{"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/linear-warmup-with-linear-decay/papers/52","list_of":"/method/linear-warmup-with-linear-decay","method":"Linear Warmup With Linear 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":52,"pages_in_order":71,"rows_per_page":100,"rows":[5101,5200],"of":7076,"counts":{"archive_papers_tagged":7076,"with_a_code_link":2913,"where_syntology_ran_a_sample":650,"not_listed_spam_title":0,"listed":7076,"listed_where_code_ran":650,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":531,"every_run_a_failure_of_syntologys_instrument":119,"listed_with_a_run_with_no_instrument_failure":531,"listed_every_run_a_failure_of_syntologys_instrument":119,"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/linear-warmup-with-linear-decay","prev":"/method/linear-warmup-with-linear-decay/papers/51","next":"/method/linear-warmup-with-linear-decay/papers/53","papers":[{"paper":null,"slug":"mixup-training-leads-to-reduced-overfitting","title":"MixUp Training Leads to Reduced Overfitting and Improved Calibration for the Transformer Architecture","date":"2021-02-22","arxiv_id":"2102.11402","n_code_links":0,"syntology":null},{"paper":"/paper/parallelizing-legendre-memory-unit-training","slug":"parallelizing-legendre-memory-unit-training","title":"Parallelizing Legendre Memory Unit Training","date":"2021-02-22","arxiv_id":"2102.11417","n_code_links":2,"syntology":null},{"paper":null,"slug":"rubert-a-bilingual-roman-urdu-bert-using","title":"RUBERT: A Bilingual Roman Urdu BERT Using Cross Lingual Transfer Learning","date":"2021-02-22","arxiv_id":"2102.11278","n_code_links":0,"syntology":null},{"paper":"/paper/using-prior-knowledge-to-guide-bert-s","slug":"using-prior-knowledge-to-guide-bert-s","title":"Using Prior Knowledge to Guide BERT's Attention in Semantic Textual Matching Tasks","date":"2021-02-22","arxiv_id":"2102.10934","n_code_links":1,"syntology":null},{"paper":null,"slug":"pre-training-bert-on-arabic-tweets-practical","title":"Pre-Training BERT on Arabic Tweets: Practical Considerations","date":"2021-02-21","arxiv_id":"2102.10684","n_code_links":0,"syntology":null},{"paper":null,"slug":"web-based-application-for-detecting","title":"Web-based Application for Detecting Indonesian Clickbait Headlines using IndoBERT","date":"2021-02-21","arxiv_id":"2102.10601","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-dynamic-bert-via-trainable-gate","title":"Learning Dynamic BERT via Trainable Gate Variables and a Bi-modal Regularizer","date":"2021-02-19","arxiv_id":"2102.09727","n_code_links":0,"syntology":null},{"paper":"/paper/towards-emotion-recognition-in-hindi-english","slug":"towards-emotion-recognition-in-hindi-english","title":"Towards Emotion Recognition in Hindi-English Code-Mixed Data: A Transformer Based Approach","date":"2021-02-19","arxiv_id":"2102.09943","n_code_links":1,"syntology":null},{"paper":"/paper/using-transformer-based-ensemble-learning-to","slug":"using-transformer-based-ensemble-learning-to","title":"Using Transformer based Ensemble Learning to classify Scientific Articles","date":"2021-02-19","arxiv_id":"2102.09991","n_code_links":2,"syntology":null},{"paper":"/paper/analysis-of-contextual-and-non-contextual","slug":"analysis-of-contextual-and-non-contextual","title":"Analysis Of Contextual and Non-Contextual Word Embedding Models For Hindi NER With Web Application For Data Collection","date":"2021-02-18","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/training-microsoft-news-recommenders-with","slug":"training-microsoft-news-recommenders-with","title":"Training Large-Scale News Recommenders with Pretrained Language Models in the Loop","date":"2021-02-18","arxiv_id":"2102.09268","n_code_links":1,"syntology":null},{"paper":null,"slug":"unibuckernel-geolocating-swiss-german-jodels","title":"UnibucKernel: Geolocating Swiss German Jodels Using Ensemble Learning","date":"2021-02-18","arxiv_id":"2102.09379","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-query-resolution-and-reading","title":"Leveraging Query Resolution and Reading Comprehension for Conversational Passage Retrieval","date":"2021-02-17","arxiv_id":"2102.08795","n_code_links":0,"syntology":null},{"paper":"/paper/scidr-at-sdu-2020-ideas-identifying-and","slug":"scidr-at-sdu-2020-ideas-identifying-and","title":"SciDr at SDU-2020: IDEAS -- Identifying and Disambiguating Everyday Acronyms for Scientific