{"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/weight-decay/papers/100","list_of":"/method/weight-decay","method":"Weight Decay","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":100,"pages_in_order":108,"rows_per_page":100,"rows":[9901,10000],"of":10713,"counts":{"archive_papers_tagged":10713,"with_a_code_link":4533,"where_syntology_ran_a_sample":1291,"not_listed_spam_title":0,"listed":10713,"listed_where_code_ran":1291,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1064,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1064,"listed_every_run_a_failure_of_syntologys_instrument":227,"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/weight-decay","prev":"/method/weight-decay/papers/99","next":"/method/weight-decay/papers/101","papers":[{"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":"/paper/harmonic-convolutional-networks-based-on","slug":"harmonic-convolutional-networks-based-on","title":"Harmonic Convolutional Networks based on Discrete Cosine Transform","date":"2020-01-18","arxiv_id":"2001.06570","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":10,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["matej-ulicny/harmonic-networks"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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":"/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":"/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":"/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":"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":"/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/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/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":"/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":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/improving-entity-linking-by-modeling-latent-2","slug":"improving-entity-linking-by-modeling-latent-2","title":"Improving Entity Linking by Modeling Latent Entity Type Information","date":"2020-01-06","arxiv_id":"2001.01447","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-layer-content-interaction-through","title":"Multi-Layer Content Interaction Through Quaternion Product For Visual Question Answering","date":"2020-01-03","arxiv_id":"2001.05840","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-al-bert-for-arbitrarily-long-document","title":"BERT-AL: BERT for Arbitrarily Long Document Understanding","date":"2020-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/stacked-debert-all-attention-in-incomplete","slug":"stacked-debert-all-attention-in-incomplete","title":"Stacked DeBERT: All Attention in Incomplete Data for Text Classification","date":"2020-01-01","arxiv_id":"2001.00137","n_code_links":1,"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: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gcunhase/StackedDeBERT"],"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","unlocated"]}}},{"paper":"/paper/olmpics-on-what-language-model-pre-training","slug":"olmpics-on-what-language-model-pre-training","title":"oLMpics -- On what Language Model Pre-training Captures","date":"2019-12-31","arxiv_id":"1912.13283","n_code_links":2,"syntology":null},{"paper":"/paper/oteann-estimating-the-transparency-of","slug":"oteann-estimating-the-transparency-of","title":"OTEANN: Estimating the Transparency of Orthographies with an Artificial Neural Network","date":"2019-12-31","arxiv_id":"1912.13321","n_code_links":2,"syntology":null},{"paper":"/paper/autodiscern-rating-the-quality-of-online","slug":"autodiscern-rating-the-quality-of-online","title":"AutoDiscern: Rating the Quality of Online Health Information with Hierarchical Encoder Attention-based Neural Networks","date":"2019-12-30","arxiv_id":"1912.12999","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":"/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":"/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":"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":"/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/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/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/pointrend-image-segmentation-as-rendering","slug":"pointrend-image-segmentation-as-rendering","title":"PointRend: Image Segmentation as Rendering","date":"2019-12-17","arxiv_id":"1912.08193","n_code_links":14,"syntology":{"ran":16,"of":18,"n_ran_checked":13,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["facebookresearch/detectron2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"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":"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":"/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/liteseg-a-novel-lightweight-convnet-for","slug":"liteseg-a-novel-lightweight-convnet-for","title":"LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation","date":"2019-12-13","arxiv_id":"1912.06683","n_code_links":2,"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":"/paper/spinenet-learning-scale-permuted-backbone-for","slug":"spinenet-learning-scale-permuted-backbone-for","title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","date":"2019-12-10","arxiv_id":"1912.05027","n_code_links":13,"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":"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":"/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":"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":"/paper/bridging-the-gap-between-anchor-based-and","slug":"bridging-the-gap-between-anchor-based-and","title":"Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection","date":"2019-12-05","arxiv_id":"1912.02424","n_code_links":13,"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":["sfzhang15/ATSS"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"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":"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":"/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":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":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/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":"/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":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":"/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/do-attention-heads-in-bert-track-syntactic","slug":"do-attention-heads-in-bert-track-syntactic","title":"Do