{"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/32","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":32,"pages_in_order":71,"rows_per_page":100,"rows":[3101,3200],"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/31","next":"/method/linear-warmup-with-linear-decay/papers/33","papers":[{"paper":"/paper/pac-man-multi-relation-network-in-social","slug":"pac-man-multi-relation-network-in-social","title":"PAC-MAN: Multi-Relation Network in Social Community for Personalized Hashtag Recommendation","date":"2022-12-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/a-pre-trained-bert-model-for-android","slug":"a-pre-trained-bert-model-for-android","title":"DexBERT: Effective, Task-Agnostic and Fine-grained Representation Learning of Android Bytecode","date":"2022-12-12","arxiv_id":"2212.05976","n_code_links":1,"syntology":null},{"paper":"/paper/classifying-the-ideological-orientation-of","slug":"classifying-the-ideological-orientation-of","title":"Classifying the Ideological Orientation of User-Submitted Texts in Social Media","date":"2022-12-12","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/punctuation-restoration-for-singaporean","slug":"punctuation-restoration-for-singaporean","title":"Punctuation Restoration for Singaporean Spoken Languages: English, Malay, and Mandarin","date":"2022-12-10","arxiv_id":"2212.05356","n_code_links":1,"syntology":null},{"paper":"/paper/incorporating-emotions-into-health-mention","slug":"incorporating-emotions-into-health-mention","title":"Incorporating Emotions into Health Mention Classification Task on Social Media","date":"2022-12-09","arxiv_id":"2212.05039","n_code_links":1,"syntology":null},{"paper":"/paper/explain-to-me-like-i-am-five-sentence","slug":"explain-to-me-like-i-am-five-sentence","title":"Explain to me like I am five -- Sentence Simplification Using Transformers","date":"2022-12-08","arxiv_id":"2212.04595","n_code_links":1,"syntology":null},{"paper":"/paper/a-study-on-extracting-named-entities-from","slug":"a-study-on-extracting-named-entities-from","title":"Memorization of Named Entities in Fine-tuned BERT Models","date":"2022-12-07","arxiv_id":"2212.03749","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-embed-adopting-transformer-based","title":"Learning-To-Embed: Adopting Transformer based models for E-commerce Products Representation Learning","date":"2022-12-07","arxiv_id":"2212.03725","n_code_links":0,"syntology":null},{"paper":"/paper/simvtp-simple-video-text-pre-training-with","slug":"simvtp-simple-video-text-pre-training-with","title":"SimVTP: Simple Video Text Pre-training with Masked Autoencoders","date":"2022-12-07","arxiv_id":"2212.03490","n_code_links":0,"syntology":null},{"paper":null,"slug":"tweetdrought-a-deep-learning-drought-impacts","title":"TweetDrought: A Deep-Learning Drought Impacts Recognizer based on Twitter Data","date":"2022-12-07","arxiv_id":"2212.04001","n_code_links":0,"syntology":null},{"paper":null,"slug":"cysecbert-a-domain-adapted-language-model-for","title":"CySecBERT: A Domain-Adapted Language Model for the Cybersecurity Domain","date":"2022-12-06","arxiv_id":"2212.02974","n_code_links":0,"syntology":null},{"paper":null,"slug":"enabling-and-accelerating-dynamic-vision","title":"Vision Transformer Computation and Resilience for Dynamic Inference","date":"2022-12-06","arxiv_id":"2212.02687","n_code_links":0,"syntology":null},{"paper":"/paper/luna-language-understanding-with-number","slug":"luna-language-understanding-with-number","title":"LUNA: Language Understanding with Number Augmentations on Transformers via Number Plugins and Pre-training","date":"2022-12-06","arxiv_id":"2212.02691","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zmy/luna"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"modern-french-poetry-generation-with-roberta","title":"Modern French Poetry Generation with RoBERTa and GPT-2","date":"2022-12-06","arxiv_id":"2212.02911","n_code_links":0,"syntology":null},{"paper":null,"slug":"style-transfer-and-classification-in-hebrew","title":"Style transfer and classification in hebrew news items","date":"2022-12-06","arxiv_id":"2212.03019","n_code_links":0,"syntology":null},{"paper":"/paper/video-games-as-a-corpus-sentiment-analysis","slug":"video-games-as-a-corpus-sentiment-analysis","title":"Video