{"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/dropout/papers/252","list_of":"/method/dropout","method":"Dropout","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":252,"pages_in_order":275,"rows_per_page":100,"rows":[25101,25200],"of":27472,"counts":{"archive_papers_tagged":27472,"with_a_code_link":12129,"where_syntology_ran_a_sample":3620,"not_listed_spam_title":0,"listed":27472,"listed_where_code_ran":3620,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3044,"every_run_a_failure_of_syntologys_instrument":576,"listed_with_a_run_with_no_instrument_failure":3044,"listed_every_run_a_failure_of_syntologys_instrument":576,"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/dropout","prev":"/method/dropout/papers/251","next":"/method/dropout/papers/253","papers":[{"paper":"/paper/encoding-word-order-in-complex-embeddings-1","slug":"encoding-word-order-in-complex-embeddings-1","title":"Encoding word order in complex embeddings","date":"2019-12-27","arxiv_id":"1912.12333","n_code_links":1,"syntology":null},{"paper":null,"slug":"graduate-employment-prediction-with-bias","title":"Graduate Employment Prediction with Bias","date":"2019-12-27","arxiv_id":"1912.12012","n_code_links":0,"syntology":null},{"paper":null,"slug":"handling-missing-mri-input-data-in-deep","title":"Handling Missing MRI Input Data in Deep Learning Segmentation of Brain Metastases: A Multi-Center Study","date":"2019-12-27","arxiv_id":"1912.11966","n_code_links":0,"syntology":null},{"paper":"/paper/is-attention-all-what-you-need-an-empirical","slug":"is-attention-all-what-you-need-an-empirical","title":"Is Attention All What You Need? -- An Empirical Investigation on Convolution-Based Active Memory and Self-Attention","date":"2019-12-27","arxiv_id":"1912.11959","n_code_links":1,"syntology":null},{"paper":"/paper/explicit-sparse-transformer-concentrated","slug":"explicit-sparse-transformer-concentrated","title":"Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection","date":"2019-12-25","arxiv_id":"1912.11637","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lancopku/Explicit-Sparse-Transformer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"make-lead-bias-in-your-favor-a-simple-and-2","title":"Leveraging Lead Bias for Zero-shot Abstractive News Summarization","date":"2019-12-25","arxiv_id":"1912.11602","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-abstractive-text-summarization-with","title":"Improving Abstractive Text Summarization with History Aggregation","date":"2019-12-24","arxiv_id":"1912.11046","n_code_links":0,"syntology":null},{"paper":"/paper/multi-graph-transformer-for-free-hand-sketch","slug":"multi-graph-transformer-for-free-hand-sketch","title":"Multi-Graph Transformer for Free-Hand Sketch Recognition","date":"2019-12-24","arxiv_id":"1912.11258","n_code_links":1,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"0 ran · 4 unverified","official":{"repos":["PengBoXiangShang/multigraph_transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":null,"slug":"a-robust-and-precise-convnet-for-small-non","title":"A Robust and Precise ConvNet for small non-coding RNA classification (RPC-snRC)","date":"2019-12-23","arxiv_id":"1912.11356","n_code_links":0,"syntology":null},{"paper":null,"slug":"learn-able-parameter-guided-activation","title":"Learn-able parameter guided Activation Functions","date":"2019-12-23","arxiv_id":"1912.10752","n_code_links":0,"syntology":null},{"paper":"/paper/probing-the-phonetic-and-phonological","slug":"probing-the-phonetic-and-phonological","title":"Probing the phonetic and phonological knowledge of tones in Mandarin TTS models","date":"2019-12-23","arxiv_id":"1912.10915","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-training-of-a-large-vocabulary-end","title":"end-to-end training of a large vocabulary end-to-end speech recognition system","date":"2019-12-22","arxiv_id":"1912.11040","n_code_links":0,"syntology":null},{"paper":"/paper/harnessing-evolution-of-multi-turn","slug":"harnessing-evolution-of-multi-turn","title":"Harnessing Evolution of Multi-Turn Conversations for Effective Answer Retrieval","date":"2019-12-22","arxiv_id":"1912.10554","n_code_links":1,"syntology":null},{"paper":"/paper/pre-trained-contextual-embedding-of-source-1","slug":"pre-trained-contextual-embedding-of-source-1","title":"Learning