{"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/343","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":343,"pages_in_order":375,"rows_per_page":100,"rows":[34201,34300],"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/342","next":"/method/softmax/papers/344","papers":[{"paper":"/paper/transformer-transducer-a-streamable-speech","slug":"transformer-transducer-a-streamable-speech","title":"Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss","date":"2020-02-07","arxiv_id":"2002.02562","n_code_links":5,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"understanding-and-optimizing-packed-neural","title":"Understanding and Optimizing Packed Neural Network Training for Hyper-Parameter Tuning","date":"2020-02-07","arxiv_id":"2002.02885","n_code_links":0,"syntology":null},{"paper":"/paper/few-shot-learning-as-domain-adaptation","slug":"few-shot-learning-as-domain-adaptation","title":"Few-Shot Learning as Domain Adaptation: Algorithm and Analysis","date":"2020-02-06","arxiv_id":"2002.02050","n_code_links":0,"syntology":null},{"paper":"/paper/introducing-aspects-of-creativity-in","slug":"introducing-aspects-of-creativity-in","title":"Introducing Aspects of Creativity in Automatic Poetry Generation","date":"2020-02-06","arxiv_id":"2002.02511","n_code_links":1,"syntology":null},{"paper":null,"slug":"perm2vec-graph-permutation-selection-for","title":"perm2vec: Graph Permutation Selection for Decoding of Error Correction Codes using Self-Attention","date":"2020-02-06","arxiv_id":"2002.02315","n_code_links":0,"syntology":null},{"paper":"/paper/variational-depth-search-in-resnets","slug":"variational-depth-search-in-resnets","title":"Variational Depth Search in ResNets","date":"2020-02-06","arxiv_id":"2002.02797","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["cambridge-mlg/arch_uncert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"aligning-the-pretraining-and-finetuning","title":"Aligning the Pretraining and Finetuning Objectives of Language Models","date":"2020-02-05","arxiv_id":"2002.02000","n_code_links":0,"syntology":null},{"paper":"/paper/k-adapter-infusing-knowledge-into-pre-trained","slug":"k-adapter-infusing-knowledge-into-pre-trained","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","date":"2020-02-05","arxiv_id":"2002.01808","n_code_links":2,"syntology":{"ran":11,"of":14,"n_ran_checked":6,"n_instrument":5,"unverified":3,"pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/rapid-adaptation-of-bert-for-information","slug":"rapid-adaptation-of-bert-for-information","title":"Rapid Adaptation of BERT for Information Extraction on Domain-Specific Business Documents","date":"2020-02-05","arxiv_id":"2002.01861","n_code_links":1,"syntology":null},{"paper":"/paper/vocoder-free-end-to-end-voice-conversion-with","slug":"vocoder-free-end-to-end-voice-conversion-with","title":"Vocoder-free End-to-End Voice Conversion with Transformer Network","date":"2020-02-05","arxiv_id":"2002.03808","n_code_links":1,"syntology":null},{"paper":"/paper/interpretable-time-budget-constrained","slug":"interpretable-time-budget-constrained","title":"Interpretable & Time-Budget-Constrained Contextualization for Re-Ranking","date":"2020-02-04","arxiv_id":"2002.01854","n_code_links":1,"syntology":null},{"paper":"/paper/large-batch-training-does-not-need-warmup","slug":"large-batch-training-does-not-need-warmup","title":"Large Batch Training Does Not Need Warmup","date":"2020-02-04","arxiv_id":"2002.01576","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-long-and-short-term-user-literal","title":"Learning Long- and Short-Term User Literal-Preference with Multimodal Hierarchical Transformer Network for Personalized Image Caption","date":"2020-02-04","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multistage-model-for-robust-face-alignment","title":"Multistage Model for Robust Face Alignment Using Deep Neural Networks","date":"2020-02-04","arxiv_id":"2002.01075","n_code_links":0,"syntology":null},{"paper":"/paper/bertrand-dr-improving-text-to-sql-using-a","slug":"bertrand-dr-improving-text-to-sql-using-a","title":"Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-ranker","date":"2020-02-03","arxiv_id":"2002.00557","n_code_links":1,"syntology":null},{"paper":null,"slug":"detection-of-obstructive-sleep-apnoea-using","title":"Detection of