{"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/78","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":78,"pages_in_order":108,"rows_per_page":100,"rows":[7701,7800],"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/77","next":"/method/weight-decay/papers/79","papers":[{"paper":null,"slug":"improving-early-sepsis-prediction-with-multi","title":"Improving Early Sepsis Prediction with Multi Modal Learning","date":"2021-07-23","arxiv_id":"2107.11094","n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-ternary-quantization","title":"Pruning Ternary Quantization","date":"2021-07-23","arxiv_id":"2107.10998","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-extractive-summarization","slug":"evaluating-extractive-summarization","title":"Evaluating Extractive Summarization Techniques on News Articles","date":"2021-07-22","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-extractive-summarization-1","slug":"evaluating-extractive-summarization-1","title":"Evaluating Extractive Summarization Techniques on News Articles","date":"2021-07-22","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-contextual-embeddings-on-less","title":"Evaluation of contextual embeddings on less-resourced languages","date":"2021-07-22","arxiv_id":"2107.10614","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-text-to-face-gan-st-2fg","title":"Semantic Text-to-Face GAN -ST^2FG","date":"2021-07-22","arxiv_id":"2107.10756","n_code_links":0,"syntology":null},{"paper":null,"slug":"causalbert-injecting-causal-knowledge-into","title":"CausalBERT: Injecting Causal Knowledge Into Pre-trained Models with Minimal Supervision","date":"2021-07-21","arxiv_id":"2107.09852","n_code_links":0,"syntology":null},{"paper":null,"slug":"drdf-determining-the-importance-of-different","title":"DRDF: Determining the Importance of Different Multimodal Information with Dual-Router Dynamic Framework","date":"2021-07-21","arxiv_id":"2107.09909","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-text-classification-via-contrastive","title":"Improved Text Classification via Contrastive Adversarial Training","date":"2021-07-21","arxiv_id":"2107.10137","n_code_links":0,"syntology":null},{"paper":null,"slug":"edge-of-chaos-as-a-guiding-principle-for","title":"Edge of chaos as a guiding principle for modern neural network training","date":"2021-07-20","arxiv_id":"2107.09437","n_code_links":0,"syntology":null},{"paper":"/paper/linked-data-triples-enhance-document","slug":"linked-data-triples-enhance-document","title":"Linked Data Triples Enhance Document Relevance Classification","date":"2021-07-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/clinical-relation-extraction-using","slug":"clinical-relation-extraction-using","title":"Clinical Relation Extraction Using Transformer-based Models","date":"2021-07-19","arxiv_id":"2107.08957","n_code_links":1,"syntology":null},{"paper":"/paper/aspect-based-sentiment-analysis-using-bert","slug":"aspect-based-sentiment-analysis-using-bert","title":"Aspect-based Sentiment Analysis using BERT with Disentangled Attention","date":"2021-07-18","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"stock-price-prediction-using-bert-and-gan","title":"Stock price prediction using BERT and GAN","date":"2021-07-18","arxiv_id":"2107.09055","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-vector-based-approach-to-few-shot-veracity","title":"A Vector-Based Approach to Few-Shot Veracity Classification for Automated Fact-Checking","date":"2021-07-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-search-learning-query-and-product","title":"Neural Search: Learning Query and Product Representations in Fashion E-commerce","date":"2021-07-17","arxiv_id":"2107.08291","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-law-of-large-documents-understanding-the","title":"The Law of Large Documents: Understanding the Structure of Legal Contracts Using Visual Cues","date":"2021-07-16","arxiv_id":"2107.08128","n_code_links":0,"syntology":null},{"paper":"/paper/autobert-zero-evolving-bert-backbone-from","slug":"autobert-zero-evolving-bert-backbone-from","title":"AutoBERT-Zero: Evolving BERT Backbone from Scratch","date":"2021-07-15","arxiv_id":"2107.07445","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-task-requirements-writing","slug":"automatic-task-requirements-writing","title":"Automatic