{"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/73","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":73,"pages_in_order":108,"rows_per_page":100,"rows":[7201,7300],"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/72","next":"/method/weight-decay/papers/74","papers":[{"paper":null,"slug":"pruning-attention-heads-of-transformer-models","title":"Pruning Attention Heads of Transformer Models Using A* Search: A Novel Approach to Compress Big NLP Architectures","date":"2021-10-28","arxiv_id":"2110.15225","n_code_links":0,"syntology":null},{"paper":"/paper/semi-siamese-bi-encoder-neural-ranking-model","slug":"semi-siamese-bi-encoder-neural-ranking-model","title":"Semi-Siamese Bi-encoder Neural Ranking Model Using Lightweight Fine-Tuning","date":"2021-10-28","arxiv_id":"2110.14943","n_code_links":1,"syntology":null},{"paper":null,"slug":"anomaly-injected-deep-support-vector-data","title":"Anomaly-Injected Deep Support Vector Data Description for Text Outlier Detection","date":"2021-10-27","arxiv_id":"2110.14729","n_code_links":0,"syntology":null},{"paper":null,"slug":"automating-control-of-overestimation-bias-for","title":"Automating Control of Overestimation Bias for Reinforcement Learning","date":"2021-10-26","arxiv_id":"2110.13523","n_code_links":0,"syntology":null},{"paper":null,"slug":"clauserec-a-clause-recommendation-framework","title":"CLAUSEREC: A Clause Recommendation Framework for AI-aided Contract Authoring","date":"2021-10-26","arxiv_id":"2110.15794","n_code_links":0,"syntology":null},{"paper":"/paper/post-processing-for-individual-fairness","slug":"post-processing-for-individual-fairness","title":"Post-processing for Individual Fairness","date":"2021-10-26","arxiv_id":"2110.13796","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"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":["felix-petersen/fairness-post-processing"],"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/s2s-ft-fine-tuning-pretrained-transformer","slug":"s2s-ft-fine-tuning-pretrained-transformer","title":"s2s-ft: Fine-Tuning Pretrained Transformer Encoders for Sequence-to-Sequence Learning","date":"2021-10-26","arxiv_id":"2110.13640","n_code_links":1,"syntology":null},{"paper":"/paper/tribert-full-body-human-centric-audio-visual","slug":"tribert-full-body-human-centric-audio-visual","title":"TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation","date":"2021-10-26","arxiv_id":"2110.13412","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["ubc-vision/tribert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/fine-tuning-of-pre-trained-transformers-for","slug":"fine-tuning-of-pre-trained-transformers-for","title":"Fine-tuning of Pre-trained Transformers for Hate, Offensive, and Profane Content Detection in English and Marathi","date":"2021-10-25","arxiv_id":"2110.12687","n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-artificial-texts-as-substitution","title":"Generating artificial texts as substitution or complement of training data","date":"2021-10-25","arxiv_id":"2110.13016","n_code_links":0,"syntology":null},{"paper":"/paper/recurrent-off-policy-baselines-for-memory","slug":"recurrent-off-policy-baselines-for-memory","title":"Recurrent Off-policy Baselines for Memory-based Continuous Control","date":"2021-10-25","arxiv_id":"2110.12628","n_code_links":1,"syntology":null},{"paper":null,"slug":"revisiting-cnn-for-highly-inflected-bengali","title":"Paradigm Shift in Language Modeling: Revisiting CNN for Modeling Sanskrit Originated Bengali and Hindi Language","date":"2021-10-25","arxiv_id":"2110.13032","n_code_links":0,"syntology":null},{"paper":null,"slug":"hate-and-offensive-speech-detection-in-hindi","title":"Hate and Offensive Speech Detection in Hindi and Marathi","date":"2021-10-23","arxiv_id":"2110.12200","n_code_links":0,"syntology":null},{"paper":"/paper/double-trouble-how-to-not-explain-a-text","slug":"double-trouble-how-to-not-explain-a-text","title":"Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?","date":"2021-10-22","arxiv_id":"2110.11929","n_code_links":1,"syntology":null},{"paper":"/paper/learning-text-image-joint-embedding-for","slug":"learning-text-image-joint-embedding-for","title":"Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering","date":"2021-10-22","arxiv_id":"2110.11592","n_code_links":1,"syntology":null},{"paper":"/paper/cloob-modern-hopfield-networks-with-infoloob-1","slug":"cloob-modern-hopfield-networks-with-infoloob-1","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","date":"2021-10-21","arxiv_id":"2110.11316","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":1,"n_instrument":6,"unverified":4,"pointer_only":4,"phrase":"7 