{"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/36","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":36,"pages_in_order":71,"rows_per_page":100,"rows":[3501,3600],"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/35","next":"/method/linear-warmup-with-linear-decay/papers/37","papers":[{"paper":"/paper/bit-robustly-binarized-multi-distilled","slug":"bit-robustly-binarized-multi-distilled","title":"BiT: Robustly Binarized Multi-distilled Transformer","date":"2022-05-25","arxiv_id":"2205.13016","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/bit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"lifelong-learning-natural-language-processing","title":"Lifelong Learning Natural Language Processing Approach for Multilingual Data Classification","date":"2022-05-25","arxiv_id":"2206.11867","n_code_links":0,"syntology":null},{"paper":null,"slug":"orca-interpreting-prompted-language-models","title":"ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data","date":"2022-05-25","arxiv_id":"2205.12600","n_code_links":0,"syntology":null},{"paper":"/paper/robustlr-evaluating-robustness-to-logical","slug":"robustlr-evaluating-robustness-to-logical","title":"RobustLR: Evaluating Robustness to Logical Perturbation in Deductive Reasoning","date":"2022-05-25","arxiv_id":"2205.12598","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["ink-usc/robustlr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"text-to-face-generation-with-stylegan2","title":"Text-to-Face Generation with StyleGAN2","date":"2022-05-25","arxiv_id":"2205.12512","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-understanding-label-regularization","title":"Do we need Label Regularization to Fine-tune Pre-trained Language Models?","date":"2022-05-25","arxiv_id":"2205.12428","n_code_links":0,"syntology":null},{"paper":null,"slug":"train-flat-then-compress-sharpness-aware","title":"Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models","date":"2022-05-25","arxiv_id":"2205.12694","n_code_links":0,"syntology":null},{"paper":"/paper/transcormer-transformer-for-sentence-scoring","slug":"transcormer-transformer-for-sentence-scoring","title":"Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling","date":"2022-05-25","arxiv_id":"2205.12986","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/vulberta-simplified-source-code-pre-training","slug":"vulberta-simplified-source-code-pre-training","title":"VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection","date":"2022-05-25","arxiv_id":"2205.12424","n_code_links":1,"syntology":null},{"paper":"/paper/formulating-few-shot-fine-tuning-towards","slug":"formulating-few-shot-fine-tuning-towards","title":"Formulating Few-shot Fine-tuning Towards Language Model Pre-training: A Pilot Study on Named Entity Recognition","date":"2022-05-24","arxiv_id":"2205.11799","n_code_links":1,"syntology":null},{"paper":"/paper/k-12bert-bert-for-k-12-education","slug":"k-12bert-bert-for-k-12-education","title":"K-12BERT: BERT for K-12 education","date":"2022-05-24","arxiv_id":"2205.12335","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-role-of-bidirectionality-in-language","title":"On the Role of Bidirectionality in Language Model Pre-Training","date":"2022-05-24","arxiv_id":"2205.11726","n_code_links":0,"syntology":null},{"paper":"/paper/partial-input-baselines-show-that-nli-models","slug":"partial-input-baselines-show-that-nli-models","title":"Partial-input baselines show that NLI models can ignore context, but they don't","date":"2022-05-24","arxiv_id":"2205.12181","n_code_links":1,"syntology":null},{"paper":"/paper/retromae-pre-training-retrieval-oriented","slug":"retromae-pre-training-retrieval-oriented","title":"RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder","date":"2022-05-24","arxiv_id":"2205.12035","n_code_links":1,"syntology":null},{"paper":"/paper/sparse-mixers-combining-moe-and-mixing-to","slug":"sparse-mixers-combining-moe-and-mixing-to","title":"Sparse Mixers: Combining MoE and Mixing to build a more efficient BERT","date":"2022-05-24","arxiv_id":"2205.12399","n_code_links":1,"syntology":null},{"paper":null,"slug":"word-order-typology-in-multilingual-bert-a","title":"Word-order