and Evaluating Contextual Embedding of Source Code","date":"2019-12-21","arxiv_id":"2001.00059","n_code_links":2,"syntology":null},{"paper":null,"slug":"are-transformers-universal-approximators-of-1","title":"Are Transformers universal approximators of sequence-to-sequence functions?","date":"2019-12-20","arxiv_id":"1912.10077","n_code_links":0,"syntology":null},{"paper":"/paper/axial-attention-in-multidimensional-1","slug":"axial-attention-in-multidimensional-1","title":"Axial Attention in Multidimensional Transformers","date":"2019-12-20","arxiv_id":"1912.12180","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"et-usb-transformer-based-sequential-behavior","title":"ET-USB: Transformer-Based Sequential Behavior Modeling for Inbound Customer Service","date":"2019-12-20","arxiv_id":"1912.10852","n_code_links":0,"syntology":null},{"paper":null,"slug":"landscape-connectivity-and-dropout-stability","title":"Landscape Connectivity and Dropout Stability of SGD Solutions for Over-parameterized Neural Networks","date":"2019-12-20","arxiv_id":"1912.10095","n_code_links":0,"syntology":null},{"paper":null,"slug":"pretrained-encyclopedia-weakly-supervised-1","title":"Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model","date":"2019-12-20","arxiv_id":"1912.09637","n_code_links":0,"syntology":null},{"paper":null,"slug":"shareable-representations-for-search-query","title":"Shareable Representations for Search Query Understanding","date":"2019-12-20","arxiv_id":"2001.04345","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-application-of-generative-adversarial","title":"An Application of Generative Adversarial Networks for Super Resolution Medical Imaging","date":"2019-12-19","arxiv_id":"1912.09507","n_code_links":0,"syntology":null},{"paper":null,"slug":"anisotropic-super-resolution-in-prostate-mri","title":"Anisotropic Super Resolution in Prostate MRI using Super Resolution Generative Adversarial Networks","date":"2019-12-19","arxiv_id":"1912.09497","n_code_links":0,"syntology":null},{"paper":"/paper/bertje-a-dutch-bert-model","slug":"bertje-a-dutch-bert-model","title":"BERTje: A Dutch BERT Model","date":"2019-12-19","arxiv_id":"1912.09582","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["wietsedv/bertje"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/cjrc-a-reliable-human-annotated-benchmark","slug":"cjrc-a-reliable-human-annotated-benchmark","title":"CJRC: A Reliable Human-Annotated Benchmark DataSet for Chinese Judicial Reading Comprehension","date":"2019-12-19","arxiv_id":"1912.09156","n_code_links":0,"syntology":null},{"paper":"/paper/mean-field-theory-for-deep-dropout-networks","slug":"mean-field-theory-for-deep-dropout-networks","title":"Mean field theory for deep dropout networks: digging up gradient backpropagation deeply","date":"2019-12-19","arxiv_id":"1912.09132","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/neural-simile-recognition-with-cyclic","slug":"neural-simile-recognition-with-cyclic","title":"Neural Simile Recognition with Cyclic Multitask Learning and Local Attention","date":"2019-12-19","arxiv_id":"1912.09084","n_code_links":1,"syntology":null},{"paper":"/paper/temporal-fusion-transformers-for","slug":"temporal-fusion-transformers-for","title":"Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting","date":"2019-12-19","arxiv_id":"1912.09363","n_code_links":36,"syntology":{"ran":8,"of":10,"n_ran_checked":4,"n_instrument":4,"unverified":2,"pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"attention-based-face-antispoofing-of-rgb","title":"Attention-Based Face AntiSpoofing of RGB Images, using a Minimal End-2-End Neural Network","date":"2019-12-18","arxiv_id":"1912.08870","n_code_links":0,"syntology":null},{"paper":null,"slug":"mri-pulse-sequence-integration-for-deep","title":"MRI Pulse Sequence Integration for Deep-Learning Based Brain Metastasis Segmentation","date":"2019-12-18","arxiv_id":"1912.08775","n_code_links":0,"syntology":null},{"paper":"/paper/a-multi-task-learning-model-for-chinese","slug":"a-multi-task-learning-model-for-chinese","title":"A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term