Obstructive Sleep Apnoea Using Features Extracted from Segmented Time-Series ECG Signals Using a One Dimensional Convolutional Neural Network","date":"2020-02-03","arxiv_id":"2002.00833","n_code_links":0,"syntology":null},{"paper":null,"slug":"exponential-discretization-of-weights-of","title":"Exponential discretization of weights of neural network connections in pre-trained neural networks","date":"2020-02-03","arxiv_id":"2002.00623","n_code_links":0,"syntology":null},{"paper":"/paper/iart-intent-aware-response-ranking-with","slug":"iart-intent-aware-response-ranking-with","title":"IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems","date":"2020-02-03","arxiv_id":"2002.00571","n_code_links":1,"syntology":null},{"paper":"/paper/robust-saliency-maps-with-decoy-enhanced","slug":"robust-saliency-maps-with-decoy-enhanced","title":"DANCE: Enhancing saliency maps using decoys","date":"2020-02-03","arxiv_id":"2002.00526","n_code_links":1,"syntology":null},{"paper":"/paper/beat-the-ai-investigating-adversarial-human","slug":"beat-the-ai-investigating-adversarial-human","title":"Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension","date":"2020-02-02","arxiv_id":"2002.00293","n_code_links":1,"syntology":null},{"paper":"/paper/non-linear-neurons-with-human-like-apical","slug":"non-linear-neurons-with-human-like-apical","title":"Non-linear Neurons with Human-like Apical Dendrite Activations","date":"2020-02-02","arxiv_id":"2003.03229","n_code_links":1,"syntology":null},{"paper":"/paper/bridging-text-and-video-a-universal","slug":"bridging-text-and-video-a-universal","title":"Bridging Text and Video: A Universal Multimodal Transformer for Video-Audio Scene-Aware Dialog","date":"2020-02-01","arxiv_id":"2002.00163","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"fine-tuning-bert-for-schema-guided-zero-shot","title":"Fine-Tuning BERT for Schema-Guided Zero-Shot Dialogue State Tracking","date":"2020-02-01","arxiv_id":"2002.00181","n_code_links":0,"syntology":null},{"paper":"/paper/pop-music-transformer-generating-music-with","slug":"pop-music-transformer-generating-music-with","title":"Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions","date":"2020-02-01","arxiv_id":"2002.00212","n_code_links":7,"syntology":null},{"paper":null,"slug":"parkingsticker-a-real-world-object-detection","title":"ParkingSticker: A Real-World Object Detection Dataset","date":"2020-01-31","arxiv_id":"2001.11639","n_code_links":0,"syntology":null},{"paper":"/paper/pretrained-transformers-for-simple-question","slug":"pretrained-transformers-for-simple-question","title":"Pretrained Transformers for Simple Question Answering over Knowledge Graphs","date":"2020-01-31","arxiv_id":"2001.11985","n_code_links":1,"syntology":null},{"paper":null,"slug":"reconstructing-natural-scenes-from-fmri","title":"Reconstructing Natural Scenes from fMRI Patterns using BigBiGAN","date":"2020-01-31","arxiv_id":"2001.11761","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-training-for-aspect-based","slug":"adversarial-training-for-aspect-based","title":"Adversarial Training for Aspect-Based Sentiment Analysis with BERT","date":"2020-01-30","arxiv_id":"2001.11316","n_code_links":4,"syntology":null},{"paper":null,"slug":"do-we-need-word-order-information-for-cross","title":"On the Importance of Word Order Information in Cross-lingual Sequence Labeling","date":"2020-01-30","arxiv_id":"2001.11164","n_code_links":0,"syntology":null},{"paper":null,"slug":"ellipse-r-cnn-learning-to-infer-elliptical","title":"Ellipse R-CNN: Learning to Infer Elliptical Object from Clustering and Occlusion","date":"2020-01-30","arxiv_id":"2001.11584","n_code_links":0,"syntology":null},{"paper":null,"slug":"learn-to-predict-sets-using-feed-forward","title":"Learn to Predict Sets Using Feed-Forward Neural Networks","date":"2020-01-30","arxiv_id":"2001.11845","n_code_links":0,"syntology":null},{"paper":"/paper/weakly-supervised-instance-segmentation-by","slug":"weakly-supervised-instance-segmentation-by","title":"Weakly Supervised Instance Segmentation by Deep Community Learning","date":"2020-01-30","arxiv_id":"2001.11207","n_code_links":0,"syntology":null},{"paper":null,"slug":"3d-aggregated-faster-r-cnn-for-general-lesion","title":"3D Aggregated Faster R-CNN for General Lesion