typology in Multilingual BERT: A case study in subordinate-clause detection","date":"2022-05-24","arxiv_id":"2205.11987","n_code_links":0,"syntology":null},{"paper":"/paper/artificial-intelligence-for-topic-modelling","slug":"artificial-intelligence-for-topic-modelling","title":"Artificial intelligence for topic modelling in Hindu philosophy: mapping themes between the Upanishads and the Bhagavad Gita","date":"2022-05-23","arxiv_id":"2205.11020","n_code_links":1,"syntology":null},{"paper":"/paper/kold-korean-offensive-language-dataset","slug":"kold-korean-offensive-language-dataset","title":"KOLD: Korean Offensive Language Dataset","date":"2022-05-23","arxiv_id":"2205.11315","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-ignore-adversarial-attacks-1","title":"Learning to Ignore Adversarial Attacks","date":"2022-05-23","arxiv_id":"2205.11551","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-paradox-of-learning-to-reason-from","slug":"on-the-paradox-of-learning-to-reason-from","title":"On the Paradox of Learning to Reason from Data","date":"2022-05-23","arxiv_id":"2205.11502","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":7,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"7 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["joshuacnf/paradox-learning2reason"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/outliers-dimensions-that-disrupt-transformers","slug":"outliers-dimensions-that-disrupt-transformers","title":"Outliers Dimensions that Disrupt Transformers Are Driven by Frequency","date":"2022-05-23","arxiv_id":"2205.11380","n_code_links":1,"syntology":{"ran":8,"of":16,"n_ran_checked":8,"n_instrument":0,"unverified":8,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["gpucce/outliersvsfreq"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/parameter-efficient-sparsity-for-large","slug":"parameter-efficient-sparsity-for-large","title":"Parameter-Efficient Sparsity for Large Language Models Fine-Tuning","date":"2022-05-23","arxiv_id":"2205.11005","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["alibaba/AliceMind","yuchaoli/pst"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/prompt-tuning-for-discriminative-pre-trained-1","slug":"prompt-tuning-for-discriminative-pre-trained-1","title":"Prompt Tuning for Discriminative Pre-trained Language Models","date":"2022-05-23","arxiv_id":"2205.11166","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":5,"n_instrument":2,"unverified":5,"pointer_only":0,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["thunlp/dpt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"scholarbert-bigger-is-not-always-better","title":"The Diminishing Returns of Masked Language Models to Science","date":"2022-05-23","arxiv_id":"2205.11342","n_code_links":0,"syntology":null},{"paper":null,"slug":"simple-recurrence-improves-masked-language","title":"Simple Recurrence Improves Masked Language Models","date":"2022-05-23","arxiv_id":"2205.11588","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-graph-enhanced-bert-model-for-event-2","title":"A Graph Enhanced BERT Model for Event Prediction","date":"2022-05-22","arxiv_id":"2205.10822","n_code_links":0,"syntology":null},{"paper":"/paper/graphmae-self-supervised-masked-graph","slug":"graphmae-self-supervised-masked-graph","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","date":"2022-05-22","arxiv_id":"2205.10803","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["thudm/graphmae"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/deeper-vs-wider-a-revisit-of-transformer","slug":"deeper-vs-wider-a-revisit-of-transformer","title":"A Study on Transformer Configuration and Training Objective","date":"2022-05-21","arxiv_id":"2205.10505","n_code_links":0,"syntology":null},{"paper":"/paper/pre-training-data-quality-and-quantity-for-a","slug":"pre-training-data-quality-and-quantity-for-a","title":"Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese","date":"2022-05-21","arxiv_id":"2205.10517","n_code_links":1,"syntology":null},{"paper":null,"slug":"current-trends-and-approaches-in-synonyms","title":"Current Trends and Approaches in Synonyms