Extraction","date":"2019-12-17","arxiv_id":"1912.07976","n_code_links":6,"syntology":null},{"paper":null,"slug":"cross-lingual-ability-of-multilingual-bert-an-1","title":"Cross-Lingual Ability of Multilingual BERT: An Empirical Study","date":"2019-12-17","arxiv_id":"1912.07840","n_code_links":0,"syntology":null},{"paper":"/paper/m2-meshed-memory-transformer-for-image","slug":"m2-meshed-memory-transformer-for-image","title":"Meshed-Memory Transformer for Image Captioning","date":"2019-12-17","arxiv_id":"1912.08226","n_code_links":2,"syntology":{"ran":8,"of":8,"n_ran_checked":6,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"8 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["aimagelab/meshed-memory-transformer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-performance-evaluation-of-multi","title":"The performance evaluation of Multi-representation in the Deep Learning models for Relation Extraction Task","date":"2019-12-17","arxiv_id":"1912.08290","n_code_links":0,"syntology":null},{"paper":null,"slug":"cag-a-real-time-low-cost-enhanced-robustness","title":"CAG: A Real-time Low-cost Enhanced-robustness High-transferability Content-aware Adversarial Attack Generator","date":"2019-12-16","arxiv_id":"1912.07742","n_code_links":0,"syntology":null},{"paper":"/paper/domain-knowledge-based-brain-tumor","slug":"domain-knowledge-based-brain-tumor","title":"Domain Knowledge Based Brain Tumor Segmentation and Overall Survival Prediction","date":"2019-12-16","arxiv_id":"1912.07224","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-malware-representation-based-on","title":"Learning Malware Representation based on Execution Sequences","date":"2019-12-16","arxiv_id":"1912.07250","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-densenet-towards-efficient-and-accurate","title":"Compressed DenseNet for Lightweight Character Recognition","date":"2019-12-15","arxiv_id":"1912.07016","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-is-not-enough-bert-for-finnish","slug":"multilingual-is-not-enough-bert-for-finnish","title":"Multilingual is not enough: BERT for Finnish","date":"2019-12-15","arxiv_id":"1912.07076","n_code_links":1,"syntology":null},{"paper":"/paper/robust-named-entity-recognition-with","slug":"robust-named-entity-recognition-with","title":"Robust Named Entity Recognition with Truecasing Pretraining","date":"2019-12-15","arxiv_id":"1912.07095","n_code_links":0,"syntology":null},{"paper":null,"slug":"bertqa-attention-on-steroids","title":"BERTQA -- Attention on Steroids","date":"2019-12-14","arxiv_id":"1912.10435","n_code_links":0,"syntology":null},{"paper":"/paper/towards-robust-toxic-content-classification","slug":"towards-robust-toxic-content-classification","title":"Towards Robust Toxic Content Classification","date":"2019-12-14","arxiv_id":"1912.06872","n_code_links":1,"syntology":null},{"paper":"/paper/voice-transformer-network-sequence-to","slug":"voice-transformer-network-sequence-to","title":"Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining","date":"2019-12-14","arxiv_id":"1912.06813","n_code_links":2,"syntology":null},{"paper":"/paper/pain-evaluation-in-video-using-extended","slug":"pain-evaluation-in-video-using-extended","title":"Pain Evaluation in Video using Extended Multitask Learning from Multidimensional Measurements","date":"2019-12-13","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/topoact-exploring-the-shape-of-activations-in","slug":"topoact-exploring-the-shape-of-activations-in","title":"TopoAct: Visually Exploring the Shape of Activations in Deep Learning","date":"2019-12-13","arxiv_id":"1912.06332","n_code_links":1,"syntology":null},{"paper":null,"slug":"waldorf-wasteless-language-model-distillation","title":"WaLDORf: Wasteless Language-model Distillation On Reading-comprehension","date":"2019-12-13","arxiv_id":"1912.06638","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-has-a-moral-compass-improvements-of","title":"BERT has a Moral Compass: Improvements of ethical and moral values of machines","date":"2019-12-11","arxiv_id":"1912.05238","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-grained-classification-of-rowing-teams","title":"Fine-grained Classification of Rowing