{"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/softmax/papers/346","list_of":"/method/softmax","method":"Softmax","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":346,"pages_in_order":375,"rows_per_page":100,"rows":[34501,34600],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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/softmax","prev":"/method/softmax/papers/345","next":"/method/softmax/papers/347","papers":[{"paper":"/paper/low-rank-factorization-for-compact-multi-head","slug":"low-rank-factorization-for-compact-multi-head","title":"Low Rank Factorization for Compact Multi-Head Self-Attention","date":"2019-11-26","arxiv_id":"1912.00835","n_code_links":1,"syntology":null},{"paper":null,"slug":"mis-classified-vector-guided-softmax-loss-for","title":"Mis-classified Vector Guided Softmax Loss for Face Recognition","date":"2019-11-26","arxiv_id":"1912.00833","n_code_links":0,"syntology":null},{"paper":"/paper/password-conditioned-anonymization-and","slug":"password-conditioned-anonymization-and","title":"Password-conditioned Anonymization and Deanonymization with Face Identity Transformers","date":"2019-11-26","arxiv_id":"1911.11759","n_code_links":1,"syntology":null},{"paper":null,"slug":"privacy-preserving-neural-network-inference","title":"Privacy preserving Neural Network Inference on Encrypted Data with GPUs","date":"2019-11-26","arxiv_id":"1911.11377","n_code_links":0,"syntology":null},{"paper":null,"slug":"relevance-promoting-language-model-for-short","title":"Relevance-Promoting Language Model for Short-Text Conversation","date":"2019-11-26","arxiv_id":"1911.11489","n_code_links":0,"syntology":null},{"paper":"/paper/single-headed-attention-rnn-stop-thinking","slug":"single-headed-attention-rnn-stop-thinking","title":"Single Headed Attention RNN: Stop Thinking With Your Head","date":"2019-11-26","arxiv_id":"1911.11423","n_code_links":5,"syntology":null},{"paper":null,"slug":"binarized-neural-architecture-search","title":"Binarized Neural Architecture Search","date":"2019-11-25","arxiv_id":"1911.10862","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-disentanglement-with-independence","title":"Towards Better Understanding of Disentangled Representations via Mutual Information","date":"2019-11-25","arxiv_id":"1911.10922","n_code_links":0,"syntology":null},{"paper":null,"slug":"cumulative-sum-ranking","title":"Cumulative Sum Ranking","date":"2019-11-25","arxiv_id":"1911.11255","n_code_links":0,"syntology":null},{"paper":null,"slug":"filling-conversation-ellipsis-for-better","title":"Filling Conversation Ellipsis for Better Social Dialog Understanding","date":"2019-11-25","arxiv_id":"1911.10776","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-reuse-translations-guiding-neural","title":"Learning to Reuse Translations: Guiding Neural Machine Translation with Examples","date":"2019-11-25","arxiv_id":"1911.10732","n_code_links":0,"syntology":null},{"paper":"/paper/meta-learning-of-neural-architectures-for-few","slug":"meta-learning-of-neural-architectures-for-few","title":"Meta-Learning of Neural Architectures for Few-Shot Learning","date":"2019-11-25","arxiv_id":"1911.11090","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"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":["boschresearch/metanas"],"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":"/paper/rethinking-softmax-with-cross-entropy-neural","slug":"rethinking-softmax-with-cross-entropy-neural","title":"Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator","date":"2019-11-25","arxiv_id":"1911.10688","n_code_links":1,"syntology":null},{"paper":"/paper/shape-aware-feature-extraction-for-instance","slug":"shape-aware-feature-extraction-for-instance","title":"Deeply Shape-guided Cascade for Instance Segmentation","date":"2019-11-25","arxiv_id":"1911.11263","n_code_links":1,"syntology":null},{"paper":"/paper/traffic-map-prediction-using-unet-based-deep","slug":"traffic-map-prediction-using-unet-based-deep","title":"Traffic map prediction using UNet based deep convolutional neural network","date":"2019-11-25","arxiv_id":"1912.05288","n_code_links":1,"syntology":null},{"paper":"/paper/who-did-they-respond-to-conversation","slug":"who-did-they-respond-to-conversation","title":"Who did They Respond to? Conversation Structure Modeling using Masked Hierarchical