Extraction: Potential Adaptation to Arabic","date":"2022-05-20","arxiv_id":"2205.10412","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-extreme-parameter-compression-for-1","slug":"exploring-extreme-parameter-compression-for-1","title":"Exploring Extreme Parameter Compression for Pre-trained Language Models","date":"2022-05-20","arxiv_id":"2205.10036","n_code_links":1,"syntology":null},{"paper":"/paper/pre-training-transformer-models-with-sentence","slug":"pre-training-transformer-models-with-sentence","title":"Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection","date":"2022-05-20","arxiv_id":"2205.10455","n_code_links":0,"syntology":null},{"paper":"/paper/progressive-class-semantic-matching-for-semi-1","slug":"progressive-class-semantic-matching-for-semi-1","title":"Progressive Class Semantic Matching for Semi-supervised Text Classification","date":"2022-05-20","arxiv_id":"2205.10189","n_code_links":1,"syntology":null},{"paper":null,"slug":"arabglossbert-fine-tuning-bert-on-context-1","title":"ArabGlossBERT: Fine-Tuning BERT on Context-Gloss Pairs for WSD","date":"2022-05-19","arxiv_id":"2205.09685","n_code_links":0,"syntology":null},{"paper":"/paper/automated-scoring-for-reading-comprehension","slug":"automated-scoring-for-reading-comprehension","title":"Automated Scoring for Reading Comprehension via In-context BERT Tuning","date":"2022-05-19","arxiv_id":"2205.09864","n_code_links":1,"syntology":null},{"paper":"/paper/overcoming-language-disparity-in-online","slug":"overcoming-language-disparity-in-online","title":"Overcoming Language Disparity in Online Content Classification with Multimodal Learning","date":"2022-05-19","arxiv_id":"2205.09744","n_code_links":1,"syntology":null},{"paper":"/paper/psychiatric-scale-guided-risky-post-screening","slug":"psychiatric-scale-guided-risky-post-screening","title":"Psychiatric Scale Guided Risky Post Screening for Early Detection of Depression","date":"2022-05-19","arxiv_id":"2205.09497","n_code_links":1,"syntology":null},{"paper":"/paper/lerac-learning-rate-curriculum","slug":"lerac-learning-rate-curriculum","title":"Learning Rate Curriculum","date":"2022-05-18","arxiv_id":"2205.09180","n_code_links":1,"syntology":null},{"paper":"/paper/persian-natural-language-inference-a-meta-1","slug":"persian-natural-language-inference-a-meta-1","title":"Persian Natural Language Inference: A Meta-learning approach","date":"2022-05-18","arxiv_id":"2205.08755","n_code_links":1,"syntology":null},{"paper":null,"slug":"feature-aggregation-in-zero-shot-cross","title":"Feature Aggregation in Zero-Shot Cross-Lingual Transfer Using Multilingual BERT","date":"2022-05-17","arxiv_id":"2205.08497","n_code_links":0,"syntology":null},{"paper":null,"slug":"samu-xlsr-semantically-aligned-multimodal","title":"SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation","date":"2022-05-17","arxiv_id":"2205.08180","n_code_links":0,"syntology":null},{"paper":"/paper/semi-fnd-stacked-ensemble-based-multimodal","slug":"semi-fnd-stacked-ensemble-based-multimodal","title":"SEMI-FND: Stacked Ensemble Based Multimodal Inference For Faster Fake News Detection","date":"2022-05-17","arxiv_id":"2205.08159","n_code_links":0,"syntology":null},{"paper":"/paper/viralbert-a-user-focused-bert-based-approach","slug":"viralbert-a-user-focused-bert-based-approach","title":"ViralBERT: A User Focused BERT-Based Approach to Virality Prediction","date":"2022-05-17","arxiv_id":"2206.10298","n_code_links":1,"syntology":null},{"paper":"/paper/chemical-transformer-compression-for","slug":"chemical-transformer-compression-for","title":"Chemical transformer compression for accelerating both training and inference of molecular modeling","date":"2022-05-16","arxiv_id":"2205.07582","n_code_links":1,"syntology":null},{"paper":null,"slug":"harnessing-multilingual-resources-to-question","title":"Harnessing Multilingual Resources to Question Answering in Arabic","date":"2022-05-16","arxiv_id":"2205.08024","n_code_links":0,"syntology":null},{"paper":null,"slug":"discovering-latent-concepts-learned-in-bert-1","title":"Discovering Latent Concepts Learned in