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; 6 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ml-jku/cloob"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","official"]}}},{"paper":"/paper/fast-model-editing-at-scale-1","slug":"fast-model-editing-at-scale-1","title":"Fast Model Editing at Scale","date":"2021-10-21","arxiv_id":"2110.11309","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["eric-mitchell/mend"],"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":null,"slug":"modeling-performance-in-open-domain-dialogue","title":"Modeling Performance in Open-Domain Dialogue with PARADISE","date":"2021-10-21","arxiv_id":"2110.11164","n_code_links":0,"syntology":null},{"paper":null,"slug":"computationally-efficient-safe-reinforcement","title":"Computationally Efficient Safe Reinforcement Learning for Power Systems","date":"2021-10-20","arxiv_id":"2110.10333","n_code_links":0,"syntology":null},{"paper":"/paper/distributionally-robust-classifiers-in","slug":"distributionally-robust-classifiers-in","title":"Distributionally Robust Classifiers in Sentiment Analysis","date":"2021-10-20","arxiv_id":"2110.10372","n_code_links":1,"syntology":null},{"paper":null,"slug":"slam-a-unified-encoder-for-speech-and","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","date":"2021-10-20","arxiv_id":"2110.10329","n_code_links":0,"syntology":null},{"paper":"/paper/ensemble-albert-on-squad-2-0","slug":"ensemble-albert-on-squad-2-0","title":"Ensemble ALBERT on SQuAD 2.0","date":"2021-10-19","arxiv_id":"2110.09665","n_code_links":1,"syntology":null},{"paper":null,"slug":"risks-of-ai-foundation-models-in-education","title":"Risks of AI Foundation Models in Education","date":"2021-10-19","arxiv_id":"2110.10024","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-data-bootstrapping-recipe-for-low-resource","title":"A Data Bootstrapping Recipe for Low Resource Multilingual Relation Classification","date":"2021-10-18","arxiv_id":"2110.09570","n_code_links":0,"syntology":null},{"paper":null,"slug":"bermo-what-can-bert-learn-from-elmo-1","title":"BERMo: What can BERT learn from ELMo?","date":"2021-10-18","arxiv_id":"2110.15802","n_code_links":0,"syntology":null},{"paper":null,"slug":"ceasing-hate-withmoh-hate-speech-detection-in","title":"Ceasing hate withMoH: Hate Speech Detection in Hindi-English Code-Switched Language","date":"2021-10-18","arxiv_id":"2110.09393","n_code_links":0,"syntology":null},{"paper":null,"slug":"contextual-hate-speech-detection-in-code","title":"Contextual Hate Speech Detection in Code Mixed Text using Transformer Based Approaches","date":"2021-10-18","arxiv_id":"2110.09338","n_code_links":0,"syntology":null},{"paper":null,"slug":"virapart-a-text-refinement-framework-for-asr","title":"ViraPart: A Text Refinement Framework for Automatic Speech Recognition and Natural Language Processing Tasks in Persian","date":"2021-10-18","arxiv_id":"2110.09086","n_code_links":0,"syntology":null},{"paper":"/paper/illiterate-dall-cdot-e-learns-to-compose-1","slug":"illiterate-dall-cdot-e-learns-to-compose-1","title":"Illiterate DALL-E Learns to Compose","date":"2021-10-17","arxiv_id":"2110.11405","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":["singhgautam/slate"],"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":"reminding-the-incremental-language-model-via","title":"Reminding the Incremental Language Model via Data-Free Self-Distillation","date":"2021-10-17","arxiv_id":"2110.08745","n_code_links":0,"syntology":null},{"paper":"/paper/taming-visually-guided-sound-generation","slug":"taming-visually-guided-sound-generation","title":"Taming Visually Guided Sound