Transformer","date":"2019-11-25","arxiv_id":"1911.10666","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploiting-operation-importance-for","title":"Exploiting Operation Importance for Differentiable Neural Architecture Search","date":"2019-11-24","arxiv_id":"1911.10511","n_code_links":0,"syntology":null},{"paper":"/paper/reinventing-2d-convolutions-for-3d-medical","slug":"reinventing-2d-convolutions-for-3d-medical","title":"Reinventing 2D Convolutions for 3D Images","date":"2019-11-24","arxiv_id":"1911.10477","n_code_links":2,"syntology":null},{"paper":null,"slug":"doctor2vec-dynamic-doctor-representation","title":"Doctor2Vec: Dynamic Doctor Representation Learning for Clinical Trial Recruitment","date":"2019-11-23","arxiv_id":"1911.10395","n_code_links":0,"syntology":null},{"paper":null,"slug":"computer-vision-based-accident-detection-in","title":"Computer Vision-based Accident Detection in Traffic Surveillance","date":"2019-11-22","arxiv_id":"1911.10037","n_code_links":0,"syntology":null},{"paper":null,"slug":"factorized-multimodal-transformer-for","title":"Factorized Multimodal Transformer for Multimodal Sequential Learning","date":"2019-11-22","arxiv_id":"1911.09826","n_code_links":0,"syntology":null},{"paper":null,"slug":"high-quality-elmo-embeddings-for-seven-less","title":"High Quality ELMo Embeddings for Seven Less-Resourced Languages","date":"2019-11-22","arxiv_id":"1911.10049","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-n-gram-language-models-with-pre","title":"Improving N-gram Language Models with Pre-trained Deep Transformer","date":"2019-11-22","arxiv_id":"1911.10235","n_code_links":0,"syntology":null},{"paper":null,"slug":"neuron-interaction-based-representation","title":"Neuron Interaction Based Representation Composition for Neural Machine Translation","date":"2019-11-22","arxiv_id":"1911.09877","n_code_links":0,"syntology":null},{"paper":null,"slug":"shape-detection-in-2d-ultrasound-images","title":"Shape Detection In 2D Ultrasound Images","date":"2019-11-22","arxiv_id":"1911.09863","n_code_links":0,"syntology":null},{"paper":null,"slug":"sm-nas-structural-to-modular-neural","title":"SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection","date":"2019-11-22","arxiv_id":"1911.09929","n_code_links":0,"syntology":null},{"paper":null,"slug":"spectral-graph-transformer-networks-for-brain","title":"Spectral Graph Transformer Networks for Brain Surface Parcellation","date":"2019-11-22","arxiv_id":"1911.10118","n_code_links":0,"syntology":null},{"paper":"/paper/automatically-neutralizing-subjective-bias-in","slug":"automatically-neutralizing-subjective-bias-in","title":"Automatically Neutralizing Subjective Bias in Text","date":"2019-11-21","arxiv_id":"1911.09709","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":12,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"12 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rpryzant/neutralizing-bias"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/chemical-protein-interaction-extraction-via","slug":"chemical-protein-interaction-extraction-via","title":"Chemical-protein Interaction Extraction via Gaussian Probability Distribution and External Biomedical Knowledge","date":"2019-11-21","arxiv_id":"1911.09487","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-proxy-generation-for-fast-and-efficient","title":"Data Proxy Generation for Fast and Efficient Neural Architecture Search","date":"2019-11-21","arxiv_id":"1911.09322","n_code_links":0,"syntology":null},{"paper":"/paper/fast-sparse-convnets-1","slug":"fast-sparse-convnets-1","title":"Fast Sparse ConvNets","date":"2019-11-21","arxiv_id":"1911.09723","n_code_links":5,"syntology":null},{"paper":"/paper/filter-response-normalization-layer","slug":"filter-response-normalization-layer","title":"Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks","date":"2019-11-21","arxiv_id":"1911.09737","n_code_links":16,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"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":"/paper/learning-spatial-fusion-for-single-shot","slug":"learning-spatial-fusion-for-single-shot","title":"Learning Spatial Fusion for Single-Shot Object Detection","date":"2019-11-21","arxiv_id":"1911.09516","n_code_links":1,"syntology":null},{"paper":null,"slug":"paraphrasing-with-large-language-models-1","title":"Paraphrasing with Large