{"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/86","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":86,"pages_in_order":108,"rows_per_page":100,"rows":[8501,8600],"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/85","next":"/method/weight-decay/papers/87","papers":[{"paper":null,"slug":"explicit-regularization-and-implicit-bias-in","title":"Explicit regularization and implicit bias in deep network classifiers trained with the square loss","date":"2020-12-31","arxiv_id":"2101.00072","n_code_links":0,"syntology":null},{"paper":"/paper/kart-privacy-leakage-framework-of-language","slug":"kart-privacy-leakage-framework-of-language","title":"KART: Parameterization of Privacy Leakage Scenarios from Pre-trained Language Models","date":"2020-12-31","arxiv_id":"2101.00036","n_code_links":1,"syntology":null},{"paper":"/paper/linear-time-wordpiece-tokenization","slug":"linear-time-wordpiece-tokenization","title":"Fast WordPiece Tokenization","date":"2020-12-31","arxiv_id":"2012.15524","n_code_links":1,"syntology":null},{"paper":"/paper/making-pre-trained-language-models-better-few","slug":"making-pre-trained-language-models-better-few","title":"Making Pre-trained Language Models Better Few-shot Learners","date":"2020-12-31","arxiv_id":"2012.15723","n_code_links":9,"syntology":{"ran":2,"of":9,"n_ran_checked":2,"n_instrument":0,"unverified":7,"pointer_only":7,"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) · 7 unverified","official":{"repos":["princeton-nlp/LM-BFF"],"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/minilmv2-multi-head-self-attention-relation","slug":"minilmv2-multi-head-self-attention-relation","title":"MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers","date":"2020-12-31","arxiv_id":"2012.15828","n_code_links":2,"syntology":null},{"paper":"/paper/the-pile-an-800gb-dataset-of-diverse-text-for","slug":"the-pile-an-800gb-dataset-of-diverse-text-for","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","date":"2020-12-31","arxiv_id":"2101.00027","n_code_links":22,"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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["EleutherAI/The-Pile"],"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/unified-mandarin-tts-front-end-based-on","slug":"unified-mandarin-tts-front-end-based-on","title":"Unified Mandarin TTS Front-end Based on Distilled BERT Model","date":"2020-12-31","arxiv_id":"2012.15404","n_code_links":1,"syntology":null},{"paper":"/paper/unks-everywhere-adapting-multilingual","slug":"unks-everywhere-adapting-multilingual","title":"UNKs Everywhere: Adapting Multilingual Language Models to New Scripts","date":"2020-12-31","arxiv_id":"2012.15562","n_code_links":2,"syntology":null},{"paper":"/paper/deer-a-data-efficient-language-model-for","slug":"deer-a-data-efficient-language-model-for","title":"ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning","date":"2020-12-30","arxiv_id":"2012.15283","n_code_links":2,"syntology":null},{"paper":null,"slug":"deriving-contextualised-semantic-features","title":"Deriving Contextualised Semantic Features from BERT (and Other Transformer Model) Embeddings","date":"2020-12-30","arxiv_id":"2012.15353","n_code_links":0,"syntology":null},{"paper":"/paper/improving-bert-with-syntax-aware-local","slug":"improving-bert-with-syntax-aware-local","title":"Improving BERT with Syntax-aware Local Attention","date":"2020-12-30","arxiv_id":"2012.15150","n_code_links":1,"syntology":null},{"paper":"/paper/optimizing-deeper-transformers-on-small","slug":"optimizing-deeper-transformers-on-small","title":"Optimizing Deeper Transformers on Small Datasets","date":"2020-12-30","arxiv_id":"2012.15355","n_code_links":1,"syntology":null},{"paper":null,"slug":"out-of-order-how-important-is-the-sequential","title":"Out of Order: How Important Is The Sequential Order of Words in a Sentence in Natural Language Understanding Tasks?","date":"2020-12-30","arxiv_id":"2012.15180","n_code_links":0,"syntology":null},{"paper":"/paper/semglove-semantic-co-occurrences-for-glove","slug":"semglove-semantic-co-occurrences-for-glove","title":"SemGloVe: Semantic Co-occurrences for GloVe from BERT","date":"2020-12-30","arxiv_id":"2012.15197","n_code_links":3,"syntology":null},{"paper":"/paper/unnatural-language-inference","slug":"unnatural-language-inference","title":"UnNatural