/paper/rex-revisiting-budgeted-training-with-an","slug":"rex-revisiting-budgeted-training-with-an","title":"REX: Revisiting Budgeted Training with an Improved Schedule","date":"2021-07-09","arxiv_id":"2107.04197","n_code_links":1,"syntology":null}],"record_sha256":"b4e90b8ba8bb651862a24ec36aff5a861686460dcb2ae4ed6d015c54adece1e2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}