Generation","date":"2021-10-17","arxiv_id":"2110.08791","n_code_links":3,"syntology":{"ran":7,"of":7,"n_ran_checked":6,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["v-iashin/SpecVQGAN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"a-short-study-on-compressing-decoder-based","title":"A Short Study on Compressing Decoder-Based Language Models","date":"2021-10-16","arxiv_id":"2110.08460","n_code_links":0,"syntology":null},{"paper":null,"slug":"bitfit-simple-parameter-efficient-fine-tuning-1","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/enct5-fine-tuning-t5-encoder-for-non","slug":"enct5-fine-tuning-t5-encoder-for-non","title":"EncT5: A Framework for Fine-tuning T5 as Non-autoregressive Models","date":"2021-10-16","arxiv_id":"2110.08426","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-transfer-learning-for-polish","title":"Evaluation of Transfer Learning for Polish with a text-to-text model","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-transformer-networks-for-long","title":"Hierarchical Transformer Networks for Long-sequence and Multiple Clinical Documents Classification","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hydra-a-system-for-large-multi-model-deep","slug":"hydra-a-system-for-large-multi-model-deep","title":"Hydra: A System for Large Multi-Model Deep Learning","date":"2021-10-16","arxiv_id":"2110.08633","n_code_links":1,"syntology":null},{"paper":null,"slug":"impli-investigating-nli-models-performance-on","title":"IMPLI: Investigating NLI Models' Performance on Figurative Language","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-inheritance-for-pre-trained-1","title":"Knowledge Inheritance for Pre-trained Language Models","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"models-in-a-spelling-bee-language-models-1","title":"Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/old-bert-new-tricks-artificial-language-1","slug":"old-bert-new-tricks-artificial-language-1","title":"Old BERT, New Tricks: Artificial Language Learning for Pre-Trained Language Models","date":"2021-10-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-current-state-of-reproducibility-and","title":"On the current state of reproducibility and reporting of uncertainty for Aspect-based Sentiment Analysis","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/on-the-robustness-of-reading-comprehension","slug":"on-the-robustness-of-reading-comprehension","title":"On the Robustness of Reading Comprehension Models to Entity Renaming","date":"2021-10-16","arxiv_id":"2110.08555","n_code_links":1,"syntology":null},{"paper":null,"slug":"pagnol-an-extra-large-french-generative-model","title":"PAGnol: An Extra-Large French Generative Model","date":"2021-10-16","arxiv_id":"2110.08554","n_code_links":0,"syntology":null},{"paper":"/paper/primer-pyramid-based-masked-sentence-pre","slug":"primer-pyramid-based-masked-sentence-pre","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","date":"2021-10-16","arxiv_id":"2110.08499","n_code_links":3,"syntology":{"ran":7,"of":7,"n_ran_checked":4,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/primer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"semantic-search-as-extractive-paraphrase-span","title":"Semantic Search as Extractive Paraphrase Span Detection","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sharpness-aware-minimization-improves","title":"Sharpness-Aware Minimization Improves Language Model Generalization","date":"2021-10-16","arxiv_id":"2110.08529","n_code_links":0,"syntology":null},{"paper":null,"slug":"spellm-augmenting-chinese-spell-check-using","title":"SpelLM: Augmenting Chinese Spell Check Using Input Salience","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-power-of-prompt-tuning-for-low-resource","title":"The Power of Prompt Tuning for Low-Resource Semantic Parsing","date":"2021-10-16","arxiv_id":"2110.08525","n_code_links":0,"syntology":null},{"paper":null,"slug":"wechsel-effective-initialization-of-subword","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"what-do-compressed-large-language-models","title":"Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding","date":"2021-10-16","arxiv_id":"2110.08419","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-gender-bias-in-transformer-based","title":"Detecting Gender Bias in Transformer-based