Games as a Corpus: Sentiment Analysis using Fallout New Vegas Dialog","date":"2022-12-05","arxiv_id":"2212.02168","n_code_links":0,"syntology":null},{"paper":null,"slug":"cold-fusion-collaborative-descent-for","title":"ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning","date":"2022-12-02","arxiv_id":"2212.01378","n_code_links":0,"syntology":null},{"paper":"/paper/event-knowledge-in-large-language-models-the","slug":"event-knowledge-in-large-language-models-the","title":"Event knowledge in large language models: the gap between the impossible and the unlikely","date":"2022-12-02","arxiv_id":"2212.01488","n_code_links":1,"syntology":null},{"paper":null,"slug":"adapted-multimodal-bert-with-layer-wise","title":"Adapted Multimodal BERT with Layer-wise Fusion for Sentiment Analysis","date":"2022-12-01","arxiv_id":"2212.00678","n_code_links":0,"syntology":null},{"paper":null,"slug":"budgetlongformer-can-we-cheaply-pretrain-a","title":"BudgetLongformer: Can we Cheaply Pretrain a SotA Legal Language Model From Scratch?","date":"2022-11-30","arxiv_id":"2211.17135","n_code_links":0,"syntology":null},{"paper":"/paper/extremebert-a-toolkit-for-accelerating","slug":"extremebert-a-toolkit-for-accelerating","title":"ExtremeBERT: A Toolkit for Accelerating Pretraining of Customized BERT","date":"2022-11-30","arxiv_id":"2211.17201","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["extreme-bert/extreme-bert"],"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":"heat-hardware-efficient-automatic-tensor","title":"HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression","date":"2022-11-30","arxiv_id":"2211.16749","n_code_links":0,"syntology":null},{"paper":"/paper/composition-based-oxidation-state-prediction","slug":"composition-based-oxidation-state-prediction","title":"Composition based oxidation state prediction of materials using deep learning","date":"2022-11-29","arxiv_id":"2211.15895","n_code_links":1,"syntology":null},{"paper":null,"slug":"diverse-multi-answer-retrieval-with-1","title":"Diverse Multi-Answer Retrieval with Determinantal Point Processes","date":"2022-11-29","arxiv_id":"2211.16029","n_code_links":0,"syntology":null},{"paper":null,"slug":"outfit-generation-and-recommendation-an","title":"Outfit Generation and Recommendation -- An Experimental Study","date":"2022-11-29","arxiv_id":"2211.16353","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatically-extracting-information-in","title":"Automatically Extracting Information in Medical Dialogue: Expert System And Attention for Labelling","date":"2022-11-28","arxiv_id":"2211.15544","n_code_links":0,"syntology":null},{"paper":"/paper/diffusionbert-improving-generative-masked","slug":"diffusionbert-improving-generative-masked","title":"DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models","date":"2022-11-28","arxiv_id":"2211.15029","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["hzfinfdu/diffusion-bert"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"handling-and-extracting-key-entities-from","title":"Handling and extracting key entities from customer conversations using Speech recognition and Named Entity recognition","date":"2022-11-28","arxiv_id":"2211.17107","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-it-required-ranking-the-skills-required","title":"Is it Required? Ranking the Skills Required for a Job-Title","date":"2022-11-28","arxiv_id":"2212.08553","n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-distance-metric-learning-for-few","title":"Revisiting Distance Metric Learning for Few-Shot Natural Language Classification","date":"2022-11-28","arxiv_id":"2211.15202","n_code_links":0,"syntology":null},{"paper":"/paper/scientific-and-creative-analogies-in","slug":"scientific-and-creative-analogies-in","title":"Scientific and Creative Analogies in Pretrained Language Models","date":"2022-11-28","arxiv_id":"2211.15268","n_code_links":2,"syntology":null},{"paper":null,"slug":"awte-bert-attending-to-wordpiece-tokenization","title":"ESIE-BERT: Enriching Sub-words Information Explicitly with BERT for Joint Intent Classification and SlotFilling","date":"2022-11-27","arxiv_id":"2211.14829","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-bloom-an-empirical-study-on","title":"Understanding