Detection","date":"2020-01-29","arxiv_id":"2001.11071","n_code_links":0,"syntology":null},{"paper":"/paper/interpretable-rumor-detection-in-microblogs","slug":"interpretable-rumor-detection-in-microblogs","title":"Interpretable Rumor Detection in Microblogs by Attending to User Interactions","date":"2020-01-29","arxiv_id":"2001.10667","n_code_links":1,"syntology":null},{"paper":"/paper/pre-defined-sparsity-for-low-complexity","slug":"pre-defined-sparsity-for-low-complexity","title":"Pre-defined Sparsity for Low-Complexity Convolutional Neural Networks","date":"2020-01-29","arxiv_id":"2001.10710","n_code_links":1,"syntology":null},{"paper":null,"slug":"joint-contextual-modeling-for-asr-correction","title":"Joint Contextual Modeling for ASR Correction and Language Understanding","date":"2020-01-28","arxiv_id":"2002.00750","n_code_links":0,"syntology":null},{"paper":"/paper/nas-bench-1shot1-benchmarking-and-dissecting-1","slug":"nas-bench-1shot1-benchmarking-and-dissecting-1","title":"NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search","date":"2020-01-28","arxiv_id":"2001.10422","n_code_links":1,"syntology":null},{"paper":null,"slug":"pel-bert-a-joint-model-for-protocol-entity","title":"PEL-BERT: A Joint Model for Protocol Entity Linking","date":"2020-01-28","arxiv_id":"2002.00744","n_code_links":0,"syntology":null},{"paper":null,"slug":"near-real-time-map-building-with-multi-class","title":"Near real-time map building with multi-class image set labelling and classification of road conditions using convolutional neural networks","date":"2020-01-27","arxiv_id":"2001.09947","n_code_links":0,"syntology":null},{"paper":"/paper/retrospective-reader-for-machine-reading","slug":"retrospective-reader-for-machine-reading","title":"Retrospective Reader for Machine Reading Comprehension","date":"2020-01-27","arxiv_id":"2001.09694","n_code_links":2,"syntology":null},{"paper":null,"slug":"bayesian-optimization-for-backpropagation-in","title":"Bayesian optimization for backpropagation in Monte-Carlo tree search","date":"2020-01-25","arxiv_id":"2001.09325","n_code_links":0,"syntology":null},{"paper":null,"slug":"further-boosting-bert-based-models-by","title":"BERT's output layer recognizes all hidden layers? Some Intriguing Phenomena and a simple way to boost BERT","date":"2020-01-25","arxiv_id":"2001.09309","n_code_links":0,"syntology":null},{"paper":null,"slug":"generation-distillation-for-efficient-natural-1","title":"Generation-Distillation for Efficient Natural Language Understanding in Low-Data Settings","date":"2020-01-25","arxiv_id":"2002.00733","n_code_links":0,"syntology":null},{"paper":"/paper/power-bert-accelerating-bert-inference-for","slug":"power-bert-accelerating-bert-inference-for","title":"PoWER-BERT: Accelerating BERT Inference via Progressive Word-vector Elimination","date":"2020-01-24","arxiv_id":"2001.08950","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["IBM/PoWER-BERT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"applying-recent-innovations-from-nlp-to-mooc","title":"Applying Recent Innovations from NLP to MOOC Student Course Trajectory Modeling","date":"2020-01-23","arxiv_id":"2001.08333","n_code_links":0,"syntology":null},{"paper":"/paper/cnn-cass-cnn-for-classification-of-coronary","slug":"cnn-cass-cnn-for-classification-of-coronary","title":"CNN-CASS: CNN for Classification of Coronary Artery Stenosis Score in MPR Images","date":"2020-01-23","arxiv_id":"2001.08593","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-a-transformer-based-language","title":"Reducing Non-Normative Text Generation from Language Models","date":"2020-01-23","arxiv_id":"2001.08764","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-objective-neural-architecture-search-2","title":"Multi-objective Neural Architecture Search via Non-stationary Policy Gradient","date":"2020-01-23","arxiv_id":"2001.08437","n_code_links":0,"syntology":null},{"paper":null,"slug":"navigation-based-candidate-expansion-and","title":"Navigation-Based Candidate Expansion and Pretrained Language Models for Citation Recommendation","date":"2020-01-23","arxiv_id":"2001.08687","n_code_links":0,"syntology":null},{"paper":"/paper/attention-a-lightweight-2d-hand-pose","slug":"attention-a-lightweight-2d-hand-pose","title":"Attention! A Lightweight 2D Hand Pose Estimation