teams","date":"2019-12-11","arxiv_id":"1912.05393","n_code_links":0,"syntology":null},{"paper":"/paper/linear-mode-connectivity-and-the-lottery","slug":"linear-mode-connectivity-and-the-lottery","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","date":"2019-12-11","arxiv_id":"1912.05671","n_code_links":2,"syntology":null},{"paper":"/paper/robust-gabor-networks","slug":"robust-gabor-networks","title":"Gabor Layers Enhance Network Robustness","date":"2019-12-11","arxiv_id":"1912.05661","n_code_links":1,"syntology":null},{"paper":null,"slug":"encoding-musical-style-with-transformer-1","title":"Encoding Musical Style with Transformer Autoencoders","date":"2019-12-10","arxiv_id":"1912.05537","n_code_links":0,"syntology":null},{"paper":"/paper/removable-andor-repeated-units-emerge-in","slug":"removable-andor-repeated-units-emerge-in","title":"Frivolous Units: Wider Networks Are Not Really That Wide","date":"2019-12-10","arxiv_id":"1912.04783","n_code_links":1,"syntology":null},{"paper":null,"slug":"unsupervised-transfer-learning-via-bert","title":"Unsupervised Transfer Learning via BERT Neuron Selection","date":"2019-12-10","arxiv_id":"1912.05308","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-study-on-position-of-the-batch","title":"An Empirical Study on Position of the Batch Normalization Layer in Convolutional Neural Networks","date":"2019-12-09","arxiv_id":"1912.04259","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-a-layout-transfer-network-for","title":"Learning a Layout Transfer Network for Context Aware Object Detection","date":"2019-12-09","arxiv_id":"1912.03865","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-reinforcement-learning-for","title":"Transformer Based Reinforcement Learning For Games","date":"2019-12-09","arxiv_id":"1912.03918","n_code_links":0,"syntology":null},{"paper":"/paper/bidirectional-scene-text-recognition-with-a","slug":"bidirectional-scene-text-recognition-with-a","title":"Bidirectional Scene Text Recognition with a Single Decoder","date":"2019-12-08","arxiv_id":"1912.03656","n_code_links":1,"syntology":null},{"paper":"/paper/individual-predictions-matter-assessing-the","slug":"individual-predictions-matter-assessing-the","title":"Individual predictions matter: Assessing the effect of data ordering in training fine-tuned CNNs for medical imaging","date":"2019-12-08","arxiv_id":"1912.03606","n_code_links":1,"syntology":null},{"paper":"/paper/salite-a-light-weight-model-for-salient","slug":"salite-a-light-weight-model-for-salient","title":"SaLite : A light-weight model for salient object detection","date":"2019-12-08","arxiv_id":"1912.03641","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-analysis-of-natural-language","title":"Adversarial Analysis of Natural Language Inference Systems","date":"2019-12-07","arxiv_id":"1912.03441","n_code_links":0,"syntology":null},{"paper":null,"slug":"personalized-patent-claim-generation-and","title":"Personalized Patent Claim Generation and Measurement","date":"2019-12-07","arxiv_id":"1912.03502","n_code_links":0,"syntology":null},{"paper":null,"slug":"explaining-sequence-level-knowledge","title":"Explaining Sequence-Level Knowledge Distillation as Data-Augmentation for Neural Machine Translation","date":"2019-12-06","arxiv_id":"1912.03334","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-mask-for-transformer-based-end-to","slug":"semantic-mask-for-transformer-based-end-to","title":"Semantic Mask for Transformer based End-to-End Speech Recognition","date":"2019-12-06","arxiv_id":"1912.03010","n_code_links":1,"syntology":null},{"paper":null,"slug":"synchronous-transformers-for-end-to-end","title":"Synchronous Transformers for End-to-End Speech Recognition","date":"2019-12-06","arxiv_id":"1912.02958","n_code_links":0,"syntology":null},{"paper":null,"slug":"weak-supervision-helps-emergence-of-word","title":"Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks","date":"2019-12-06","arxiv_id":"1912.03063","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-adam-beats-sgd-for-attention-models-1","title":"Why are Adaptive Methods Good for Attention Models?","date":"2019-12-06","arxiv_id":"1912.03194","n_code_links":0,"syntology":null},{"paper":null,"slug":"phonebit-efficient-gpu-accelerated-binary","title":"PhoneBit: Efficient GPU-Accelerated Binary Neural Network Inference Engine for Mobile