Language Inference","date":"2020-12-30","arxiv_id":"2101.00010","n_code_links":1,"syntology":null},{"paper":"/paper/reinforcement-learning-for-control-of-valves","slug":"reinforcement-learning-for-control-of-valves","title":"Reinforcement Learning for Control of Valves","date":"2020-12-29","arxiv_id":"2012.14668","n_code_links":2,"syntology":null},{"paper":"/paper/robust-dialogue-utterance-rewriting-as","slug":"robust-dialogue-utterance-rewriting-as","title":"Robust Dialogue Utterance Rewriting as Sequence Tagging","date":"2020-12-29","arxiv_id":"2012.14535","n_code_links":1,"syntology":null},{"paper":"/paper/a-paragraph-level-multi-task-learning-model","slug":"a-paragraph-level-multi-task-learning-model","title":"A Paragraph-level Multi-task Learning Model for Scientific Fact-Verification","date":"2020-12-28","arxiv_id":"2012.14500","n_code_links":1,"syntology":null},{"paper":null,"slug":"burt-bert-inspired-universal-representation-1","title":"BURT: BERT-inspired Universal Representation from Learning Meaningful Segment","date":"2020-12-28","arxiv_id":"2012.14320","n_code_links":0,"syntology":null},{"paper":"/paper/syntax-enhanced-pre-trained-model","slug":"syntax-enhanced-pre-trained-model","title":"Syntax-Enhanced Pre-trained Model","date":"2020-12-28","arxiv_id":"2012.14116","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-task-learning-network-using-shared","title":"A multi-task learning network using shared BERT models for aspect-based sentiment analysis","date":"2020-12-27","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"alp-kd-attention-based-layer-projection-for","title":"ALP-KD: Attention-Based Layer Projection for Knowledge Distillation","date":"2020-12-27","arxiv_id":"2012.14022","n_code_links":0,"syntology":null},{"paper":"/paper/an-embarrassingly-simple-model-for-dialogue","slug":"an-embarrassingly-simple-model-for-dialogue","title":"An Embarrassingly Simple Model for Dialogue Relation Extraction","date":"2020-12-27","arxiv_id":"2012.13873","n_code_links":1,"syntology":null},{"paper":"/paper/inserting-information-bottlenecks-for","slug":"inserting-information-bottlenecks-for","title":"Inserting Information Bottlenecks for Attribution in Transformers","date":"2020-12-27","arxiv_id":"2012.13838","n_code_links":1,"syntology":null},{"paper":"/paper/medal-medical-abbreviation-disambiguation","slug":"medal-medical-abbreviation-disambiguation","title":"MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining","date":"2020-12-27","arxiv_id":"2012.13978","n_code_links":1,"syntology":null},{"paper":"/paper/sentence-based-model-agnostic-nlp","slug":"sentence-based-model-agnostic-nlp","title":"On the Granularity of Explanations in Model Agnostic NLP Interpretability","date":"2020-12-24","arxiv_id":"2012.13189","n_code_links":1,"syntology":null},{"paper":null,"slug":"to-what-extent-do-human-explanations-of-model","title":"To what extent do human explanations of model behavior align with actual model behavior?","date":"2020-12-24","arxiv_id":"2012.13354","n_code_links":0,"syntology":null},{"paper":"/paper/bridging-textual-and-tabular-data-for-cross","slug":"bridging-textual-and-tabular-data-for-cross","title":"Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing","date":"2020-12-23","arxiv_id":"2012.12627","n_code_links":2,"syntology":null},{"paper":"/paper/detecting-hate-speech-in-memes-using","slug":"detecting-hate-speech-in-memes-using","title":"Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge","date":"2020-12-23","arxiv_id":"2012.12975","n_code_links":1,"syntology":null},{"paper":"/paper/training-data-efficient-image-transformers","slug":"training-data-efficient-image-transformers","title":"Training data-efficient image transformers & distillation through attention","date":"2020-12-23","arxiv_id":"2012.12877","n_code_links":40,"syntology":{"ran":12,"of":19,"n_ran_checked":9,"n_instrument":3,"unverified":7,"pointer_only":3,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","official":{"repos":["facebookresearch/deit"],"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":"applying-wav2vec2-0-to-speech-recognition-in","title":"Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages","date":"2020-12-22","arxiv_id":"2012.12121","n_code_links":0,"syntology":null},{"paper":"/paper/improved-biomedical-word-embeddings-in-the","slug":"improved-biomedical-word-embeddings-in-the","title":"Improved