Approach","date":"2020-01-22","arxiv_id":"2001.08047","n_code_links":1,"syntology":null},{"paper":null,"slug":"autofcl-automatically-tuning-fully-connected","title":"AutoFCL: Automatically Tuning Fully Connected Layers for Handling Small Dataset","date":"2020-01-22","arxiv_id":"2001.11951","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-denoising-pre-training-for","slug":"multilingual-denoising-pre-training-for","title":"Multilingual Denoising Pre-training for Neural Machine Translation","date":"2020-01-22","arxiv_id":"2001.08210","n_code_links":8,"syntology":null},{"paper":null,"slug":"generate-high-resolution-adversarial-samples","title":"HRFA: High-Resolution Feature-based Attack","date":"2020-01-21","arxiv_id":"2001.07631","n_code_links":0,"syntology":null},{"paper":null,"slug":"random-matrix-theory-proves-that-deep-1","title":"Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures","date":"2020-01-21","arxiv_id":"2001.08370","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-level-head-wise-match-and-aggregation","title":"Multi-level Head-wise Match and Aggregation in Transformer for Textual Sequence Matching","date":"2020-01-20","arxiv_id":"2001.07234","n_code_links":0,"syntology":null},{"paper":null,"slug":"real-time-object-detection-and-recognition-on","title":"Real-Time Object Detection and Recognition on Low-Compute Humanoid Robots using Deep Learning","date":"2020-01-20","arxiv_id":"2002.03735","n_code_links":0,"syntology":null},{"paper":"/paper/recommending-themes-for-ad-creative-design","slug":"recommending-themes-for-ad-creative-design","title":"Recommending Themes for Ad Creative Design via Visual-Linguistic Representations","date":"2020-01-20","arxiv_id":"2001.07194","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multimodal-deep-learning-approach-for-named","title":"A multimodal deep learning approach for named entity recognition from social media","date":"2020-01-19","arxiv_id":"2001.06888","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-for-hindi-text-classification-a","title":"Deep Learning for Hindi Text Classification: A Comparison","date":"2020-01-19","arxiv_id":"2001.10340","n_code_links":0,"syntology":null},{"paper":null,"slug":"capturing-evolution-in-word-usage-just-add","title":"Capturing Evolution in Word Usage: Just Add More Clusters?","date":"2020-01-18","arxiv_id":"2001.06629","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-neural-architecture-search-a-broad","title":"BNAS:An Efficient Neural Architecture Search Approach Using Broad Scalable Architecture","date":"2020-01-18","arxiv_id":"2001.06679","n_code_links":0,"syntology":null},{"paper":null,"slug":"enas-u-net-evolutionary-neural-architecture","title":"Evolutionary Neural Architecture Search for Retinal Vessel Segmentation","date":"2020-01-18","arxiv_id":"2001.06678","n_code_links":0,"syntology":null},{"paper":"/paper/compounding-the-performance-improvements-of","slug":"compounding-the-performance-improvements-of","title":"Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network","date":"2020-01-17","arxiv_id":"2001.06268","n_code_links":1,"syntology":{"ran":3,"of":11,"n_ran_checked":2,"n_instrument":1,"unverified":8,"pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 8 unverified","official":{"repos":["clovaai/assembled-cnn"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"graphbgs-background-subtraction-via-recovery","title":"GraphBGS: Background Subtraction via Recovery of Graph Signals","date":"2020-01-17","arxiv_id":"2001.06404","n_code_links":0,"syntology":null},{"paper":"/paper/latency-aware-differentiable-neural","slug":"latency-aware-differentiable-neural","title":"Latency-Aware Differentiable Neural Architecture Search","date":"2020-01-17","arxiv_id":"2001.06392","n_code_links":1,"syntology":null},{"paper":"/paper/robbert-a-dutch-roberta-based-language-model","slug":"robbert-a-dutch-roberta-based-language-model","title":"RobBERT: a Dutch RoBERTa-based Language Model","date":"2020-01-17","arxiv_id":"2001.06286","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["iPieter/RobBERT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"up-to-two-billion-times-acceleration-of","title":"Building high accuracy emulators for scientific simulations with deep neural architecture search","date":"2020-01-17","arxiv_id":"2001.08055","n_code_links":0,"syntology":null},{"paper":"/paper/mixpath-a-unified-approach-for-one-shot","slug":"mixpath-a-unified-approach-for-one-shot","title":"MixPath: A Unified Approach for One-shot Neural Architecture Search","date":"2020-01-16","arxiv_id":"2001.05887","n_code_links":1,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"0 ran · 4 unverified","official":{"repos":["xiaomi-automl/MixPath"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":null,"slug":"rsnet-an-improvement-for-darknet","title":"A lightweight target detection algorithm based on Mobilenet Convolution","date":"2020-01-16","arxiv_id":"2002.03729","n_code_links":0,"syntology":null},{"paper":"/paper/schema2qa-answering-complex-queries-on-the","slug":"schema2qa-answering-complex-queries-on-the","title":"Schema2QA: High-Quality and Low-Cost Q&A Agents for the Structured Web","date":"2020-01-16","arxiv_id":"2001.05609","n_code_links":3,"syntology":null},{"paper":null,"slug":"shifted-and-squeezed-8-bit-floating-point-1","title":"Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural Networks","date":"2020-01-16","arxiv_id":"2001.05674","n_code_links":0,"syntology":null},{"paper":"/paper/deep-residual-flow-for-novelty-detection","slug":"deep-residual-flow-for-novelty-detection","title":"Deep Residual Flow for Out of Distribution Detection","date":"2020-01-15","arxiv_id":"2001.05419","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["EvZissel/Residual-Flow"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/fgn-fusion-glyph-network-for-chinese-named","slug":"fgn-fusion-glyph-network-for-chinese-named","title":"FGN: Fusion Glyph Network for Chinese Named Entity Recognition","date":"2020-01-15","arxiv_id":"2001.05272","n_code_links":1,"syntology":null},{"paper":null,"slug":"insertion-deletion-transformer","title":"Insertion-Deletion Transformer","date":"2020-01-15","arxiv_id":"2001.05540","n_code_links":0,"syntology":null},{"paper":"/paper/parallel-machine-translation-with","slug":"parallel-machine-translation-with","title":"Non-Autoregressive Machine Translation with Disentangled Context Transformer","date":"2020-01-15","arxiv_id":"2001.05136","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-online-ctcattention-end-to","title":"Transformer-based Online CTC/attention End-to-End Speech Recognition Architecture","date":"2020-01-15","arxiv_id":"2001.08290","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-bert-based-sentiment-analysis-and-key","title":"A BERT based Sentiment Analysis and Key Entity Detection Approach for Online Financial Texts","date":"2020-01-14","arxiv_id":"2001.05326","n_code_links":0,"syntology":null},{"paper":null,"slug":"auto-completion-of-user-interface-layout-1","title":"Auto Completion of User Interface Layout Design Using Transformer-Based Tree Decoders","date":"2020-01-14","arxiv_id":"2001.05308","n_code_links":0,"syntology":null},{"paper":"/paper/neural-architecture-search-for-deep-image","slug":"neural-architecture-search-for-deep-image","title":"Neural Architecture Search for Deep Image Prior","date":"2020-01-14","arxiv_id":"2001.04776","n_code_links":2,"syntology":null},{"paper":"/paper/quantisation-and-pruning-for-neural-network","slug":"quantisation-and-pruning-for-neural-network","title":"Quantisation and Pruning for Neural Network Compression and Regularisation","date":"2020-01-14","arxiv_id":"2001.04850","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-problems-with-using-stns-to-align-cnn","title":"The problems with using STNs to align CNN feature maps","date":"2020-01-14","arxiv_id":"2001.05858","n_code_links":0,"syntology":null},{"paper":"/paper/adabert-task-adaptive-bert-compression-with","slug":"adabert-task-adaptive-bert-compression-with","title":"AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search","date":"2020-01-13","arxiv_id":"2001.04246","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":null}},{"paper":"/paper/reformer-the-efficient-transformer-1","slug":"reformer-the-efficient-transformer-1","title":"Reformer: The Efficient Transformer","date":"2020-01-13","arxiv_id":"2001.04451","n_code_links":10,"syntology":{"ran":6,"of":8,"n_ran_checked":1,"n_instrument":5,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","official":{"repos":["google/trax"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/representations-lexicales-pour-la-detection","slug":"representations-lexicales-pour-la-detection","title":"Représentations