Task Requirements Writing Evaluation via Machine Reading Comprehension","date":"2021-07-15","arxiv_id":"2107.07957","n_code_links":1,"syntology":null},{"paper":"/paper/fewclue-a-chinese-few-shot-learning","slug":"fewclue-a-chinese-few-shot-learning","title":"FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark","date":"2021-07-15","arxiv_id":"2107.07498","n_code_links":1,"syntology":null},{"paper":"/paper/only-train-once-a-one-shot-neural-network","slug":"only-train-once-a-one-shot-neural-network","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","date":"2021-07-15","arxiv_id":"2107.07467","n_code_links":1,"syntology":null},{"paper":"/paper/self-supervised-contrastive-learning-with","slug":"self-supervised-contrastive-learning-with","title":"Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based Attacks","date":"2021-07-15","arxiv_id":"2107.07610","n_code_links":1,"syntology":null},{"paper":"/paper/trusting-roberta-over-bert-insights-from","slug":"trusting-roberta-over-bert-insights-from","title":"Trusting RoBERTa over BERT: Insights from CheckListing the Natural Language Inference Task","date":"2021-07-15","arxiv_id":"2107.07229","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-fine-tuning-for-sentiment-analysis-on","title":"BERT Fine-Tuning for Sentiment Analysis on Indonesian Mobile Apps Reviews","date":"2021-07-14","arxiv_id":"2107.06802","n_code_links":0,"syntology":null},{"paper":"/paper/chimera-efficiently-training-large-scale","slug":"chimera-efficiently-training-large-scale","title":"Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelines","date":"2021-07-14","arxiv_id":"2107.06925","n_code_links":1,"syntology":null},{"paper":"/paper/indonesia-s-fake-news-detection-using","slug":"indonesia-s-fake-news-detection-using","title":"Indonesia's Fake News Detection using Transformer Network","date":"2021-07-14","arxiv_id":"2107.06796","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-scale-news-classification-using-bert","title":"Large-Scale News Classification using BERT Language Model: Spark NLP Approach","date":"2021-07-14","arxiv_id":"2107.06785","n_code_links":0,"syntology":null},{"paper":"/paper/scalable-memory-protection-in-the-penglai","slug":"scalable-memory-protection-in-the-penglai","title":"Scalable Memory Protection in the PENGLAI Enclave","date":"2021-07-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"a-deep-reinforcement-learning-approach-for-6","title":"A Deep Reinforcement Learning Approach for Traffic Signal Control Optimization","date":"2021-07-13","arxiv_id":"2107.06115","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploiting-network-structures-to-improve","title":"Exploiting Network Structures to Improve Semantic Representation for the Financial Domain","date":"2021-07-13","arxiv_id":"2107.05885","n_code_links":0,"syntology":null},{"paper":null,"slug":"rating-facts-under-coarse-to-fine-regimes","title":"Rating Facts under Coarse-to-fine Regimes","date":"2021-07-13","arxiv_id":"2107.06051","n_code_links":0,"syntology":null},{"paper":null,"slug":"tscan-dialog-structure-discovery-using-scan","title":"TSCAN : Dialog Structure discovery using SCAN","date":"2021-07-13","arxiv_id":"2107.06426","n_code_links":0,"syntology":null},{"paper":"/paper/using-bert-encoding-to-tackle-the-mad-lib","slug":"using-bert-encoding-to-tackle-the-mad-lib","title":"Using BERT Encoding to Tackle the Mad-lib Attack in SMS Spam Detection","date":"2021-07-13","arxiv_id":"2107.06400","n_code_links":1,"syntology":null},{"paper":"/paper/what-do-writing-features-tell-us-about-ai","slug":"what-do-writing-features-tell-us-about-ai","title":"What do writing features tell us about AI papers?","date":"2021-07-13","arxiv_id":"2107.06310","n_code_links":1,"syntology":null},{"paper":"/paper/a-flexible-multi-task-model-for-bert-serving","slug":"a-flexible-multi-task-model-for-bert-serving","title":"A Flexible Multi-Task Model for BERT Serving","date":"2021-07-12","arxiv_id":"2107.05377","n_code_links":1,"syntology":null},{"paper":null,"slug":"asking-clarifying-questions-based-on-negative","title":"Asking Clarifying Questions Based on Negative Feedback in Conversational