BLOOM: An empirical study on diverse NLP tasks","date":"2022-11-27","arxiv_id":"2211.14865","n_code_links":0,"syntology":null},{"paper":"/paper/an-analysis-of-social-biases-present-in-bert","slug":"an-analysis-of-social-biases-present-in-bert","title":"An Analysis of Social Biases Present in BERT Variants Across Multiple Languages","date":"2022-11-25","arxiv_id":"2211.14402","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["parishadbehnam/social-biases-in-bert-variants-across-multiple-languages"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/finetuning-bert-on-partially-annotated-ner","slug":"finetuning-bert-on-partially-annotated-ner","title":"Finetuning BERT on Partially Annotated NER Corpora","date":"2022-11-25","arxiv_id":"2211.14360","n_code_links":1,"syntology":null},{"paper":null,"slug":"index-indonesian-idiom-and-expression-dataset","title":"InDEX: Indonesian Idiom and Expression Dataset for Cloze Test","date":"2022-11-24","arxiv_id":"2211.13376","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-selective-masking-as-a-bridge-between","title":"Using Selective Masking as a Bridge between Pre-training and Fine-tuning","date":"2022-11-24","arxiv_id":"2211.13815","n_code_links":0,"syntology":null},{"paper":"/paper/improving-visual-textual-sentiment-analysis","slug":"improving-visual-textual-sentiment-analysis","title":"Holistic Visual-Textual Sentiment Analysis with Prior Models","date":"2022-11-23","arxiv_id":"2211.12981","n_code_links":1,"syntology":null},{"paper":null,"slug":"seat-stable-and-explainable-attention","title":"SEAT: Stable and Explainable Attention","date":"2022-11-23","arxiv_id":"2211.13290","n_code_links":0,"syntology":null},{"paper":null,"slug":"word-level-representation-from-bytes-for","title":"Word-Level Representation From Bytes For Language Modeling","date":"2022-11-23","arxiv_id":"2211.12677","n_code_links":0,"syntology":null},{"paper":null,"slug":"olga-an-ontology-and-lstm-based-approach-for","title":"OLGA : An Ontology and LSTM-based approach for generating Arithmetic Word Problems (AWPs) of transfer type","date":"2022-11-22","arxiv_id":"2211.12164","n_code_links":0,"syntology":null},{"paper":"/paper/cbeaf-adapting-enhanced-continual-pretraining","slug":"cbeaf-adapting-enhanced-continual-pretraining","title":"AF Adapter: Continual Pretraining for Building Chinese Biomedical Language Model","date":"2022-11-21","arxiv_id":"2211.11363","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-the-efficacy-of-pre-trained","slug":"exploring-the-efficacy-of-pre-trained","title":"Exploring the Efficacy of Pre-trained Checkpoints in Text-to-Music Generation Task","date":"2022-11-21","arxiv_id":"2211.11216","n_code_links":2,"syntology":null},{"paper":null,"slug":"l3cube-hindbert-and-devbert-pre-trained-bert","title":"L3Cube-HindBERT and DevBERT: Pre-Trained BERT Transformer models for Devanagari based Hindi and Marathi Languages","date":"2022-11-21","arxiv_id":"2211.11418","n_code_links":0,"syntology":null},{"paper":"/paper/l3cube-mahasbert-and-hindsbert-sentence-bert","slug":"l3cube-mahasbert-and-hindsbert-sentence-bert","title":"L3Cube-MahaSBERT and HindSBERT: Sentence BERT Models and Benchmarking BERT Sentence Representations for Hindi and Marathi","date":"2022-11-21","arxiv_id":"2211.11187","n_code_links":1,"syntology":null},{"paper":null,"slug":"tcbert-a-technical-report-for-chinese-topic","title":"TCBERT: A Technical Report for Chinese Topic Classification BERT","date":"2022-11-21","arxiv_id":"2211.11304","n_code_links":0,"syntology":null},{"paper":null,"slug":"conceptor-aided-debiasing-of-contextualized","title":"Conceptor-Aided Debiasing of Large Language Models","date":"2022-11-20","arxiv_id":"2211.11087","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-conspiracy-theory-against-covid-19","title":"Detecting Conspiracy Theory Against COVID-19 Vaccines","date":"2022-11-20","arxiv_id":"2211.13003","n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-weaken-vicinal-data-augmentation-for","title":"Feature Weaken: Vicinal Data Augmentation for Classification","date":"2022-11-20","arxiv_id":"2211.10944","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-and-improving-knowledge-1","slug":"understanding-and-improving-knowledge-1","title":"Understanding