Domain","date":"2021-02-17","arxiv_id":"2102.08818","n_code_links":2,"syntology":null},{"paper":"/paper/tcn-table-convolutional-network-for-web-table","slug":"tcn-table-convolutional-network-for-web-table","title":"TCN: Table Convolutional Network for Web Table Interpretation","date":"2021-02-17","arxiv_id":"2102.09460","n_code_links":1,"syntology":null},{"paper":"/paper/coco-lm-correcting-and-contrasting-text","slug":"coco-lm-correcting-and-contrasting-text","title":"COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining","date":"2021-02-16","arxiv_id":"2102.08473","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":1,"n_instrument":4,"unverified":1,"pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/coco-lm"],"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/exploring-transformers-in-natural-language","slug":"exploring-transformers-in-natural-language","title":"Exploring Transformers in Natural Language Generation: GPT, BERT, and XLNet","date":"2021-02-16","arxiv_id":"2102.08036","n_code_links":1,"syntology":null},{"paper":null,"slug":"have-attention-heads-in-bert-learned","title":"Have Attention Heads in BERT Learned Constituency Grammar?","date":"2021-02-16","arxiv_id":"2102.07926","n_code_links":0,"syntology":null},{"paper":"/paper/non-autoregressive-text-generation-with-pre","slug":"non-autoregressive-text-generation-with-pre","title":"Non-Autoregressive Text Generation with Pre-trained Language Models","date":"2021-02-16","arxiv_id":"2102.08220","n_code_links":1,"syntology":null},{"paper":"/paper/dobf-a-deobfuscation-pre-training-objective","slug":"dobf-a-deobfuscation-pre-training-objective","title":"DOBF: A Deobfuscation Pre-Training Objective for Programming Languages","date":"2021-02-15","arxiv_id":"2102.07492","n_code_links":2,"syntology":null},{"paper":null,"slug":"fast-end-to-end-speech-recognition-via-non","title":"Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT","date":"2021-02-15","arxiv_id":"2102.07594","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-customer-transaction-classification","title":"Improved Customer Transaction Classification using Semi-Supervised Knowledge Distillation","date":"2021-02-15","arxiv_id":"2102.07635","n_code_links":0,"syntology":null},{"paper":null,"slug":"within-document-event-coreference-with-bert","title":"Within-Document Event Coreference with BERT-Based Contextualized Representations","date":"2021-02-15","arxiv_id":"2102.09600","n_code_links":0,"syntology":null},{"paper":"/paper/indicnlp-kgp-at-dravidianlangtech-eacl2021","slug":"indicnlp-kgp-at-dravidianlangtech-eacl2021","title":"indicnlp@kgp at DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Languages","date":"2021-02-14","arxiv_id":"2102.07150","n_code_links":1,"syntology":null},{"paper":"/paper/indicnlp-kgp-at-dravidianlangtech-eacl2021-1","slug":"indicnlp-kgp-at-dravidianlangtech-eacl2021-1","title":"indicnlp@ kgp at DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Languages","date":"2021-02-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/characterizing-english-variation-across","slug":"characterizing-english-variation-across","title":"Characterizing English Variation across Social Media Communities with BERT","date":"2021-02-12","arxiv_id":"2102.06820","n_code_links":1,"syntology":null},{"paper":null,"slug":"dancing-along-battery-enabling-transformer","title":"Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices","date":"2021-02-12","arxiv_id":"2102.06336","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-precision-analog-computing-for-neural","slug":"dynamic-precision-analog-computing-for-neural","title":"Dynamic Precision Analog Computing for Neural Networks","date":"2021-02-12","arxiv_id":"2102.06365","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-classic-and-neural-lexical","slug":"exploring-classic-and-neural-lexical","title":"Exploring Classic and Neural Lexical Translation Models for Information Retrieval: Interpretability, Effectiveness, and Efficiency Benefits","date":"2021-02-12","arxiv_id":"2102.06815","n_code_links":2,"syntology":null},{"paper":null,"slug":"optimizing-inference-performance-of","title":"Optimizing Inference Performance of Transformers on CPUs","date":"2021-02-12","arxiv_id":"2102.06621","n_code_links":0,"syntology":null},{"paper":null,"slug":"newsbert-distilling-pre-trained-language","title":"NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application","date":"2021-02-09","arxiv_id":"2102.04887","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-approach-for-arabic","title":"Transfer