Language Models","date":"2019-11-21","arxiv_id":"1911.09661","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-hierarchy-emerges-in-deep-generative","slug":"semantic-hierarchy-emerges-in-deep-generative","title":"Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis","date":"2019-11-21","arxiv_id":"1911.09267","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":1,"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":null}},{"paper":null,"slug":"wildmix-dataset-and-spectro-temporal","title":"WildMix Dataset and Spectro-Temporal Transformer Model for Monoaural Audio Source Separation","date":"2019-11-21","arxiv_id":"1911.09783","n_code_links":0,"syntology":null},{"paper":null,"slug":"avoiding-jammers-a-reinforcement-learning","title":"Avoiding Jammers: A Reinforcement Learning Approach","date":"2019-11-20","arxiv_id":"1911.08874","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-transferability-and","title":"Evaluating the Transferability and Adversarial Discrimination of Convolutional Neural Networks for Threat Object Detection and Classification within X-Ray Security Imagery","date":"2019-11-20","arxiv_id":"1911.08966","n_code_links":0,"syntology":null},{"paper":null,"slug":"inspect-transfer-learning-architecture-with","title":"Inspect Transfer Learning Architecture with Dilated Convolution","date":"2019-11-20","arxiv_id":"1911.08769","n_code_links":0,"syntology":null},{"paper":null,"slug":"joint-emotion-label-space-modelling-for","title":"Joint Emotion Label Space Modelling for Affect Lexica","date":"2019-11-20","arxiv_id":"1911.08782","n_code_links":0,"syntology":null},{"paper":null,"slug":"search-to-distill-pearls-are-everywhere-but","title":"Search to Distill: Pearls are Everywhere but not the Eyes","date":"2019-11-20","arxiv_id":"1911.09074","n_code_links":0,"syntology":null},{"paper":null,"slug":"toward-filament-segmentation-using-deep","title":"Toward Filament Segmentation Using Deep Neural Networks","date":"2019-11-20","arxiv_id":"1912.02743","n_code_links":0,"syntology":null},{"paper":null,"slug":"addnet-deep-neural-networks-using-fpga","title":"AddNet: Deep Neural Networks Using FPGA-Optimized Multipliers","date":"2019-11-19","arxiv_id":"1911.08097","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-composition-with-idleblock-more","title":"Hybrid Composition with IdleBlock: More Efficient Networks for Image Recognition","date":"2019-11-19","arxiv_id":"1911.08609","n_code_links":0,"syntology":null},{"paper":"/paper/ifq-net-integrated-fixed-point-quantization","slug":"ifq-net-integrated-fixed-point-quantization","title":"IFQ-Net: Integrated Fixed-point Quantization Networks for Embedded Vision","date":"2019-11-19","arxiv_id":"1911.08076","n_code_links":0,"syntology":null},{"paper":null,"slug":"marionette-few-shot-face-reenactment","title":"MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets","date":"2019-11-19","arxiv_id":"1911.08139","n_code_links":0,"syntology":null},{"paper":null,"slug":"partial-auc-optimization-based-deep-speaker","title":"Partial AUC optimization based deep speaker embeddings with class-center learning for text-independent speaker verification","date":"2019-11-19","arxiv_id":"1911.08077","n_code_links":0,"syntology":null},{"paper":"/paper/towards-lingua-franca-named-entity","slug":"towards-lingua-franca-named-entity","title":"Towards Lingua Franca Named Entity Recognition with BERT","date":"2019-11-19","arxiv_id":"1912.01389","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-non-toxic-landscapes-automatic-toxic","title":"Towards non-toxic landscapes: Automatic toxic comment detection using DNN","date":"2019-11-19","arxiv_id":"1911.08395","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-natural-question-answering-with-1","title":"Unsupervised Natural Question Answering with a Small Model","date":"2019-11-19","arxiv_id":"1911.08340","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-based-pilgrim-detection-using","title":"AI-based Pilgrim Detection using Convolutional Neural Networks","date":"2019-11-18","arxiv_id":"1911.07509","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-grained-neural-architecture-search","title":"Fine-Grained Neural Architecture Search","date":"2019-11-18","arxiv_id":"1911.07478","n_code_links":0,"syntology":null},{"paper":"/paper/graph-transformer-for-graph-to-sequence","slug":"graph-transformer-for-graph-to-sequence","title":"Graph