Attention Heads in BERT Track Syntactic Dependencies?","date":"2019-11-27","arxiv_id":"1911.12246","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-commonsense-in-pre-trained","slug":"evaluating-commonsense-in-pre-trained","title":"Evaluating Commonsense in Pre-trained Language Models","date":"2019-11-27","arxiv_id":"1911.11931","n_code_links":1,"syntology":null},{"paper":"/paper/ghostnet-more-features-from-cheap-operations","slug":"ghostnet-more-features-from-cheap-operations","title":"GhostNet: More Features from Cheap Operations","date":"2019-11-27","arxiv_id":"1911.11907","n_code_links":33,"syntology":{"ran":19,"of":23,"n_ran_checked":16,"n_instrument":3,"unverified":4,"pointer_only":5,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["huawei-noah/ghostnet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"taking-a-stance-on-fake-news-towards","title":"Taking a Stance on Fake News: Towards Automatic Disinformation Assessment via Deep Bidirectional Transformer Language Models for Stance Detection","date":"2019-11-27","arxiv_id":"1911.11951","n_code_links":0,"syntology":null},{"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":"/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":"/paper/adversarial-examples-improve-image","slug":"adversarial-examples-improve-image","title":"Adversarial Examples Improve Image Recognition","date":"2019-11-21","arxiv_id":"1911.09665","n_code_links":6,"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":{"repos":["tensorflow/tpu"],"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/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":"/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/efficientdet-scalable-and-efficient-object","slug":"efficientdet-scalable-and-efficient-object","title":"EfficientDet: Scalable and Efficient Object Detection","date":"2019-11-20","arxiv_id":"1911.09070","n_code_links":64,"syntology":{"ran":55,"of":70,"n_ran_checked":48,"n_instrument":7,"unverified":15,"pointer_only":7,"phrase":"55 ran (of which 1 constructed an object rather than computing a result; 48 with no instrument failure: 4 honoured, 0 violated, 44 with no contract checked; 7 where Syntology's instrument failed) · 15 unverified","official":{"repos":["google/automl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"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":"/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":"/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":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":"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":"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":null,"slug":"improved-exploration-through-latent","title":"Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient","date":"2019-11-15","arxiv_id":"1911.06833","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-the-disharmony-between-weight","slug":"understanding-the-disharmony-between-weight","title":"Understanding the Disharmony between Weight Normalization Family and Weight Decay: $ε-$shifted $L_2$ Regularizer","date":"2019-11-14","arxiv_id":"1911.05920","n_code_links":1,"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/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":"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":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":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"]}}},{"paper":"/paper/effectiveness-of-self-supervised-pre-training","slug":"effectiveness-of-self-supervised-pre-training","title":"Effectiveness of self-supervised pre-training for speech recognition","date":"2019-11-10","arxiv_id":"1911.03912","n_code_links":2,"syntology":null},{"paper":null,"slug":"improving-bert-fine-tuning-with-embedding","title":"Improving BERT Fine-tuning with Embedding Normalization","date":"2019-11-10","arxiv_id":"1911.03918","n_code_links":0,"syntology":null},{"paper":"/paper/inset-sentence-infilling-with-inter","slug":"inset-sentence-infilling-with-inter","title":"INSET: Sentence Infilling with INter-SEntential Transformer","date":"2019-11-10","arxiv_id":"1911.03892","n_code_links":1,"syntology":null},{"paper":"/paper/rat-sql-relation-aware-schema-encoding-and-1","slug":"rat-sql-relation-aware-schema-encoding-and-1","title":"RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers","date":"2019-11-10","arxiv_id":"1911.04942","n_code_links":4,"syntology":{"ran":5,"of":7,"n_ran_checked":3,"n_instrument":2,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["Microsoft/rat-sql"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"robust-natural-language-inference-models-with","title":"Increasing Robustness to Spurious Correlations using Forgettable Examples","date":"2019-11-10","arxiv_id":"1911.03861","n_code_links":0,"syntology":null},{"paper":null,"slug":"syntax-infused-transformer-and-bert-models","title":"Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding","date":"2019-11-10","arxiv_id":"1911.06156","n_code_links":0,"syntology":null},{"paper":null,"slug":"yelm-end-to-end-contextualized-entity-linking","title":"Contextualized End-to-End Neural Entity Linking","date":"2019-11-10","arxiv_id":"1911.03834","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-entity-linking-with-dense-entity","slug":"zero-shot-entity-linking-with-dense-entity","title":"Scalable Zero-shot Entity Linking with Dense Entity Retrieval","date":"2019-11-10","arxiv_id":"1911.03814","n_code_links":3,"syntology":null},{"paper":null,"slug":"attentive-student-meets-multi-task-teacher","title":"MKD: a Multi-Task Knowledge Distillation Approach for Pretrained Language Models","date":"2019-11-09","arxiv_id":"1911.03588","n_code_links":0,"syntology":null}],"record_sha256":"5506e86b0148a18243fd8757df0e1981e5348fe62f873240cbe1de4d68bdb1bf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}