Learning Approach for Arabic Offensive Language Detection System -- BERT-Based Model","date":"2021-02-09","arxiv_id":"2102.05708","n_code_links":0,"syntology":null},{"paper":"/paper/spoiler-alert-using-natural-language","slug":"spoiler-alert-using-natural-language","title":"Spoiler Alert: Using Natural Language Processing to Detect Spoilers in Book Reviews","date":"2021-02-07","arxiv_id":"2102.03882","n_code_links":1,"syntology":null},{"paper":"/paper/pipetransformer-automated-elastic-pipelining","slug":"pipetransformer-automated-elastic-pipelining","title":"PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers","date":"2021-02-05","arxiv_id":"2102.03161","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Distributed-AI/PipeTransformer"],"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":["official"]}}},{"paper":"/paper/rpbert-a-text-image-relation-propagation","slug":"rpbert-a-text-image-relation-propagation","title":"RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER","date":"2021-02-05","arxiv_id":"2102.02967","n_code_links":1,"syntology":null},{"paper":"/paper/1-bit-adam-communication-efficient-large","slug":"1-bit-adam-communication-efficient-large","title":"1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed","date":"2021-02-04","arxiv_id":"2102.02888","n_code_links":2,"syntology":null},{"paper":"/paper/hierarchical-multi-head-attentive-network-for","slug":"hierarchical-multi-head-attentive-network-for","title":"Hierarchical Multi-head Attentive Network for Evidence-aware Fake News Detection","date":"2021-02-04","arxiv_id":"2102.02680","n_code_links":1,"syntology":null},{"paper":null,"slug":"bootstrapping-multilingual-amr-with","title":"Bootstrapping Multilingual AMR with Contextual Word Alignments","date":"2021-02-03","arxiv_id":"2102.02189","n_code_links":0,"syntology":null},{"paper":null,"slug":"hebert-hebemo-a-hebrew-bert-model-and-a-tool","title":"HeBERT & HebEMO: a Hebrew BERT Model and a Tool for Polarity Analysis and Emotion Recognition","date":"2021-02-03","arxiv_id":"2102.01909","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-transfer-learning-with-transformers","title":"Introduction to Neural Transfer Learning with Transformers for Social Science Text Analysis","date":"2021-02-03","arxiv_id":"2102.02111","n_code_links":0,"syntology":null},{"paper":"/paper/autofreeze-automatically-freezing-model","slug":"autofreeze-automatically-freezing-model","title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning","date":"2021-02-02","arxiv_id":"2102.01386","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":{"repos":["uw-mad-dash/AutoFreeze"],"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":"clickbait-headline-detection-in-indonesian","title":"Clickbait Headline Detection in Indonesian News Sites using Multilingual Bidirectional Encoder Representations from Transformers (M-BERT)","date":"2021-02-02","arxiv_id":"2102.01497","n_code_links":0,"syntology":null},{"paper":"/paper/improving-distantly-supervised-relation-3","slug":"improving-distantly-supervised-relation-3","title":"Improving Distantly-Supervised Relation Extraction through BERT-based Label & Instance Embeddings","date":"2021-02-01","arxiv_id":"2102.01156","n_code_links":1,"syntology":null},{"paper":null,"slug":"polyphone-disambiguition-in-mandarin-chinese","title":"Polyphone Disambiguation in Mandarin Chinese with Semi-Supervised Learning","date":"2021-02-01","arxiv_id":"2102.00621","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-federated-learning-for-fine-tuning-of","title":"Scaling Federated Learning for Fine-tuning of Large Language Models","date":"2021-02-01","arxiv_id":"2102.00875","n_code_links":0,"syntology":null},{"paper":"/paper/sj-aj-dravidianlangtech-eacl2021-task","slug":"sj-aj-dravidianlangtech-eacl2021-task","title":"SJ_AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification","date":"2021-02-01","arxiv_id":"2102.01051","n_code_links":1,"syntology":null},{"paper":"/paper/text-to-hashtag-generation-using-seq2seq","slug":"text-to-hashtag-generation-using-seq2seq","title":"Text-to-hashtag Generation using Seq2seq Learning","date":"2021-02-01","arxiv_id":"2102.00904","n_code_links":1,"syntology":null},{"paper":"/paper/re-reproducing-learning-to-deceive-with","slug":"re-reproducing-learning-to-deceive-with","title":"[Re] Reproducing