Transformer for Graph-to-Sequence Learning","date":"2019-11-18","arxiv_id":"1911.07470","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":7,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["jcyk/gtos"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"immunecs-neural-committee-search-by-an","title":"ImmuNeCS: Neural Committee Search by an Artificial Immune System","date":"2019-11-18","arxiv_id":"1911.07729","n_code_links":0,"syntology":null},{"paper":"/paper/segmentation-guided-attention-network-for","slug":"segmentation-guided-attention-network-for","title":"Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss","date":"2019-11-18","arxiv_id":"1911.07990","n_code_links":1,"syntology":null},{"paper":null,"slug":"dense-color-constancy-with-effective-edge","title":"ADCC: An Effective and Intelligent Attention Dense Color Constancy System for Studying Images in Smart Cities","date":"2019-11-17","arxiv_id":"1911.07163","n_code_links":0,"syntology":null},{"paper":"/paper/improving-relation-classification-by-entity","slug":"improving-relation-classification-by-entity","title":"Improving Relation Classification by Entity Pair Graph","date":"2019-11-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/muse-parallel-multi-scale-attention-for","slug":"muse-parallel-multi-scale-attention-for","title":"MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning","date":"2019-11-17","arxiv_id":"1911.09483","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["lancopku/MUSE"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":"/paper/neural-recurrent-structure-search-for","slug":"neural-recurrent-structure-search-for","title":"Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding","date":"2019-11-17","arxiv_id":"1911.07132","n_code_links":4,"syntology":null},{"paper":null,"slug":"unsupervised-visual-representation-learning-2","title":"Unsupervised Visual Representation Learning with Increasing Object Shape Bias","date":"2019-11-17","arxiv_id":"1911.07272","n_code_links":0,"syntology":null},{"paper":null,"slug":"liver-steatosis-segmentation-with-deep","title":"Liver Steatosis Segmentation with Deep Learning Methods","date":"2019-11-16","arxiv_id":"1911.07088","n_code_links":0,"syntology":null},{"paper":null,"slug":"music-theme-recognition-using-cnn-and-self","title":"Music theme recognition using CNN and self-attention","date":"2019-11-16","arxiv_id":"1911.07041","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimized-cnn-for-polsar-image-classification","title":"Automatic Design of CNNs via Differentiable Neural Architecture Search for PolSAR Image Classification","date":"2019-11-16","arxiv_id":"1911.06993","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-reading-comprehension-with-linguistic","title":"Robust Reading Comprehension with Linguistic Constraints via Posterior Regularization","date":"2019-11-16","arxiv_id":"1911.06948","n_code_links":0,"syntology":null},{"paper":"/paper/centermask-real-time-anchor-free-instance-1","slug":"centermask-real-time-anchor-free-instance-1","title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","date":"2019-11-15","arxiv_id":"1911.06667","n_code_links":8,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["youngwanLEE/CenterMask"],"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":["listed","official"]}}},{"paper":null,"slug":"curriculum-self-paced-learning-for-cross","title":"Curriculum Self-Paced Learning for Cross-Domain Object Detection","date":"2019-11-15","arxiv_id":"1911.06849","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-robustness-of-language-models-for","title":"Evaluating robustness of language models for chief complaint extraction from patient-generated text","date":"2019-11-15","arxiv_id":"1911.06915","n_code_links":0,"syntology":null},{"paper":"/paper/multi-attention-networks-for-temporal","slug":"multi-attention-networks-for-temporal","title":"Multi-attention Networks for Temporal Localization of Video-level Labels","date":"2019-11-15","arxiv_id":"1911.06866","n_code_links":1,"syntology":null},{"paper":"/paper/selection-based-question-answering-of-an-mooc","slug":"selection-based-question-answering-of-an-mooc","title":"Selection-based Question Answering of an