Models: A Case Study on BERT","date":"2021-10-15","arxiv_id":"2110.15733","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-faithfulness-of-importance","slug":"evaluating-the-faithfulness-of-importance","title":"Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining","date":"2021-10-15","arxiv_id":"2110.08412","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["AndreasMadsen/nlp-roar-interpretability"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generating-natural-language-adversarial-1","title":"Generating Natural Language Adversarial Examples through An Improved Beam Search Algorithm","date":"2021-10-15","arxiv_id":"2110.08036","n_code_links":0,"syntology":null},{"paper":null,"slug":"intent-based-product-collections-for-e","title":"Intent-based Product Collections for E-commerce using Pretrained Language Models","date":"2021-10-15","arxiv_id":"2110.08241","n_code_links":0,"syntology":null},{"paper":null,"slug":"kronecker-decomposition-for-gpt-compression","title":"Kronecker Decomposition for GPT Compression","date":"2021-10-15","arxiv_id":"2110.08152","n_code_links":0,"syntology":null},{"paper":"/paper/probing-as-quantifying-the-inductive-bias-of","slug":"probing-as-quantifying-the-inductive-bias-of","title":"Probing as Quantifying Inductive Bias","date":"2021-10-15","arxiv_id":"2110.08388","n_code_links":1,"syntology":null},{"paper":"/paper/tracing-origins-coref-aware-machine-reading","slug":"tracing-origins-coref-aware-machine-reading","title":"Tracing Origins: Coreference-aware Machine Reading Comprehension","date":"2021-10-15","arxiv_id":"2110.07961","n_code_links":1,"syntology":null},{"paper":"/paper/a-simple-strong-and-robust-baseline-for","slug":"a-simple-strong-and-robust-baseline-for","title":"PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation Extraction","date":"2021-10-14","arxiv_id":"2110.07415","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert2bert-towards-reusable-pretrained","title":"bert2BERT: Towards Reusable Pretrained Language Models","date":"2021-10-14","arxiv_id":"2110.07143","n_code_links":0,"syntology":null},{"paper":"/paper/bi-rads-bert-using-section-tokenization-to","slug":"bi-rads-bert-using-section-tokenization-to","title":"BI-RADS BERT & Using Section Segmentation to Understand Radiology Reports","date":"2021-10-14","arxiv_id":"2110.07552","n_code_links":1,"syntology":null},{"paper":"/paper/building-chinese-biomedical-language-models","slug":"building-chinese-biomedical-language-models","title":"Building Chinese Biomedical Language Models via Multi-Level Text Discrimination","date":"2021-10-14","arxiv_id":"2110.07244","n_code_links":1,"syntology":null},{"paper":null,"slug":"causally-estimating-the-sensitivity-of-neural-1","title":"Interpreting the Robustness of Neural NLP Models to Textual Perturbations","date":"2021-10-14","arxiv_id":"2110.07159","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-gloss-augmentation-for-improving-word","title":"Context-gloss Augmentation for Improving Word Sense Disambiguation","date":"2021-10-14","arxiv_id":"2110.07174","n_code_links":0,"syntology":null},{"paper":"/paper/delphi-towards-machine-ethics-and-norms","slug":"delphi-towards-machine-ethics-and-norms","title":"Can Machines Learn Morality? The Delphi Experiment","date":"2021-10-14","arxiv_id":"2110.07574","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-off-the-shelf-machine-listening","title":"Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning","date":"2021-10-14","arxiv_id":"2110.07410","n_code_links":0,"syntology":null},{"paper":"/paper/identifying-introductions-in-podcast-episodes","slug":"identifying-introductions-in-podcast-episodes","title":"Identifying Introductions in Podcast Episodes from Automatically Generated Transcripts","date":"2021-10-14","arxiv_id":"2110.07096","n_code_links":1,"syntology":null},{"paper":"/paper/p-adapters-robustly-extracting-factual-1","slug":"p-adapters-robustly-extracting-factual-1","title":"P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts","date":"2021-10-14","arxiv_id":"2110.07280","n_code_links":1,"syntology":null},{"paper":"/paper/symbolic-knowledge-distillation-from-general","slug":"symbolic-knowledge-distillation-from-general","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","date":"2021-10-14","arxiv_id":"2110.07178","n_code_links":1,"syntology":null},{"paper":null,"slug":"covert-message-passing-over-public-internet","title":"Leveraging