Learning to Deceive With Attention-Based Explanations","date":"2021-01-31","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarially-learning-disentangled-speech","title":"Adversarially learning disentangled speech representations for robust multi-factor voice conversion","date":"2021-01-30","arxiv_id":"2102.00184","n_code_links":0,"syntology":null},{"paper":null,"slug":"empathbert-a-bert-based-framework-for","title":"EmpathBERT: A BERT-based Framework for Demographic-aware Empathy Prediction","date":"2021-01-30","arxiv_id":"2102.00272","n_code_links":0,"syntology":null},{"paper":"/paper/learning-from-how-human-correct","slug":"learning-from-how-human-correct","title":"Learning From Human Correction","date":"2021-01-30","arxiv_id":"2102.00225","n_code_links":1,"syntology":null},{"paper":null,"slug":"shuftext-a-simple-black-box-approach-to","title":"ShufText: A Simple Black Box Approach to Evaluate the Fragility of Text Classification Models","date":"2021-01-30","arxiv_id":"2102.00238","n_code_links":0,"syntology":null},{"paper":null,"slug":"speech-recognition-by-simply-fine-tuning-bert","title":"Speech Recognition by Simply Fine-tuning BERT","date":"2021-01-30","arxiv_id":"2102.00291","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-bert-based-models-for-plant","slug":"fine-tuning-bert-based-models-for-plant","title":"Fine-tuning BERT-based models for Plant Health Bulletin Classification","date":"2021-01-29","arxiv_id":"2102.00838","n_code_links":1,"syntology":null},{"paper":"/paper/a-graph-based-relevance-matching-model-for-ad","slug":"a-graph-based-relevance-matching-model-for-ad","title":"A Graph-based Relevance Matching Model for Ad-hoc Retrieval","date":"2021-01-28","arxiv_id":"2101.11873","n_code_links":1,"syntology":null},{"paper":null,"slug":"bertau-itau-bert-for-digital-customer-service","title":"BERTaú: Itaú BERT for digital customer service","date":"2021-01-28","arxiv_id":"2101.12015","n_code_links":0,"syntology":null},{"paper":null,"slug":"korealbert-pretraining-a-lite-bert-model-for","title":"KoreALBERT: Pretraining a Lite BERT Model for Korean Language Understanding","date":"2021-01-27","arxiv_id":"2101.11363","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-evolution-of-syntactic-information","title":"On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations","date":"2021-01-27","arxiv_id":"2101.11492","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-can-reflect-syntactic-structure-if","title":"Attention Can Reflect Syntactic Structure (If You Let It)","date":"2021-01-26","arxiv_id":"2101.10927","n_code_links":0,"syntology":null},{"paper":null,"slug":"climp-a-benchmark-for-chinese-language-model","title":"CLiMP: A Benchmark for Chinese Language Model Evaluation","date":"2021-01-26","arxiv_id":"2101.11131","n_code_links":0,"syntology":null},{"paper":"/paper/deep-subjecthood-higher-order-grammatical","slug":"deep-subjecthood-higher-order-grammatical","title":"Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERT","date":"2021-01-26","arxiv_id":"2101.11043","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-bert-and-albert-sentence","title":"Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks","date":"2021-01-26","arxiv_id":"2101.10642","n_code_links":0,"syntology":null},{"paper":"/paper/first-align-then-predict-understanding-the","slug":"first-align-then-predict-understanding-the","title":"First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT","date":"2021-01-26","arxiv_id":"2101.11109","n_code_links":1,"syntology":null},{"paper":null,"slug":"named-entity-recognition-in-the-style-of","title":"Named Entity Recognition in the Style of Object Detection","date":"2021-01-26","arxiv_id":"2101.11122","n_code_links":0,"syntology":null},{"paper":null,"slug":"regulatory-compliance-through-doc2doc","title":"Regulatory Compliance through Doc2Doc Information Retrieval: A case study in EU/UK legislation where text similarity has limitations","date":"2021-01-26","arxiv_id":"2101.10726","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hybrid-approach-to-measure-semantic","title":"A Hybrid Approach to Measure Semantic Relatedness in Biomedical Concepts","date":"2021-01-25","arxiv_id":"2101.10196","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-dialog-length-matter-for-next-response","title":"Does Dialog Length matter for Next Response Selection task? An Empirical