lexicales pour la détection non supervisée d'événements dans un flux de tweets : étude sur des corpus français et anglais","date":"2020-01-13","arxiv_id":"2001.04139","n_code_links":1,"syntology":null},{"paper":"/paper/the-two-pass-softmax-algorithm","slug":"the-two-pass-softmax-algorithm","title":"The Two-Pass Softmax Algorithm","date":"2020-01-13","arxiv_id":"2001.04438","n_code_links":4,"syntology":null},{"paper":null,"slug":"urdu-english-machine-transliteration-using","title":"Urdu-English Machine Transliteration using Neural Networks","date":"2020-01-12","arxiv_id":"2001.05296","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-and-improving-robustness-of-multi","slug":"exploring-and-improving-robustness-of-multi","title":"Exploring and Improving Robustness of Multi Task Deep Neural Networks via Domain Agnostic Defenses","date":"2020-01-11","arxiv_id":"2001.05286","n_code_links":1,"syntology":null},{"paper":null,"slug":"patenttransformer-2-controlling-patent-text","title":"PatentTransformer-2: Controlling Patent Text Generation by Structural Metadata","date":"2020-01-11","arxiv_id":"2001.03708","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-giraffes-become-birds-an-evaluation-of","title":"Can Giraffes Become Birds? An Evaluation of Image-to-image Translation for Data Generation","date":"2020-01-10","arxiv_id":"2001.03637","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-control-of-embedding-strength-in","title":"Adaptive Control of Embedding Strength in Image Watermarking using Neural Networks","date":"2020-01-09","arxiv_id":"2001.03251","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-oriented-neural-architecture","title":"Performance-Oriented Neural Architecture Search","date":"2020-01-09","arxiv_id":"2001.02976","n_code_links":0,"syntology":null},{"paper":"/paper/resolving-the-scope-of-speculation-and","slug":"resolving-the-scope-of-speculation-and","title":"Resolving the Scope of Speculation and Negation using Transformer-Based Architectures","date":"2020-01-09","arxiv_id":"2001.02885","n_code_links":1,"syntology":null},{"paper":"/paper/spatial-temporal-transformer-networks-for","slug":"spatial-temporal-transformer-networks-for","title":"Spatial-Temporal Transformer Networks for Traffic Flow Forecasting","date":"2020-01-09","arxiv_id":"2001.02908","n_code_links":1,"syntology":null},{"paper":"/paper/fast-neural-network-adaptation-via-parameter","slug":"fast-neural-network-adaptation-via-parameter","title":"Fast Neural Network Adaptation via Parameter Remapping and Architecture Search","date":"2020-01-08","arxiv_id":"2001.02525","n_code_links":0,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":null}},{"paper":null,"slug":"high-level-plan-for-behavioral-robot","title":"High-Level Plan for Behavioral Robot Navigation with Natural Language Directions and R-NET","date":"2020-01-08","arxiv_id":"2001.02330","n_code_links":0,"syntology":null},{"paper":"/paper/sgd-with-hardness-weighted-sampling-for-1","slug":"sgd-with-hardness-weighted-sampling-for-1","title":"Distributionally Robust Deep Learning using Hardness Weighted Sampling","date":"2020-01-08","arxiv_id":"2001.02658","n_code_links":1,"syntology":null},{"paper":null,"slug":"streaming-automatic-speech-recognition-with","title":"Streaming automatic speech recognition with the transformer model","date":"2020-01-08","arxiv_id":"2001.02674","n_code_links":0,"syntology":null},{"paper":null,"slug":"to-transfer-or-not-to-transfer","title":"To Transfer or Not to Transfer: Misclassification Attacks Against Transfer Learned Text Classifiers","date":"2020-01-08","arxiv_id":"2001.02438","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-aware-attention-network-for-protein","slug":"knowledge-aware-attention-network-for-protein","title":"Knowledge-aware Attention Network for Protein-Protein Interaction Extraction","date":"2020-01-07","arxiv_id":"2001.02091","n_code_links":1,"syntology":null},{"paper":null,"slug":"recast-interactive-auditing-of-automatic","title":"RECAST: Interactive Auditing of Automatic Toxicity Detection Models","date":"2020-01-07","arxiv_id":"2001.01819","n_code_links":0,"syntology":null}],"record_sha256":"2d856992ccfbda8623c97fac466cbadcdede09214d9d7dd0654b886fc3295fe4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}