and Improving Knowledge Distillation for Quantization-Aware Training of Large Transformer Encoders","date":"2022-11-20","arxiv_id":"2211.11014","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-knowledge-enhanced-multimodal","title":"A survey on knowledge-enhanced multimodal learning","date":"2022-11-19","arxiv_id":"2211.12328","n_code_links":0,"syntology":null},{"paper":null,"slug":"entity-assisted-language-models-for","title":"Entity-Assisted Language Models for Identifying Check-worthy Sentences","date":"2022-11-19","arxiv_id":"2211.10678","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-users-social-network-embeddings","title":"Leveraging Users' Social Network Embeddings for Fake News Detection on Twitter","date":"2022-11-19","arxiv_id":"2211.10672","n_code_links":0,"syntology":null},{"paper":null,"slug":"metadata-might-make-language-models-better","title":"Metadata Might Make Language Models Better","date":"2022-11-18","arxiv_id":"2211.10086","n_code_links":0,"syntology":null},{"paper":null,"slug":"where-did-you-tweet-from-inferring-the-origin","title":"Where did you tweet from? Inferring the origin locations of tweets based on contextual information","date":"2022-11-18","arxiv_id":"2211.16506","n_code_links":0,"syntology":null},{"paper":null,"slug":"longfnt-long-form-speech-recognition-with","title":"LongFNT: Long-form Speech Recognition with Factorized Neural Transducer","date":"2022-11-17","arxiv_id":"2211.09412","n_code_links":0,"syntology":null},{"paper":"/paper/protsi-prototypical-siamese-network-with-data","slug":"protsi-prototypical-siamese-network-with-data","title":"ProtSi: Prototypical Siamese Network with Data Augmentation for Few-Shot Subjective Answer Evaluation","date":"2022-11-17","arxiv_id":"2211.09855","n_code_links":1,"syntology":null},{"paper":"/paper/random-ltd-random-and-layerwise-token","slug":"random-ltd-random-and-layerwise-token","title":"Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers","date":"2022-11-17","arxiv_id":"2211.11586","n_code_links":1,"syntology":null},{"paper":null,"slug":"fast-and-accurate-fsa-system-using-elbert-an","title":"Fast and Accurate FSA System Using ELBERT: An Efficient and Lightweight BERT","date":"2022-11-16","arxiv_id":"2211.08842","n_code_links":0,"syntology":null},{"paper":"/paper/an-fnet-based-auto-encoder-for-long-sequence","slug":"an-fnet-based-auto-encoder-for-long-sequence","title":"An FNet based Auto Encoder for Long Sequence News Story Generation","date":"2022-11-15","arxiv_id":"2211.08295","n_code_links":1,"syntology":null},{"paper":null,"slug":"empowering-language-models-with-knowledge","title":"Empowering Language Models with Knowledge Graph Reasoning for Question Answering","date":"2022-11-15","arxiv_id":"2211.08380","n_code_links":0,"syntology":null},{"paper":null,"slug":"robbert-2022-updating-a-dutch-language-model","title":"RobBERT-2022: Updating a Dutch Language Model to Account for Evolving Language Use","date":"2022-11-15","arxiv_id":"2211.08192","n_code_links":0,"syntology":null},{"paper":"/paper/greenplm-cross-lingual-pre-trained-language","slug":"greenplm-cross-lingual-pre-trained-language","title":"GreenPLM: Cross-Lingual Transfer of Monolingual Pre-Trained Language Models at Almost No Cost","date":"2022-11-13","arxiv_id":"2211.06993","n_code_links":1,"syntology":null},{"paper":"/paper/xu-at-semeval-2022-task-4-pre-bert-neural-1","slug":"xu-at-semeval-2022-task-4-pre-bert-neural-1","title":"Xu at SemEval-2022 Task 4: Pre-BERT Neural Network Methods vs Post-BERT RoBERTa Approach for Patronizing and Condescending Language Detection","date":"2022-11-13","arxiv_id":"2211.06874","n_code_links":1,"syntology":null},{"paper":"/paper/dark-patterns-in-e-commerce-a-dataset-and-its","slug":"dark-patterns-in-e-commerce-a-dataset-and-its","title":"Dark patterns in e-commerce: a dataset and its baseline evaluations","date":"2022-11-12","arxiv_id":"2211.06543","n_code_links":1,"syntology":null},{"paper":"/paper/misinformation-detection-using-persuasive","slug":"misinformation-detection-using-persuasive","title":"Using Persuasive Writing Strategies to Explain and Detect Health