MOOC","date":"2019-11-15","arxiv_id":"1911.07629","n_code_links":1,"syntology":null},{"paper":null,"slug":"sequential-recommendation-with-relation-aware","title":"Sequential Recommendation with Relation-Aware Kernelized Self-Attention","date":"2019-11-15","arxiv_id":"1911.06478","n_code_links":0,"syntology":null},{"paper":"/paper/skin-lesion-segmentation-using-segnet-with","slug":"skin-lesion-segmentation-using-segnet-with","title":"Skin Lesion Segmentation using SegNet with Binary Cross-Entropy","date":"2019-11-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"attention-on-abstract-visual-reasoning","title":"Attention on Abstract Visual Reasoning","date":"2019-11-14","arxiv_id":"1911.05990","n_code_links":0,"syntology":null},{"paper":"/paper/iterative-answer-prediction-with-pointer","slug":"iterative-answer-prediction-with-pointer","title":"Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA","date":"2019-11-14","arxiv_id":"1911.06258","n_code_links":1,"syntology":null},{"paper":null,"slug":"sdgm-sparse-bayesian-classifier-based-on-a","title":"A Discriminative Gaussian Mixture Model with Sparsity","date":"2019-11-14","arxiv_id":"1911.06028","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-and-evaluating-a-deep-learning","title":"Adapting and evaluating a deep learning language model for clinical why-question answering","date":"2019-11-13","arxiv_id":"1911.05604","n_code_links":0,"syntology":null},{"paper":"/paper/compressive-transformers-for-long-range-1","slug":"compressive-transformers-for-long-range-1","title":"Compressive Transformers for Long-Range Sequence Modelling","date":"2019-11-13","arxiv_id":"1911.05507","n_code_links":6,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":null}},{"paper":null,"slug":"dynamic-connected-neural-decision-classifier","title":"Dynamic Connected Neural Decision Classifier and Regressor with Dynamic Softing Pruning","date":"2019-11-13","arxiv_id":"1911.05443","n_code_links":0,"syntology":null},{"paper":null,"slug":"image-based-feature-representation-for","title":"Image-Based Feature Representation for Insider Threat Classification","date":"2019-11-13","arxiv_id":"1911.05879","n_code_links":0,"syntology":null},{"paper":"/paper/momentum-contrast-for-unsupervised-visual","slug":"momentum-contrast-for-unsupervised-visual","title":"Momentum Contrast for Unsupervised Visual Representation Learning","date":"2019-11-13","arxiv_id":"1911.05722","n_code_links":44,"syntology":{"ran":28,"of":42,"n_ran_checked":23,"n_instrument":5,"unverified":14,"pointer_only":19,"phrase":"28 ran (of which 16 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified","official":{"repos":["facebookresearch/moco","ppwwyyxx/moco.tensorflow"],"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/self-labelling-via-simultaneous-clustering-1","slug":"self-labelling-via-simultaneous-clustering-1","title":"Self-labelling via simultaneous clustering and representation learning","date":"2019-11-13","arxiv_id":"1911.05371","n_code_links":5,"syntology":{"ran":16,"of":18,"n_ran_checked":12,"n_instrument":4,"unverified":2,"pointer_only":6,"phrase":"16 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; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["yukimasano/self-label"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/unsupervised-domain-adaptation-on-reading","slug":"unsupervised-domain-adaptation-on-reading","title":"Unsupervised Domain Adaptation on Reading Comprehension","date":"2019-11-13","arxiv_id":"1911.06137","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-do-you-mean-bert-assessing-bert-as-a","title":"What do you mean, BERT? Assessing BERT as a Distributional Semantics Model","date":"2019-11-13","arxiv_id":"1911.05758","n_code_links":0,"syntology":null},{"paper":"/paper/a-syntax-aware-multi-task-learning-framework-1","slug":"a-syntax-aware-multi-task-learning-framework-1","title":"A Syntax-aware Multi-task Learning Framework for Chinese Semantic Role Labeling","date":"2019-11-12","arxiv_id":"1911.04641","n_code_links":1,"syntology":null},{"paper":null,"slug":"character-based-nmt-with-transformer","title":"Character-based NMT with Transformer","date":"2019-11-12","arxiv_id":"1911.04997","n_code_links":0,"syntology":null},{"paper":null,"slug":"cheetah-an-ultra-fast-approximation-free-and","title":"CHEETAH: An Ultra-Fast, Approximation-Free, and Privacy-Preserved Neural Network Framework based on Joint Obscure Linear and