Biomedical Word Embeddings in the Transformer Era","date":"2020-12-22","arxiv_id":"2012.11808","n_code_links":1,"syntology":null},{"paper":"/paper/intrinsic-dimensionality-explains-the","slug":"intrinsic-dimensionality-explains-the","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","date":"2020-12-22","arxiv_id":"2012.13255","n_code_links":2,"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":["rabeehk/compacter"],"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/learning-to-retrieve-entity-aware-knowledge","slug":"learning-to-retrieve-entity-aware-knowledge","title":"Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems","date":"2020-12-22","arxiv_id":"2012.11937","n_code_links":1,"syntology":null},{"paper":"/paper/recognizing-emotion-cause-in-conversations-1","slug":"recognizing-emotion-cause-in-conversations-1","title":"Recognizing Emotion Cause in Conversations","date":"2020-12-22","arxiv_id":"2012.11820","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncertainty-and-surprisal-jointly-deliver-the","title":"Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition","date":"2020-12-22","arxiv_id":"2012.12007","n_code_links":0,"syntology":null},{"paper":null,"slug":"2012-11643","title":"myGym: Modular Toolkit for Visuomotor Robotic Tasks","date":"2020-12-21","arxiv_id":"2012.11643","n_code_links":0,"syntology":null},{"paper":"/paper/cross-domain-retrieval-in-the-legal-and","slug":"cross-domain-retrieval-in-the-legal-and","title":"Cross-domain Retrieval in the Legal and Patent Domains: a Reproducibility Study","date":"2020-12-21","arxiv_id":"2012.11405","n_code_links":1,"syntology":null},{"paper":"/paper/domain-specific-bert-representation-for-named","slug":"domain-specific-bert-representation-for-named","title":"Domain specific BERT representation for Named Entity Recognition of lab protocol","date":"2020-12-21","arxiv_id":"2012.11145","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-parsbert-and-pretrained-mt5-for","slug":"leveraging-parsbert-and-pretrained-mt5-for","title":"Leveraging ParsBERT and Pretrained mT5 for Persian Abstractive Text Summarization","date":"2020-12-21","arxiv_id":"2012.11204","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-incorporating-entity-specific","title":"Towards Incorporating Entity-specific Knowledge Graph Information in Predicting Drug-Drug Interactions","date":"2020-12-21","arxiv_id":"2012.11142","n_code_links":0,"syntology":null},{"paper":null,"slug":"controllable-and-contextualised-writing-tool","title":"Breaking Writer's Block: Low-cost Fine-tuning of Natural Language Generation Models","date":"2020-12-19","arxiv_id":"2101.03216","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-of-using-pre-trained-bert","slug":"an-empirical-study-of-using-pre-trained-bert","title":"An Empirical Study of Using Pre-trained BERT Models for Vietnamese Relation Extraction Task at VLSP 2020","date":"2020-12-18","arxiv_id":"2012.10275","n_code_links":1,"syntology":null},{"paper":"/paper/hatexplain-a-benchmark-dataset-for","slug":"hatexplain-a-benchmark-dataset-for","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","date":"2020-12-18","arxiv_id":"2012.10289","n_code_links":6,"syntology":null},{"paper":"/paper/on-modality-bias-in-the-tvqa-dataset","slug":"on-modality-bias-in-the-tvqa-dataset","title":"On Modality Bias in the TVQA Dataset","date":"2020-12-18","arxiv_id":"2012.10210","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-white-box-analysis-of-colbert","title":"A White Box Analysis of ColBERT","date":"2020-12-17","arxiv_id":"2012.09650","n_code_links":0,"syntology":null},{"paper":"/paper/bert-goes-shopping-comparing-distributional","slug":"bert-goes-shopping-comparing-distributional","title":"BERT Goes Shopping: Comparing Distributional Models for Product Representations","date":"2020-12-17","arxiv_id":"2012.09807","n_code_links":1,"syntology":null},{"paper":"/paper/literature-retrieval-for-precision-medicine","slug":"literature-retrieval-for-precision-medicine","title":"Literature Retrieval for Precision Medicine with Neural Matching and Faceted