Phones","date":"2019-12-05","arxiv_id":"1912.04050","n_code_links":0,"syntology":null},{"paper":"/paper/scratch-that-an-evolution-based-adversarial","slug":"scratch-that-an-evolution-based-adversarial","title":"Scratch that! An Evolution-based Adversarial Attack against Neural Networks","date":"2019-12-05","arxiv_id":"1912.02316","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-supervised-contextual-language","title":"Self-Supervised Contextual Language Representation of Radiology Reports to Improve the Identification of Communication Urgency","date":"2019-12-05","arxiv_id":"1912.02703","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-robust-neural-vocoding-for-speech","title":"Towards Robust Neural Vocoding for Speech Generation: A Survey","date":"2019-12-05","arxiv_id":"1912.02461","n_code_links":0,"syntology":null},{"paper":null,"slug":"acquiring-knowledge-from-pre-trained-model-to","title":"Acquiring Knowledge from Pre-trained Model to Neural Machine Translation","date":"2019-12-04","arxiv_id":"1912.01774","n_code_links":0,"syntology":null},{"paper":null,"slug":"amused-a-multi-stream-vector-representation-1","title":"AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue","date":"2019-12-04","arxiv_id":"1912.10160","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exploration-of-data-augmentation-and-1","title":"An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering","date":"2019-12-04","arxiv_id":"1912.02145","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-relation-extraction-using-syntactic","slug":"enhancing-relation-extraction-using-syntactic","title":"Enhancing Relation Extraction Using Syntactic Indicators and Sentential Contexts","date":"2019-12-04","arxiv_id":"1912.01858","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-pretrained-language","title":"A Comparative Study of Pretrained Language Models on Thai Social Text Categorization","date":"2019-12-03","arxiv_id":"1912.01580","n_code_links":0,"syntology":null},{"paper":"/paper/tu-wien-trec-deep-learning-19-simple","slug":"tu-wien-trec-deep-learning-19-simple","title":"TU Wien @ TREC Deep Learning '19 -- Simple Contextualization for Re-ranking","date":"2019-12-03","arxiv_id":"1912.01385","n_code_links":1,"syntology":null},{"paper":null,"slug":"audiovisual-transformer-architectures-for","title":"Audiovisual Transformer Architectures for Large-Scale Classification and Synchronization of Weakly Labeled Audio Events","date":"2019-12-02","arxiv_id":"1912.02615","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-for-large-scale-video-segment","title":"BERT for Large-scale Video Segment Classification with Test-time Augmentation","date":"2019-12-02","arxiv_id":"1912.01127","n_code_links":0,"syntology":null},{"paper":"/paper/blimp-a-benchmark-of-linguistic-minimal-pairs","slug":"blimp-a-benchmark-of-linguistic-minimal-pairs","title":"BLiMP: The Benchmark of Linguistic Minimal Pairs for English","date":"2019-12-02","arxiv_id":"1912.00582","n_code_links":4,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alexwarstadt/blimp","alexwarstadt/data_generation"],"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/ft-clipact-resilience-analysis-of-deep-neural","slug":"ft-clipact-resilience-analysis-of-deep-neural","title":"FT-ClipAct: Resilience Analysis of Deep Neural Networks and Improving their Fault Tolerance using Clipped Activation","date":"2019-12-02","arxiv_id":"1912.00941","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-contextual-embeddings-for","title":"Leveraging Contextual Embeddings for Detecting Diachronic Semantic Shift","date":"2019-12-02","arxiv_id":"1912.01072","n_code_links":0,"syntology":null},{"paper":"/paper/long-distance-relationships-without-time","slug":"long-distance-relationships-without-time","title":"Long Distance Relationships without Time Travel: Boosting the Performance of a Sparse Predictive Autoencoder in Sequence Modeling","date":"2019-12-02","arxiv_id":"1912.01116","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-scale-self-attention-for-text","title":"Multi-Scale Self-Attention for Text Classification","date":"2019-12-02","arxiv_id":"1912.00544","n_code_links":0,"syntology":null},{"paper":"/paper/neural-academic-paper-generation","slug":"neural-academic-paper-generation","title":"Neural Academic Paper