Misinformation","date":"2022-11-11","arxiv_id":"2211.05985","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-based-combination-of-convolutional-and","title":"BERT-Based Combination of Convolutional and Recurrent Neural Network for Indonesian Sentiment Analysis","date":"2022-11-10","arxiv_id":"2211.05273","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-in-plutarch-s-shadows","title":"BERT in Plutarch's Shadows","date":"2022-11-10","arxiv_id":"2211.05673","n_code_links":0,"syntology":null},{"paper":null,"slug":"biomedical-multi-hop-question-answering-using","title":"Biomedical Multi-hop Question Answering Using Knowledge Graph Embeddings and Language Models","date":"2022-11-10","arxiv_id":"2211.05351","n_code_links":0,"syntology":null},{"paper":"/paper/cherry-hypothesis-identifying-the-cherry-on","slug":"cherry-hypothesis-identifying-the-cherry-on","title":"PAD-Net: An Efficient Framework for Dynamic Networks","date":"2022-11-10","arxiv_id":"2211.05528","n_code_links":1,"syntology":null},{"paper":null,"slug":"syntax-guided-domain-adaptation-for-aspect","title":"Syntax-Guided Domain Adaptation for Aspect-based Sentiment Analysis","date":"2022-11-10","arxiv_id":"2211.05457","n_code_links":0,"syntology":null},{"paper":"/paper/collateral-facilitation-in-humans-and","slug":"collateral-facilitation-in-humans-and","title":"Collateral facilitation in humans and language models","date":"2022-11-09","arxiv_id":"2211.05198","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":["jmichaelov/collateral-facilitation"],"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":null,"slug":"cross-lingual-transfer-learning-for-check","title":"Cross-lingual Transfer Learning for Check-worthy Claim Identification over Twitter","date":"2022-11-09","arxiv_id":"2211.05087","n_code_links":0,"syntology":null},{"paper":"/paper/mask-more-and-mask-later-efficient-pre","slug":"mask-more-and-mask-later-efficient-pre","title":"Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token","date":"2022-11-09","arxiv_id":"2211.04898","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentiment-analysis-of-persian-language-review","title":"Sentiment Analysis of Persian Language: Review of Algorithms, Approaches and Datasets","date":"2022-11-09","arxiv_id":"2212.06041","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multimodal-approach-for-dementia-detection","title":"A Multimodal Approach for Dementia Detection from Spontaneous Speech with Tensor Fusion Layer","date":"2022-11-08","arxiv_id":"2211.04368","n_code_links":0,"syntology":null},{"paper":null,"slug":"discover-explanation-improvement-automatic","title":"Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing","date":"2022-11-08","arxiv_id":"2211.04476","n_code_links":0,"syntology":null},{"paper":null,"slug":"ad-bert-using-pre-trained-contextualized","title":"AD-BERT: Using Pre-trained contextualized embeddings to Predict the Progression from Mild Cognitive Impairment to Alzheimer's Disease","date":"2022-11-07","arxiv_id":"2212.06042","n_code_links":0,"syntology":null},{"paper":"/paper/suffix-retrieval-augmented-language-modeling","slug":"suffix-retrieval-augmented-language-modeling","title":"Suffix Retrieval-Augmented Language Modeling","date":"2022-11-06","arxiv_id":"2211.03053","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-deep-cnn-state-of-the-art-for-sentiment","title":"BERT-Deep CNN: State-of-the-Art for Sentiment Analysis of COVID-19 Tweets","date":"2022-11-04","arxiv_id":"2211.09733","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-for-long-documents-a-case-study-of","title":"BERT for Long Documents: A Case Study of Automated ICD Coding","date":"2022-11-04","arxiv_id":"2211.02519","n_code_links":0,"syntology":null},{"paper":"/paper/continuous-prompt-tuning-based-textual","slug":"continuous-prompt-tuning-based-textual","title":"Continuous Prompt Tuning Based Textual Entailment Model for E-commerce Entity Typing","date":"2022-11-04","arxiv_id":"2211.02483","n_code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-language-models-via-epistemic","slug":"fine-tuning-language-models-via-epistemic","title":"Fine-Tuning Language Models via Epistemic Neural