Generative Models for Covert Messaging: Challenges and Tradeoffs for \"Dead-Drop\" Deployments","date":"2021-10-13","arxiv_id":"2110.07009","n_code_links":0,"syntology":null},{"paper":"/paper/fake-news-detection-in-spanish-using-deep","slug":"fake-news-detection-in-spanish-using-deep","title":"Fake News Detection in Spanish Using Deep Learning Techniques","date":"2021-10-13","arxiv_id":"2110.06461","n_code_links":1,"syntology":null},{"paper":"/paper/improving-graph-based-sentence-ordering-with","slug":"improving-graph-based-sentence-ordering-with","title":"Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings","date":"2021-10-13","arxiv_id":"2110.06446","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["deeplearnxmu/irseg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"language-modelling-via-learning-to-rank","title":"Language Modelling via Learning to Rank","date":"2021-10-13","arxiv_id":"2110.06961","n_code_links":0,"syntology":null},{"paper":null,"slug":"maximizing-efficiency-of-language-model-pre","title":"Maximizing Efficiency of Language Model Pre-training for Learning Representation","date":"2021-10-13","arxiv_id":"2110.06620","n_code_links":0,"syntology":null},{"paper":"/paper/mderank-a-masked-document-embedding-rank","slug":"mderank-a-masked-document-embedding-rank","title":"MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction","date":"2021-10-13","arxiv_id":"2110.06651","n_code_links":1,"syntology":null},{"paper":null,"slug":"multistage-linguistic-conditioning-of","title":"Multistage linguistic conditioning of convolutional layers for speech emotion recognition","date":"2021-10-13","arxiv_id":"2110.06650","n_code_links":0,"syntology":null},{"paper":null,"slug":"parallel-deep-neural-networks-have-zero-1","title":"Parallel Deep Neural Networks Have Zero Duality Gap","date":"2021-10-13","arxiv_id":"2110.06482","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-laws-for-the-few-shot-adaptation-of-1","title":"Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers","date":"2021-10-13","arxiv_id":"2110.06990","n_code_links":0,"syntology":null},{"paper":"/paper/towards-efficient-nlp-a-standard-evaluation","slug":"towards-efficient-nlp-a-standard-evaluation","title":"Towards Efficient NLP: A Standard Evaluation and A Strong Baseline","date":"2021-10-13","arxiv_id":"2110.07038","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-of-emotion-perception-from-art","title":"Understanding of Emotion Perception from Art","date":"2021-10-13","arxiv_id":"2110.06486","n_code_links":0,"syntology":null},{"paper":"/paper/yformer-u-net-inspired-transformer-1","slug":"yformer-u-net-inspired-transformer-1","title":"Yformer: U-Net Inspired Transformer Architecture for Far Horizon Time Series Forecasting","date":"2021-10-13","arxiv_id":"2110.08255","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-large-scale-lexical-and-semantic-analysis","title":"Regionalized models for Spanish language variations based on Twitter","date":"2021-10-12","arxiv_id":"2110.06128","n_code_links":0,"syntology":null},{"paper":null,"slug":"all-dolphins-are-intelligent-and-some-are","title":"ALL Dolphins Are Intelligent and SOME Are Friendly: Probing BERT for Nouns' Semantic Properties and their Prototypicality","date":"2021-10-12","arxiv_id":"2110.06376","n_code_links":0,"syntology":null},{"paper":"/paper/bertraffic-a-robust-bert-based-approach-for","slug":"bertraffic-a-robust-bert-based-approach-for","title":"BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications","date":"2021-10-12","arxiv_id":"2110.05781","n_code_links":2,"syntology":null},{"paper":"/paper/contrastive-learning-for-representation","slug":"contrastive-learning-for-representation","title":"Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation","date":"2021-10-12","arxiv_id":"2110.05730","n_code_links":2,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["RuihongQiu/DuoRec"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"extracting-feelings-of-people-regarding-covid","title":"Extracting