Nonlinear Computations","date":"2019-11-12","arxiv_id":"1911.05184","n_code_links":0,"syntology":null},{"paper":null,"slug":"equalization-loss-for-large-vocabulary","title":"Equalization Loss for Large Vocabulary Instance Segmentation","date":"2019-11-12","arxiv_id":"1911.04692","n_code_links":0,"syntology":null},{"paper":"/paper/smiles-transformer-pre-trained-molecular","slug":"smiles-transformer-pre-trained-molecular","title":"SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery","date":"2019-11-12","arxiv_id":"1911.04738","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["DSPsleeporg/smiles-transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/time-dynamic-estimates-of-the-reliability-of","slug":"time-dynamic-estimates-of-the-reliability-of","title":"Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networks","date":"2019-11-12","arxiv_id":"1911.05075","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-unified-sequence-to-sequence-front-end","title":"A unified sequence-to-sequence front-end model for Mandarin text-to-speech synthesis","date":"2019-11-11","arxiv_id":"1911.04111","n_code_links":0,"syntology":null},{"paper":null,"slug":"activity-monitoring-of-islamic-prayer-salat","title":"Activity Monitoring of Islamic Prayer (Salat) Postures using Deep Learning","date":"2019-11-11","arxiv_id":"1911.04102","n_code_links":0,"syntology":null},{"paper":null,"slug":"attending-to-entities-for-better-text","title":"Attending to Entities for Better Text Understanding","date":"2019-11-11","arxiv_id":"1911.04361","n_code_links":0,"syntology":null},{"paper":"/paper/bp-transformer-modelling-long-range-context","slug":"bp-transformer-modelling-long-range-context","title":"BP-Transformer: Modelling Long-Range Context via Binary Partitioning","date":"2019-11-11","arxiv_id":"1911.04070","n_code_links":2,"syntology":{"ran":2,"of":7,"n_ran_checked":2,"n_instrument":0,"unverified":5,"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) · 5 unverified","official":{"repos":["yzh119/BPT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/disentangle-align-and-fuse-for-multimodal-and","slug":"disentangle-align-and-fuse-for-multimodal-and","title":"Disentangle, align and fuse for multimodal and semi-supervised image segmentation","date":"2019-11-11","arxiv_id":"1911.04417","n_code_links":2,"syntology":null},{"paper":"/paper/learning-graph-convolutional-network-for","slug":"learning-graph-convolutional-network-for","title":"Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching","date":"2019-11-11","arxiv_id":"1911.04131","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"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":null}},{"paper":null,"slug":"long-span-language-modeling-for-speech","title":"Long-span language modeling for speech recognition","date":"2019-11-11","arxiv_id":"1911.04571","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-answering-for-machine-reading","title":"Meta Answering for Machine Reading","date":"2019-11-11","arxiv_id":"1911.04156","n_code_links":0,"syntology":null},{"paper":"/paper/negbert-a-transfer-learning-approach-for","slug":"negbert-a-transfer-learning-approach-for","title":"NegBERT: A Transfer Learning Approach for Negation Detection and Scope Resolution","date":"2019-11-11","arxiv_id":"1911.04211","n_code_links":1,"syntology":null},{"paper":"/paper/tanda-transfer-and-adapt-pre-trained","slug":"tanda-transfer-and-adapt-pre-trained","title":"TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection","date":"2019-11-11","arxiv_id":"1911.04118","n_code_links":2,"syntology":null},{"paper":null,"slug":"understanding-bert-performance-in-propaganda-1","title":"Understanding BERT performance in propaganda analysis","date":"2019-11-11","arxiv_id":"1911.04525","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-the-knowledge-of-bert-for-text-1","slug":"distilling-the-knowledge-of-bert-for-text-1","title":"Distilling Knowledge Learned in BERT for Text Generation","date":"2019-11-10","arxiv_id":"1911.03829","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: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ChenRocks/Distill-BERT-Textgen"],"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"]}}}],"record_sha256":"62af87c00b31e1e6bce3ada8da59d38384f705825b06fb92457f710362912a81","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}