Search","date":"2021-07-12","arxiv_id":"2107.05760","n_code_links":0,"syntology":null},{"paper":"/paper/coberl-contrastive-bert-for-reinforcement","slug":"coberl-contrastive-bert-for-reinforcement","title":"CoBERL: Contrastive BERT for Reinforcement Learning","date":"2021-07-12","arxiv_id":"2107.05431","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["deepmind/dm_control"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/coper-a-query-adaptable-semantics-based","slug":"coper-a-query-adaptable-semantics-based","title":"COPER: a Query-adaptable Semantics-based Search Engine for Persian COVID-19 Articles","date":"2021-07-12","arxiv_id":"2107.05722","n_code_links":1,"syntology":null},{"paper":"/paper/midibert-piano-large-scale-pre-training-for","slug":"midibert-piano-large-scale-pre-training-for","title":"BERT-like Pre-training for Symbolic Piano Music Classification Tasks","date":"2021-07-12","arxiv_id":"2107.05223","n_code_links":1,"syntology":null},{"paper":"/paper/quantifying-explainability-in-nlp-and","slug":"quantifying-explainability-in-nlp-and","title":"Quantifying Explainability in NLP and Analyzing Algorithms for Performance-Explainability Tradeoff","date":"2021-07-12","arxiv_id":"2107.05693","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mnaylor5/quantifying-explainability"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/split-embed-and-merge-an-accurate-table","slug":"split-embed-and-merge-an-accurate-table","title":"Split, embed and merge: An accurate table structure recognizer","date":"2021-07-12","arxiv_id":"2107.05214","n_code_links":0,"syntology":null},{"paper":null,"slug":"noise-stability-regularization-for-improving-1","title":"Noise Stability Regularization for Improving BERT Fine-tuning","date":"2021-07-10","arxiv_id":"2107.04835","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-initial-investigation-of-non-native-spoken","title":"An Initial Investigation of Non-Native Spoken Question-Answering","date":"2021-07-09","arxiv_id":"2107.04691","n_code_links":0,"syntology":null},{"paper":"/paper/a-review-of-bangla-natural-language","slug":"a-review-of-bangla-natural-language","title":"A Review of Bangla Natural Language Processing Tasks and the Utility of Transformer Models","date":"2021-07-08","arxiv_id":"2107.03844","n_code_links":2,"syntology":null},{"paper":null,"slug":"bumblebee-a-transformer-for-music","title":"BumbleBee: A Transformer for Music","date":"2021-07-07","arxiv_id":"2107.03443","n_code_links":0,"syntology":null},{"paper":"/paper/can-transformer-models-measure-coherence-in-1","slug":"can-transformer-models-measure-coherence-in-1","title":"Can Transformer Models Measure Coherence In Text? Re-Thinking the Shuffle Test","date":"2021-07-07","arxiv_id":"2107.03448","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-transformer-for-direct-speech","title":"Efficient Transformer for Direct Speech Translation","date":"2021-07-07","arxiv_id":"2107.03069","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-large-language-models-trained-on","slug":"evaluating-large-language-models-trained-on","title":"Evaluating Large Language Models Trained on Code","date":"2021-07-07","arxiv_id":"2107.03374","n_code_links":13,"syntology":{"ran":26,"of":39,"n_ran_checked":24,"n_instrument":2,"unverified":13,"pointer_only":4,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 0 violated, 23 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified","official":{"repos":["openai/human-eval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["found_in_text","listed","official"]}}},{"paper":null,"slug":"identifying-hijacked-reviews","title":"Identifying Hijacked Reviews","date":"2021-07-07","arxiv_id":"2107.05385","n_code_links":0,"syntology":null},{"paper":null,"slug":"languagerefer-spatial-language-model-for-3d","title":"LanguageRefer: Spatial-Language Model for 3D Visual Grounding","date":"2021-07-07","arxiv_id":"2107.03438","n_code_links":0,"syntology":null},{"paper":null,"slug":"not-quite-ask-a-librarian-ai-on-the-nature","title":"Not Quite 'Ask a Librarian': AI on the Nature, Value, and Future of LIS","date":"2021-07-07","arxiv_id":"2107.05383","n_code_links":0,"syntology":null},{"paper":null,"slug":"contradiction-detection-in-persian-text","title":"Contradiction Detection in Persian