Generation","date":"2019-12-02","arxiv_id":"1912.01982","n_code_links":1,"syntology":null},{"paper":"/paper/solving-arithmetic-word-problems","slug":"solving-arithmetic-word-problems","title":"Solving Arithmetic Word Problems Automatically Using Transformer and Unambiguous Representations","date":"2019-12-02","arxiv_id":"1912.00871","n_code_links":1,"syntology":null},{"paper":"/paper/autoprune-automatic-network-pruning-by","slug":"autoprune-automatic-network-pruning-by","title":"AutoPrune: Automatic Network Pruning by Regularizing Auxiliary Parameters","date":"2019-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/fast-and-accurate-stochastic-gradient","slug":"fast-and-accurate-stochastic-gradient","title":"Fast and Accurate Stochastic Gradient Estimation","date":"2019-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"hybrid-8-bit-floating-point-hfp8-training-and","title":"Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks","date":"2019-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"image-segmentation-of-liver-stage-malaria","title":"Image segmentation of liver stage malaria infection with spatial uncertainty sampling","date":"2019-11-30","arxiv_id":"1912.00262","n_code_links":0,"syntology":null},{"paper":"/paper/learning-rate-dropout","slug":"learning-rate-dropout","title":"Learning Rate Dropout","date":"2019-11-30","arxiv_id":"1912.00144","n_code_links":1,"syntology":null},{"paper":null,"slug":"pruning-at-a-glance-global-neural-pruning-for","title":"Pruning at a Glance: Global Neural Pruning for Model Compression","date":"2019-11-30","arxiv_id":"1912.00200","n_code_links":0,"syntology":null},{"paper":null,"slug":"semi-relaxed-quantization-with-dropbits","title":"Semi-Relaxed Quantization with DropBits: Training Low-Bit Neural Networks via Bit-wise Regularization","date":"2019-11-29","arxiv_id":"1911.12990","n_code_links":0,"syntology":null},{"paper":"/paper/whats-hidden-in-a-randomly-weighted-neural","slug":"whats-hidden-in-a-randomly-weighted-neural","title":"What's Hidden in a Randomly Weighted Neural Network?","date":"2019-11-29","arxiv_id":"1911.13299","n_code_links":4,"syntology":{"ran":9,"of":9,"n_ran_checked":8,"n_instrument":1,"unverified":0,"pointer_only":5,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/hidden-networks"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/continuous-dropout","slug":"continuous-dropout","title":"Continuous Dropout","date":"2019-11-28","arxiv_id":"1911.12675","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-driven-compression-of-convolutional","title":"Data-Driven Compression of Convolutional Neural Networks","date":"2019-11-28","arxiv_id":"1911.12740","n_code_links":0,"syntology":null},{"paper":null,"slug":"inducing-relational-knowledge-from-bert","title":"Inducing Relational Knowledge from BERT","date":"2019-11-28","arxiv_id":"1911.12753","n_code_links":0,"syntology":null},{"paper":null,"slug":"minimum-bayes-risk-training-of-rnn-transducer","title":"Minimum Bayes Risk Training of RNN-Transducer for End-to-End Speech Recognition","date":"2019-11-28","arxiv_id":"1911.12487","n_code_links":0,"syntology":null},{"paper":"/paper/brain-age-prediction-using-deep-learning","slug":"brain-age-prediction-using-deep-learning","title":"Brain age prediction using deep learning uncovers associated sequence variants","date":"2019-11-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/crypto-oriented-neural-architecture-design","slug":"crypto-oriented-neural-architecture-design","title":"Crypto-Oriented Neural Architecture Design","date":"2019-11-27","arxiv_id":"1911.12322","n_code_links":1,"syntology":null},{"paper":"/paper/cspnet-a-new-backbone-that-can-enhance","slug":"cspnet-a-new-backbone-that-can-enhance","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","date":"2019-11-27","arxiv_id":"1911.11929","n_code_links":123,"syntology":null},{"paper":"/paper/define-deep-factorized-input-word-embeddings-1","slug":"define-deep-factorized-input-word-embeddings-1","title":"DeFINE: DEep Factorized INput Token Embeddings for Neural Sequence Modeling","date":"2019-11-27","arxiv_id":"1911.12385","n_code_links":1,"syntology":null}],"record_sha256":"e88e78a580b95abe286090014f87076e3effab9b00a92274d586936e59e16f85","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}