Study","date":"2021-01-24","arxiv_id":"2101.09647","n_code_links":0,"syntology":null},{"paper":"/paper/romebert-robust-training-of-multi-exit-bert","slug":"romebert-robust-training-of-multi-exit-bert","title":"RomeBERT: Robust Training of Multi-Exit BERT","date":"2021-01-24","arxiv_id":"2101.09755","n_code_links":1,"syntology":null},{"paper":"/paper/stereotype-and-skew-quantifying-gender-bias","slug":"stereotype-and-skew-quantifying-gender-bias","title":"Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models","date":"2021-01-24","arxiv_id":"2101.09688","n_code_links":1,"syntology":null},{"paper":"/paper/training-multilingual-pre-trained-language","slug":"training-multilingual-pre-trained-language","title":"Training Multilingual Pre-trained Language Model with Byte-level Subwords","date":"2021-01-23","arxiv_id":"2101.09469","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-perspective-combined-recall-and-rank","title":"A multi-perspective combined recall and rank framework for Chinese procedure terminology normalization","date":"2021-01-22","arxiv_id":"2101.09101","n_code_links":0,"syntology":null},{"paper":"/paper/drug-and-disease-interpretation-learning-with","slug":"drug-and-disease-interpretation-learning-with","title":"Drug and Disease Interpretation Learning with Biomedical Entity Representation Transformer","date":"2021-01-22","arxiv_id":"2101.09311","n_code_links":1,"syntology":null},{"paper":null,"slug":"extracting-lifestyle-factors-for-alzheimer-s","title":"Extracting Lifestyle Factors for Alzheimer's Disease from Clinical Notes Using Deep Learning with Weak Supervision","date":"2021-01-22","arxiv_id":"2101.09244","n_code_links":0,"syntology":null},{"paper":"/paper/hasocone-fire-hasoc2020-using-bert-and","slug":"hasocone-fire-hasoc2020-using-bert-and","title":"HASOCOne@FIRE-HASOC2020: Using BERT and Multilingual BERT models for Hate Speech Detection","date":"2021-01-22","arxiv_id":"2101.09007","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-pre-trained-transformers-and","title":"Multilingual Pre-Trained Transformers and Convolutional NN Classification Models for Technical Domain Identification","date":"2021-01-22","arxiv_id":"2101.09012","n_code_links":0,"syntology":null},{"paper":"/paper/the-heads-hypothesis-a-unifying-statistical","slug":"the-heads-hypothesis-a-unifying-statistical","title":"The heads hypothesis: A unifying statistical approach towards understanding multi-headed attention in BERT","date":"2021-01-22","arxiv_id":"2101.09115","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-multilingual-text-encoders-for","slug":"evaluating-multilingual-text-encoders-for","title":"Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval","date":"2021-01-21","arxiv_id":"2101.08370","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rlitschk/EncoderCLIR"],"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":["official"]}}},{"paper":"/paper/classifying-scientific-publications-with-bert","slug":"classifying-scientific-publications-with-bert","title":"Classifying Scientific Publications with BERT -- Is Self-Attention a Feature Selection Method?","date":"2021-01-20","arxiv_id":"2101.08114","n_code_links":1,"syntology":null},{"paper":"/paper/divide-and-conquer-an-ensemble-approach-for","slug":"divide-and-conquer-an-ensemble-approach-for","title":"Divide and Conquer: An Ensemble Approach for Hostile Post Detection in Hindi","date":"2021-01-20","arxiv_id":"2101.07973","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-augment-for-data-scarce-domain","slug":"learning-to-augment-for-data-scarce-domain","title":"Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation","date":"2021-01-20","arxiv_id":"2101.08106","n_code_links":0,"syntology":{"ran":2,"of":15,"n_ran_checked":2,"n_instrument":0,"unverified":13,"pointer_only":15,"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) · 13 unverified","official":null}},{"paper":"/paper/situation-and-behavior-understanding-by-trope","slug":"situation-and-behavior-understanding-by-trope","title":"Situation and Behavior Understanding by Trope Detection on Films","date":"2021-01-19","arxiv_id":"2101.07632","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-punctuation-restoration-with-bert","slug":"automatic-punctuation-restoration-with-bert","title":"Automatic punctuation restoration with BERT models","date":"2021-01-18","arxiv_id":"2101.07343","n_code_links":1,"syntology":null},{"paper":"/paper/can-a-fruit-fly-learn-word-embeddings-1","slug":"can-a-fruit-fly-learn-word-embeddings-1","title":"Can