Text","date":"2021-07-05","arxiv_id":"2107.01987","n_code_links":0,"syntology":null},{"paper":"/paper/ernie-3-0-large-scale-knowledge-enhanced-pre","slug":"ernie-3-0-large-scale-knowledge-enhanced-pre","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","date":"2021-07-05","arxiv_id":"2107.02137","n_code_links":2,"syntology":null},{"paper":null,"slug":"experiments-with-adversarial-attacks-on-text","title":"Experiments with adversarial attacks on text genres","date":"2021-07-05","arxiv_id":"2107.02246","n_code_links":0,"syntology":null},{"paper":null,"slug":"uso-de-gso-cooperativos-com-decaimentos-de","title":"Uso de GSO cooperativos com decaimentos de pesos para otimizacao de redes neurais","date":"2021-07-05","arxiv_id":"2107.02080","n_code_links":0,"syntology":null},{"paper":"/paper/what-helps-transformers-recognize","slug":"what-helps-transformers-recognize","title":"What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition","date":"2021-07-05","arxiv_id":"2107.02294","n_code_links":1,"syntology":null},{"paper":"/paper/kaisa-an-adaptive-second-order-optimizer","slug":"kaisa-an-adaptive-second-order-optimizer","title":"KAISA: An Adaptive Second-Order Optimizer Framework for Deep Neural Networks","date":"2021-07-04","arxiv_id":"2107.01739","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gpauloski/kfac_pytorch"],"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/he-thinks-he-knows-better-than-the-doctors","slug":"he-thinks-he-knows-better-than-the-doctors","title":"He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics","date":"2021-07-02","arxiv_id":"2107.00807","n_code_links":1,"syntology":null},{"paper":null,"slug":"language-identification-of-hindi-english","title":"Language Identification of Hindi-English tweets using code-mixed BERT","date":"2021-07-02","arxiv_id":"2107.01202","n_code_links":0,"syntology":null},{"paper":null,"slug":"scarecrow-a-framework-for-scrutinizing","title":"Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text","date":"2021-07-02","arxiv_id":"2107.01294","n_code_links":0,"syntology":null},{"paper":"/paper/ultrasound-video-transformers-for-cardiac","slug":"ultrasound-video-transformers-for-cardiac","title":"Ultrasound Video Transformers for Cardiac Ejection Fraction Estimation","date":"2021-07-02","arxiv_id":"2107.00977","n_code_links":1,"syntology":null},{"paper":null,"slug":"elbert-fast-albert-with-confidence-window","title":"Elbert: Fast Albert with Confidence-Window Based Early Exit","date":"2021-07-01","arxiv_id":"2107.00175","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-domain-agnostic-and-specific","title":"Leveraging Domain Agnostic and Specific Knowledge for Acronym Disambiguation","date":"2021-07-01","arxiv_id":"2107.00316","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-based-secure-noma-and-cognitive-radio","title":"AI-Based Secure NOMA and Cognitive Radio enabled Green Communications: Channel State Information and Battery Value Uncertainties","date":"2021-06-30","arxiv_id":"2106.15964","n_code_links":0,"syntology":null},{"paper":null,"slug":"autolaw-augmented-legal-reasoning-through","title":"AutoLAW: Augmented Legal Reasoning through Legal Precedent Prediction","date":"2021-06-30","arxiv_id":"2106.16034","n_code_links":0,"syntology":null},{"paper":null,"slug":"early-risk-detection-of-pathological-gambling","title":"Early Risk Detection of Pathological Gambling, Self-Harm and Depression Using BERT","date":"2021-06-30","arxiv_id":"2106.16175","n_code_links":0,"syntology":null},{"paper":"/paper/the-multiberts-bert-reproductions-for","slug":"the-multiberts-bert-reproductions-for","title":"The MultiBERTs: BERT Reproductions for Robustness Analysis","date":"2021-06-30","arxiv_id":"2106.16163","n_code_links":3,"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":["google-research/language"],"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":["official"]}}},{"paper":"/paper/hate-speech-detection-using-static-bert","slug":"hate-speech-detection-using-static-bert","title":"Hate speech detection using static BERT embeddings","date":"2021-06-29","arxiv_id":"2106.15537","n_code_links":0,"syntology":null},{"paper":null,"slug":"new-arabic-medical-dataset-for-diseases","title":"New Arabic Medical Dataset for Diseases