Networks","date":"2022-11-03","arxiv_id":"2211.01568","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["deepmind/neural_testbed"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bectra-transducer-based-end-to-end-asr-with","title":"BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder","date":"2022-11-02","arxiv_id":"2211.00792","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-level-distillation-of-semantic","title":"Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model","date":"2022-11-02","arxiv_id":"2211.01200","n_code_links":0,"syntology":null},{"paper":null,"slug":"processing-long-legal-documents-with-pre","title":"Processing Long Legal Documents with Pre-trained Transformers: Modding LegalBERT and Longformer","date":"2022-11-02","arxiv_id":"2211.00974","n_code_links":0,"syntology":null},{"paper":"/paper/classactionprediction-a-challenging-benchmark","slug":"classactionprediction-a-challenging-benchmark","title":"ClassActionPrediction: A Challenging Benchmark for Legal Judgment Prediction of Class Action Cases in the US","date":"2022-11-01","arxiv_id":"2211.00582","n_code_links":1,"syntology":null},{"paper":null,"slug":"investigating-content-aware-neural-text-to","title":"Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features","date":"2022-11-01","arxiv_id":"2211.00342","n_code_links":0,"syntology":null},{"paper":null,"slug":"reduce-reuse-recycle-improving-training","title":"Reduce, Reuse, Recycle: Improving Training Efficiency with Distillation","date":"2022-11-01","arxiv_id":"2211.00683","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-document-retrieval-by-end-to-end","slug":"efficient-document-retrieval-by-end-to-end","title":"Efficient Document Retrieval by End-to-End Refining and Quantizing BERT Embedding with Contrastive Product Quantization","date":"2022-10-31","arxiv_id":"2210.17170","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-pre-trained-models-for-failure","title":"Leveraging Pre-trained Models for Failure Analysis Triplets Generation","date":"2022-10-31","arxiv_id":"2210.17497","n_code_links":0,"syntology":null},{"paper":"/paper/quala-minilm-a-quantized-length-adaptive","slug":"quala-minilm-a-quantized-length-adaptive","title":"QuaLA-MiniLM: a Quantized Length Adaptive MiniLM","date":"2022-10-31","arxiv_id":"2210.17114","n_code_links":2,"syntology":null},{"paper":null,"slug":"sdcl-self-distillation-contrastive-learning","title":"SDCL: Self-Distillation Contrastive Learning for Chinese Spell Checking","date":"2022-10-31","arxiv_id":"2210.17168","n_code_links":0,"syntology":null},{"paper":"/paper/parameter-efficient-tuning-makes-a-good","slug":"parameter-efficient-tuning-makes-a-good","title":"Parameter-Efficient Tuning Makes a Good Classification Head","date":"2022-10-30","arxiv_id":"2210.16771","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-meets-ctc-new-formulation-of-end-to-end","title":"BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model","date":"2022-10-29","arxiv_id":"2210.16663","n_code_links":0,"syntology":null},{"paper":null,"slug":"empirical-evaluation-of-post-training","title":"Empirical Evaluation of Post-Training Quantization Methods for Language Tasks","date":"2022-10-29","arxiv_id":"2210.16621","n_code_links":0,"syntology":null},{"paper":"/paper/exploiting-prompt-learning-with-pre-trained","slug":"exploiting-prompt-learning-with-pre-trained","title":"Exploiting prompt learning with pre-trained language models for Alzheimer's Disease detection","date":"2022-10-29","arxiv_id":"2210.16539","n_code_links":1,"syntology":null},{"paper":"/paper/bebert-efficient-and-robust-binary-ensemble","slug":"bebert-efficient-and-robust-binary-ensemble","title":"BEBERT: Efficient and Robust Binary Ensemble BERT","date":"2022-10-28","arxiv_id":"2210.15976","n_code_links":1,"syntology":null},{"paper":null,"slug":"feature-engineering-vs-bert-on-twitter-data","title":"Feature Engineering vs BERT on Twitter Data","date":"2022-10-28","arxiv_id":"2210.16168","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-use-of-modality-specific-large-scale","title":"On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis","date":"2022-10-28","arxiv_id":"2210.15937","n_code_links":0,"syntology":null}],"record_sha256":"3227c97e53af51d1b3371bc226261fe5180f4a9e119ba2cca3dbe58ced3c731d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}