Summarization","date":"2020-12-17","arxiv_id":"2012.09355","n_code_links":1,"syntology":null},{"paper":"/paper/masker-masked-keyword-regularization-for","slug":"masker-masked-keyword-regularization-for","title":"MASKER: Masked Keyword Regularization for Reliable Text Classification","date":"2020-12-17","arxiv_id":"2012.09392","n_code_links":1,"syntology":null},{"paper":null,"slug":"mix-a-multi-task-learning-approach-to-solve","title":"MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering","date":"2020-12-17","arxiv_id":"2012.09766","n_code_links":0,"syntology":null},{"paper":"/paper/sceneformer-indoor-scene-generation-with","slug":"sceneformer-indoor-scene-generation-with","title":"SceneFormer: Indoor Scene Generation with Transformers","date":"2020-12-17","arxiv_id":"2012.09793","n_code_links":2,"syntology":null},{"paper":"/paper/a-lightweight-neural-model-for-biomedical","slug":"a-lightweight-neural-model-for-biomedical","title":"A Lightweight Neural Model for Biomedical Entity Linking","date":"2020-12-16","arxiv_id":"2012.08844","n_code_links":1,"syntology":null},{"paper":null,"slug":"focusing-more-on-conflicts-with-mis","title":"Learning from Mistakes: Using Mis-predictions as Harm Alerts in Language Pre-Training","date":"2020-12-16","arxiv_id":"2012.08789","n_code_links":0,"syntology":null},{"paper":null,"slug":"query-expansion-with-artificially-generated","title":"Query expansion with artificially generated texts","date":"2020-12-16","arxiv_id":"2012.08787","n_code_links":0,"syntology":null},{"paper":null,"slug":"r-2-net-relation-of-relation-learning-network","title":"R$^2$-Net: Relation of Relation Learning Network for Sentence Semantic Matching","date":"2020-12-16","arxiv_id":"2012.08920","n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-linformer-with-a-modified-self","title":"Revisiting Linformer with a modified self-attention with linear complexity","date":"2020-12-16","arxiv_id":"2101.10277","n_code_links":0,"syntology":null},{"paper":"/paper/pre-training-transformers-as-energy-based-1","slug":"pre-training-transformers-as-energy-based-1","title":"Pre-Training Transformers as Energy-Based Cloze Models","date":"2020-12-15","arxiv_id":"2012.08561","n_code_links":1,"syntology":null},{"paper":"/paper/recipenlg-a-cooking-recipes-dataset-for-semi","slug":"recipenlg-a-cooking-recipes-dataset-for-semi","title":"RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation","date":"2020-12-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/extracting-training-data-from-large-language","slug":"extracting-training-data-from-large-language","title":"Extracting Training Data from Large Language Models","date":"2020-12-14","arxiv_id":"2012.07805","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ftramer/LM_Memorization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lrc-bert-latent-representation-contrastive","title":"LRC-BERT: Latent-representation Contrastive Knowledge Distillation for Natural Language Understanding","date":"2020-12-14","arxiv_id":"2012.07335","n_code_links":0,"syntology":null},{"paper":null,"slug":"policy-gradient-for-items-recommendation-on","title":"Policy Gradient for items Recommendation on Virtual Taobao","date":"2020-12-14","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/policy-gradient-rl-algorithms-as-directed","slug":"policy-gradient-rl-algorithms-as-directed","title":"Policy Gradient RL Algorithms as Directed Acyclic Graphs","date":"2020-12-14","arxiv_id":"2012.07763","n_code_links":1,"syntology":null},{"paper":null,"slug":"vartani-spellcheck-automatic-context","title":"Vartani Spellcheck -- Automatic Context-Sensitive Spelling Correction of OCR-generated Hindi Text Using BERT and Levenshtein Distance","date":"2020-12-14","arxiv_id":"2012.07652","n_code_links":0,"syntology":null},{"paper":null,"slug":"virtual-autonomous-driving-with-reinforcement","title":"Virtual Autonomous Driving with Reinforcement Learning","date":"2020-12-14","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"discriminative-pre-training-for-low-resource","title":"Discriminative Pre-training for Low Resource Title Compression in Conversational Grocery","date":"2020-12-13","arxiv_id":"2012.06943","n_code_links":0,"syntology":null},{"paper":"/paper/kvl-bert-knowledge-enhanced-visual-and","slug":"kvl-bert-knowledge-enhanced-visual-and","title":"KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense Reasoning","date":"2020-12-13","arxiv_id":"2012.07000","n_code_links":0,"syntology":null},{"paper":null,"slug":"minivlm-a-smaller-and-faster-vision-language","title":"MiniVLM: A Smaller and Faster Vision-Language Model","date":"2020-12-13","arxiv_id":"2012.06946","n_code_links":0,"syntology":null},{"paper":"/paper/cogalex-vi-shared-task-transrelation-a-robust","slug":"cogalex-vi-shared-task-transrelation-a-robust","title":"CogALex-VI Shared Task: Transrelation - A Robust Multilingual Language Model for Multilingual Relation Identification","date":"2020-12-12","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/yelp-review-rating-prediction-machine","slug":"yelp-review-rating-prediction-machine","title":"Yelp Review Rating Prediction: Machine Learning and Deep Learning Models","date":"2020-12-12","arxiv_id":"2012.06690","n_code_links":1,"syntology":null},{"paper":"/paper/avoiding-the-double-descent-phenomenon-of","slug":"avoiding-the-double-descent-phenomenon-of","title":"Avoiding The Double Descent Phenomenon of Random Feature Models Using Hybrid Regularization","date":"2020-12-11","arxiv_id":"2012.06667","n_code_links":1,"syntology":null},{"paper":null,"slug":"hardware-beyond-backpropagation-a-photonic-co","title":"Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignment","date":"2020-12-11","arxiv_id":"2012.06373","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-task-agnostic-bert-distillation","title":"Improving Task-Agnostic BERT Distillation with Layer Mapping Search","date":"2020-12-11","arxiv_id":"2012.06153","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-practical-approach-towards-causality-mining","title":"A Practical Approach towards Causality Mining in Clinical Text using Active Transfer Learning","date":"2020-12-10","arxiv_id":"2012.07563","n_code_links":0,"syntology":null},{"paper":"/paper/as-good-as-new-how-to-successfully-recycle","slug":"as-good-as-new-how-to-successfully-recycle","title":"As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages","date":"2020-12-10","arxiv_id":"2012.05628","n_code_links":1,"syntology":null},{"paper":"/paper/towards-neural-programming-interfaces-1","slug":"towards-neural-programming-interfaces-1","title":"Towards Neural Programming Interfaces","date":"2020-12-10","arxiv_id":"2012.05983","n_code_links":1,"syntology":null},{"paper":null,"slug":"convex-regularization-behind-neural-1","title":"Convex Regularization Behind Neural Reconstruction","date":"2020-12-09","arxiv_id":"2012.05169","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-word-sense-disambiguation-using","title":"Cross-lingual Word Sense Disambiguation using mBERT Embeddings with Syntactic Dependencies","date":"2020-12-09","arxiv_id":"2012.05300","n_code_links":0,"syntology":null},{"paper":"/paper/mapping-the-space-of-chemical-reactions-using","slug":"mapping-the-space-of-chemical-reactions-using","title":"Mapping the Space of Chemical Reactions Using Attention-Based Neural Networks","date":"2020-12-09","arxiv_id":"2012.06051","n_code_links":1,"syntology":null},{"paper":null,"slug":"discourse-parsing-of-contentious-non","title":"Discourse Parsing of Contentious, Non-Convergent Online Discussions","date":"2020-12-08","arxiv_id":"2012.04585","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-mass-media-shape-public-opinion-toward","title":"Large-scale Quantitative Evidence of Media Impact on Public Opinion toward China","date":"2020-12-08","arxiv_id":"2012.07575","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-estimation-of-influence-of-a","title":"Efficient Estimation of Influence of a Training Instance","date":"2020-12-08","arxiv_id":"2012.04207","n_code_links":0,"syntology":null},{"paper":"/paper/from-bag-of-sentences-to-document-distantly","slug":"from-bag-of-sentences-to-document-distantly","title":"From Bag of Sentences to Document: Distantly Supervised Relation Extraction via Machine Reading Comprehension","date":"2020-12-08","arxiv_id":"2012.04334","n_code_links":1,"syntology":null},{"paper":"/paper/tado-time-varying-attention-with-dual","slug":"tado-time-varying-attention-with-dual","title":"TADO: Time-varying Attention with Dual-Optimizer