Feelings of People Regarding COVID-19 by Social Network Mining","date":"2021-10-12","arxiv_id":"2110.06151","n_code_links":0,"syntology":null},{"paper":"/paper/lightseq-accelerated-training-for-transformer","slug":"lightseq-accelerated-training-for-transformer","title":"LightSeq2: Accelerated Training for Transformer-based Models on GPUs","date":"2021-10-12","arxiv_id":"2110.05722","n_code_links":1,"syntology":null},{"paper":"/paper/list-lite-self-training-makes-efficient-few-1","slug":"list-lite-self-training-makes-efficient-few-1","title":"LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners","date":"2021-10-12","arxiv_id":"2110.06274","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":7,"n_instrument":2,"unverified":3,"pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["microsoft/list"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"global-optimality-beyond-two-layers-training","title":"Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs","date":"2021-10-11","arxiv_id":"2110.05518","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-gender-fairness-of-pre-trained-1","title":"Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting","date":"2021-10-11","arxiv_id":"2110.05367","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-learning-for-situated-multi-domain","title":"Multi-Task Learning for Situated Multi-Domain End-to-End Dialogue Systems","date":"2021-10-11","arxiv_id":"2110.05221","n_code_links":0,"syntology":null},{"paper":null,"slug":"offensive-language-detection-with-bert-based","title":"Offensive Language Detection with BERT-based models, By Customizing Attention Probabilities","date":"2021-10-11","arxiv_id":"2110.05133","n_code_links":0,"syntology":null},{"paper":"/paper/topic-modeling-clade-assisted-sentiment","slug":"topic-modeling-clade-assisted-sentiment","title":"Topic Modeling, Clade-assisted Sentiment Analysis, and Vaccine Brand Reputation Analysis of COVID-19 Vaccine-related Facebook Comments in the Philippines","date":"2021-10-11","arxiv_id":"2111.04416","n_code_links":1,"syntology":null},{"paper":"/paper/towards-demystifying-representation-learning-1","slug":"towards-demystifying-representation-learning-1","title":"Towards Demystifying Representation Learning with Non-contrastive Self-supervision","date":"2021-10-11","arxiv_id":"2110.04947","n_code_links":2,"syntology":null},{"paper":"/paper/paste-a-tagging-free-decoding-framework-using","slug":"paste-a-tagging-free-decoding-framework-using","title":"PASTE: A Tagging-Free Decoding Framework Using Pointer Networks for Aspect Sentiment Triplet Extraction","date":"2021-10-10","arxiv_id":"2110.04794","n_code_links":1,"syntology":null},{"paper":"/paper/yuan-1-0-large-scale-pre-trained-language","slug":"yuan-1-0-large-scale-pre-trained-language","title":"Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning","date":"2021-10-10","arxiv_id":"2110.04725","n_code_links":1,"syntology":null},{"paper":"/paper/an-isotropy-analysis-in-the-multilingual-bert","slug":"an-isotropy-analysis-in-the-multilingual-bert","title":"An Isotropy Analysis in the Multilingual BERT Embedding Space","date":"2021-10-09","arxiv_id":"2110.04504","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-recent-advances-in-pre-trained","slug":"leveraging-recent-advances-in-pre-trained","title":"Leveraging recent advances in Pre-Trained Language Models forEye-Tracking Prediction","date":"2021-10-09","arxiv_id":"2110.04475","n_code_links":1,"syntology":null},{"paper":"/paper/pairwise-margin-maximization-for-deep-neural","slug":"pairwise-margin-maximization-for-deep-neural","title":"Pairwise Margin Maximization for Deep Neural Networks","date":"2021-10-09","arxiv_id":"2110.04519","n_code_links":1,"syntology":null},{"paper":"/paper/vector-quantized-image-modeling-with-improved-1","slug":"vector-quantized-image-modeling-with-improved-1","title":"Vector-quantized Image Modeling with Improved VQGAN","date":"2021-10-09","arxiv_id":"2110.04627","n_code_links":5,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}}],"record_sha256":"047801145f2fb88ae4a48d9b68a26a822baa0a4d1ccf110bc2f48fc1426ce514","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}