Classification","date":"2021-06-29","arxiv_id":"2106.15236","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-periodic-behavior-of-neural-network","slug":"on-the-periodic-behavior-of-neural-network","title":"On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay","date":"2021-06-29","arxiv_id":"2106.15739","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["tipt0p/periodic_behavior_bn_wd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/packing-towards-2x-nlp-bert-acceleration","slug":"packing-towards-2x-nlp-bert-acceleration","title":"Efficient Sequence Packing without Cross-contamination: Accelerating Large Language Models without Impacting Performance","date":"2021-06-29","arxiv_id":"2107.02027","n_code_links":1,"syntology":null},{"paper":"/paper/a-3d-cnn-network-with-bert-for-automatic","slug":"a-3d-cnn-network-with-bert-for-automatic","title":"A 3D CNN Network with BERT For Automatic COVID-19 Diagnosis From CT-Scan Images","date":"2021-06-28","arxiv_id":"2106.14403","n_code_links":1,"syntology":null},{"paper":null,"slug":"current-landscape-of-the-russian-sentiment","title":"Current Landscape of the Russian Sentiment Corpora","date":"2021-06-28","arxiv_id":"2106.14434","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-the-generalization-for-intent","title":"Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU","date":"2021-06-28","arxiv_id":"2106.14464","n_code_links":0,"syntology":null},{"paper":null,"slug":"traditional-machine-learning-and-deep","title":"Traditional Machine Learning and Deep Learning Models for Argumentation Mining in Russian Texts","date":"2021-06-28","arxiv_id":"2106.14438","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-s-in-a-measurement-using-gpt-3-on","title":"What's in a Measurement? Using GPT-3 on SemEval 2021 Task 8 -- MeasEval","date":"2021-06-28","arxiv_id":"2106.14720","n_code_links":0,"syntology":null},{"paper":"/paper/a-closer-look-at-how-fine-tuning-changes-bert","slug":"a-closer-look-at-how-fine-tuning-changes-bert","title":"A Closer Look at How Fine-tuning Changes BERT","date":"2021-06-27","arxiv_id":"2106.14282","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 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["utahnlp/BERT-fine-tuning-analysis"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ai-based-presentation-creator-with-customized","title":"AI based Presentation Creator With Customized Audio Content Delivery","date":"2021-06-27","arxiv_id":"2106.14213","n_code_links":0,"syntology":null},{"paper":"/paper/symbolicgpt-a-generative-transformer-model","slug":"symbolicgpt-a-generative-transformer-model","title":"SymbolicGPT: A Generative Transformer Model for Symbolic Regression","date":"2021-06-27","arxiv_id":"2106.14131","n_code_links":2,"syntology":{"ran":9,"of":9,"n_ran_checked":8,"n_instrument":1,"unverified":0,"pointer_only":0,"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":["git.uwaterloo.ca/data-analytics-lab/symbolicgpt2"],"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":"answering-chinese-elementary-school-social","title":"Answering Chinese Elementary School Social Study Multiple Choice Questions","date":"2021-06-26","arxiv_id":"2107.02893","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-differential-privacy-and","slug":"benchmarking-differential-privacy-and","title":"Benchmarking Differential Privacy and Federated Learning for BERT Models","date":"2021-06-26","arxiv_id":"2106.13973","n_code_links":1,"syntology":null},{"paper":null,"slug":"low-precision-training-in-logarithmic-number","title":"LNS-Madam: Low-Precision Training in Logarithmic Number System using Multiplicative Weight Update","date":"2021-06-26","arxiv_id":"2106.13914","n_code_links":0,"syntology":null},{"paper":"/paper/spreadsheetcoder-formula-prediction-from-semi-1","slug":"spreadsheetcoder-formula-prediction-from-semi-1","title":"SpreadsheetCoder: Formula Prediction from Semi-structured Context","date":"2021-06-26","arxiv_id":"2106.15339","n_code_links":1,"syntology":null},{"paper":null,"slug":"toward-less-hidden-cost-of-code-completion","title":"Toward Less Hidden Cost of Code Completion with Acceptance and Ranking