Model","date":"2020-12-08","arxiv_id":"2012.04558","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-empirical-survey-of-unsupervised-text","title":"An Empirical Survey of Unsupervised Text Representation Methods on Twitter Data","date":"2020-12-07","arxiv_id":"2012.03468","n_code_links":0,"syntology":null},{"paper":"/paper/cx-db8-a-queryable-extractive-summarizer-and","slug":"cx-db8-a-queryable-extractive-summarizer-and","title":"CX DB8: A queryable extractive summarizer and semantic search engine","date":"2020-12-07","arxiv_id":"2012.03942","n_code_links":2,"syntology":null},{"paper":null,"slug":"dartmouth-cs-at-wnut-2020-task-2-informative","title":"Dartmouth CS at WNUT-2020 Task 2: Informative COVID-19 Tweet Classification Using BERT","date":"2020-12-07","arxiv_id":"2012.04539","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-insincere-questions-from-text-a","slug":"detecting-insincere-questions-from-text-a","title":"Detecting Insincere Questions from Text: A Transfer Learning Approach","date":"2020-12-07","arxiv_id":"2012.07587","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-reservoir-management-through-deep","title":"Efficient Reservoir Management through Deep Reinforcement Learning","date":"2020-12-07","arxiv_id":"2012.03822","n_code_links":0,"syntology":null},{"paper":null,"slug":"kgplm-knowledge-guided-language-model-pre","title":"KgPLM: Knowledge-guided Language Model Pre-training via Generative and Discriminative Learning","date":"2020-12-07","arxiv_id":"2012.03551","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-role-of-regularization-in-shaping-weight","title":"The Role of Regularization in Shaping Weight and Node Pruning Dependency and Dynamics","date":"2020-12-07","arxiv_id":"2012.03827","n_code_links":0,"syntology":null},{"paper":"/paper/ubar-towards-fully-end-to-end-task-oriented","slug":"ubar-towards-fully-end-to-end-task-oriented","title":"UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2","date":"2020-12-07","arxiv_id":"2012.03539","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhanced-offensive-language-detection-through","title":"Enhanced Offensive Language Detection Through Data Augmentation","date":"2020-12-05","arxiv_id":"2012.02954","n_code_links":0,"syntology":null},{"paper":"/paper/pre-training-protein-language-models-with","slug":"pre-training-protein-language-models-with","title":"Pre-training Protein Language Models with Label-Agnostic Binding Pairs Enhances Performance in Downstream Tasks","date":"2020-12-05","arxiv_id":"2012.03084","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-detection-of-cyberbullying-against","title":"Automated Detection of Cyberbullying Against Women and Immigrants and Cross-domain Adaptability","date":"2020-12-04","arxiv_id":"2012.02565","n_code_links":0,"syntology":null},{"paper":"/paper/echobert-a-transformer-based-approach-for","slug":"echobert-a-transformer-based-approach-for","title":"EchoBERT: A Transformer-Based Approach for Behavior Detection in Echograms","date":"2020-12-04","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-bert-for-low-resource-natural","title":"Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning","date":"2020-12-04","arxiv_id":"2012.02462","n_code_links":0,"syntology":null},{"paper":null,"slug":"modelling-general-properties-of-nouns-by","title":"Modelling General Properties of Nouns by Selectively Averaging Contextualised Embeddings","date":"2020-12-04","arxiv_id":"2012.07580","n_code_links":0,"syntology":null},{"paper":null,"slug":"playing-text-based-games-with-common-sense","title":"Playing Text-Based Games with Common Sense","date":"2020-12-04","arxiv_id":"2012.02757","n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-trained-language-models-as-knowledge","title":"Pre-trained language models as knowledge bases for Automotive Complaint Analysis","date":"2020-12-04","arxiv_id":"2012.02558","n_code_links":0,"syntology":null},{"paper":null,"slug":"relational-pretrained-transformers-towards","title":"RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation","date":"2020-12-04","arxiv_id":"2012.02469","n_code_links":0,"syntology":null}],"record_sha256":"c770ae59210ff8b5f63a65b04d24fe1d1696128fb94df8ca16b9939887c8a127","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}