a Fruit Fly Learn Word Embeddings?","date":"2021-01-18","arxiv_id":"2101.06887","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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"transformer-based-models-for-question","title":"Transformer-Based Models for Question Answering on COVID19","date":"2021-01-16","arxiv_id":"2101.11432","n_code_links":0,"syntology":null},{"paper":null,"slug":"grid-search-hyperparameter-benchmarking-of","title":"Grid Search Hyperparameter Benchmarking of BERT, ALBERT, and LongFormer on DuoRC","date":"2021-01-15","arxiv_id":"2101.06326","n_code_links":0,"syntology":null},{"paper":null,"slug":"hostility-detection-and-covid-19-fake-news","title":"Hostility Detection and Covid-19 Fake News Detection in Social Media","date":"2021-01-15","arxiv_id":"2101.05953","n_code_links":0,"syntology":null},{"paper":null,"slug":"kdlsq-bert-a-quantized-bert-combining","title":"KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization","date":"2021-01-15","arxiv_id":"2101.05938","n_code_links":0,"syntology":null},{"paper":"/paper/ecol-early-detection-of-covid-lies-using","slug":"ecol-early-detection-of-covid-lies-using","title":"ECOL: Early Detection of COVID Lies Using Content, Prior Knowledge and Source Information","date":"2021-01-14","arxiv_id":"2101.05499","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-language-model-fine-tuning","title":"Transformer-based Language Model Fine-tuning Methods for COVID-19 Fake News Detection","date":"2021-01-14","arxiv_id":"2101.05509","n_code_links":0,"syntology":null},{"paper":null,"slug":"wer-bert-automatic-wer-estimation-with-bert","title":"WER-BERT: Automatic WER Estimation with BERT in a Balanced Ordinal Classification Paradigm","date":"2021-01-14","arxiv_id":"2101.05478","n_code_links":0,"syntology":null},{"paper":null,"slug":"experimental-evaluation-of-deep-learning","title":"Experimental Evaluation of Deep Learning models for Marathi Text Classification","date":"2021-01-13","arxiv_id":"2101.04899","n_code_links":0,"syntology":null},{"paper":null,"slug":"heterogeneous-network-embedding-for-deep","title":"Heterogeneous Network Embedding for Deep Semantic Relevance Match in E-commerce Search","date":"2021-01-13","arxiv_id":"2101.04850","n_code_links":0,"syntology":null},{"paper":"/paper/ladiff-ulmfit-a-layer-differentiated-training","slug":"ladiff-ulmfit-a-layer-differentiated-training","title":"LaDiff ULMFiT: A Layer Differentiated training approach for ULMFiT","date":"2021-01-13","arxiv_id":"2101.04965","n_code_links":1,"syntology":null},{"paper":null,"slug":"fake-news-detection-system-using-xlnet-model","title":"Fake News Detection System using XLNet model with Topic Distributions: CONSTRAINT@AAAI2021 Shared Task","date":"2021-01-12","arxiv_id":"2101.11425","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-contract-element-extraction-revisited","title":"Neural Contract Element Extraction Revisited: Letters from Sesame Street","date":"2021-01-12","arxiv_id":"2101.04355","n_code_links":0,"syntology":null},{"paper":"/paper/of-non-linearity-and-commutativity-in-bert","slug":"of-non-linearity-and-commutativity-in-bert","title":"Of Non-Linearity and Commutativity in BERT","date":"2021-01-12","arxiv_id":"2101.04547","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-more-efficient-chinese-named-entity","title":"A More Efficient Chinese Named Entity Recognition base on BERT and Syntactic Analysis","date":"2021-01-11","arxiv_id":"2101.11423","n_code_links":0,"syntology":null},{"paper":null,"slug":"at-bert-adversarial-training-bert-for-acronym","title":"AT-BERT: Adversarial Training BERT for Acronym Identification Winning Solution for SDU@AAAI-21","date":"2021-01-11","arxiv_id":"2101.03700","n_code_links":0,"syntology":null},{"paper":"/paper/bert-gt-cross-sentence-n-ary-relation","slug":"bert-gt-cross-sentence-n-ary-relation","title":"BERT-GT: Cross-sentence n-ary relation extraction with BERT and Graph Transformer","date":"2021-01-11","arxiv_id":"2101.04158","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-deep-learning-models-for","title":"Evaluation of Deep Learning Models for Hostility Detection in Hindi Text","date":"2021-01-11","arxiv_id":"2101.04144","n_code_links":0,"syntology":null}],"record_sha256":"b045f881bcd0e440797be9fba38c74f1c7bf94243bf4547a7b12e7dbe3df5f9b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}