Models","date":"2021-06-26","arxiv_id":"2106.13928","n_code_links":0,"syntology":null},{"paper":"/paper/umic-an-unreferenced-metric-for-image","slug":"umic-an-unreferenced-metric-for-image","title":"UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning","date":"2021-06-26","arxiv_id":"2106.14019","n_code_links":1,"syntology":{"ran":7,"of":14,"n_ran_checked":7,"n_instrument":0,"unverified":7,"pointer_only":0,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","official":{"repos":["hwanheelee1993/UMIC"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":4,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"adapt-and-distill-developing-small-fast-and","title":"Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains","date":"2021-06-25","arxiv_id":"2106.13474","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-sample-replacements-for-electra","title":"Learning to Sample Replacements for ELECTRA Pre-Training","date":"2021-06-25","arxiv_id":"2106.13715","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-automated-knowledge-mining-and-document","title":"An Automated Knowledge Mining and Document Classification System with Multi-model Transfer Learning","date":"2021-06-24","arxiv_id":"2106.12744","n_code_links":0,"syntology":null},{"paper":null,"slug":"discovering-novel-drug-supplement","title":"Discovering novel drug-supplement interactions using a dietary supplements knowledge graph generated from the biomedical literature","date":"2021-06-24","arxiv_id":"2106.12741","n_code_links":0,"syntology":null},{"paper":"/paper/education-to-skill-mapping-using-hierarchical","slug":"education-to-skill-mapping-using-hierarchical","title":"Education-to-Skill Mapping Using Hierarchical Classification and Transformer Neural Network","date":"2021-06-24","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"quantization-aware-training-ernie-and","title":"Quantization Aware Training, ERNIE and Kurtosis Regularizer: a short empirical study","date":"2021-06-24","arxiv_id":"2106.13035","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-topic-segmentation-of-meetings","slug":"unsupervised-topic-segmentation-of-meetings","title":"Unsupervised Topic Segmentation of Meetings with BERT Embeddings","date":"2021-06-24","arxiv_id":"2106.12978","n_code_links":2,"syntology":null},{"paper":"/paper/classifying-textual-data-with-pre-trained","slug":"classifying-textual-data-with-pre-trained","title":"Classifying Textual Data with Pre-trained Vision Models through Transfer Learning and Data Transformations","date":"2021-06-23","arxiv_id":"2106.12479","n_code_links":1,"syntology":null},{"paper":"/paper/learnt-sparsity-for-effective-and","slug":"learnt-sparsity-for-effective-and","title":"Extractive Explanations for Interpretable Text Ranking","date":"2021-06-23","arxiv_id":"2106.12460","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-case-study-in-bootstrapping-ontology-graphs","title":"A Case Study in Bootstrapping Ontology Graphs from Textbooks","date":"2021-06-22","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/a-comprehensive-exploration-of-pre-training","slug":"a-comprehensive-exploration-of-pre-training","title":"A Comprehensive Comparison of Pre-training Language Models","date":"2021-06-22","arxiv_id":"2106.11483","n_code_links":2,"syntology":null},{"paper":"/paper/combining-analogy-with-language-models-for","slug":"combining-analogy-with-language-models-for","title":"Combining Analogy with Language Models for Knowledge Extraction","date":"2021-06-22","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/fine-tune-the-entire-rag-architecture","slug":"fine-tune-the-entire-rag-architecture","title":"Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering","date":"2021-06-22","arxiv_id":"2106.11517","n_code_links":2,"syntology":null},{"paper":"/paper/lv-bert-exploiting-layer-variety-for-bert","slug":"lv-bert-exploiting-layer-variety-for-bert","title":"LV-BERT: Exploiting Layer Variety for BERT","date":"2021-06-22","arxiv_id":"2106.11740","n_code_links":1,"syntology":null},{"paper":"/paper/one-shot-to-weakly-supervised-relation","slug":"one-shot-to-weakly-supervised-relation","title":"One-shot to Weakly-Supervised Relation Classification using Language Models","date":"2021-06-22","arxiv_id":null,"n_code_links":1,"syntology":null}],"record_sha256":"b252ce041f8e96aa4dd19a1671eede6577cec18fdda806e18780c32f6749f73b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}