BERT","date":"2022-05-15","arxiv_id":"2205.07237","n_code_links":0,"syntology":null},{"paper":"/paper/learning-lip-based-audio-visual-speaker","slug":"learning-lip-based-audio-visual-speaker","title":"Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT","date":"2022-05-15","arxiv_id":"2205.07180","n_code_links":1,"syntology":null},{"paper":null,"slug":"fake-news-quick-detection-on-dynamic","title":"Fake News Quick Detection on Dynamic Heterogeneous Information Networks","date":"2022-05-14","arxiv_id":"2205.07039","n_code_links":0,"syntology":null},{"paper":"/paper/naturalistic-causal-probing-for-morpho-syntax","slug":"naturalistic-causal-probing-for-morpho-syntax","title":"Naturalistic Causal Probing for Morpho-Syntax","date":"2022-05-14","arxiv_id":"2205.07043","n_code_links":1,"syntology":null},{"paper":"/paper/a-study-of-the-attention-abnormality-in-1","slug":"a-study-of-the-attention-abnormality-in-1","title":"A Study of the Attention Abnormality in Trojaned BERTs","date":"2022-05-13","arxiv_id":"2205.08305","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["weimin17/attention_abnormality_in_trojaned_berts"],"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":"improving-contextual-representation-with-1","title":"Improving Contextual Representation with Gloss Regularized Pre-training","date":"2022-05-13","arxiv_id":"2205.06603","n_code_links":0,"syntology":null},{"paper":null,"slug":"apptek-s-submission-to-the-iwslt-2022","title":"AppTek's Submission to the IWSLT 2022 Isometric Spoken Language Translation Task","date":"2022-05-12","arxiv_id":"2205.05807","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-the-computation-of-abstract-sameness","title":"Is the Computation of Abstract Sameness Relations Human-Like in Neural Language Models?","date":"2022-05-12","arxiv_id":"2205.06149","n_code_links":0,"syntology":null},{"paper":null,"slug":"ner-mqmrc-formulating-named-entity","title":"NER-MQMRC: Formulating Named Entity Recognition as Multi Question Machine Reading Comprehension","date":"2022-05-12","arxiv_id":"2205.05904","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-time-varying-study-of-chinese-investor","title":"A time-varying study of Chinese investor sentiment, stock market liquidity and volatility: Based on deep learning BERT model and TVP-VAR model","date":"2022-05-11","arxiv_id":"2205.05719","n_code_links":0,"syntology":null},{"paper":"/paper/query-based-keyphrase-extraction-from-long","slug":"query-based-keyphrase-extraction-from-long","title":"Query-Based Keyphrase Extraction from Long Documents","date":"2022-05-11","arxiv_id":"2205.05391","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-based-chinese-text-sentiment","title":"Deep learning based Chinese text sentiment mining and stock market correlation research","date":"2022-05-10","arxiv_id":"2205.04743","n_code_links":0,"syntology":null},{"paper":"/paper/problems-with-cosine-as-a-measure-of","slug":"problems-with-cosine-as-a-measure-of","title":"Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words","date":"2022-05-10","arxiv_id":"2205.05092","n_code_links":2,"syntology":null},{"paper":null,"slug":"automated-evaluation-for-student","title":"Automated Evaluation for Student Argumentative Writing: A Survey","date":"2022-05-09","arxiv_id":"2205.04083","n_code_links":0,"syntology":null},{"paper":"/paper/long-document-re-ranking-with-modular-re","slug":"long-document-re-ranking-with-modular-re","title":"Long Document Re-ranking with Modular Re-ranker","date":"2022-05-09","arxiv_id":"2205.04275","n_code_links":1,"syntology":null},{"paper":null,"slug":"research-on-the-correlation-between-text","title":"Research on the correlation between text emotion mining and stock market based on deep learning","date":"2022-05-09","arxiv_id":"2205.06675","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-use-of-bert-for-automated-essay","slug":"on-the-use-of-bert-for-automated-essay","title":"On the Use of BERT for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representation","date":"2022-05-08","arxiv_id":"2205.03835","n_code_links":1,"syntology":null},{"paper":"/paper/aki-bert-a-pre-trained-clinical-language","slug":"aki-bert-a-pre-trained-clinical-language","title":"AKI-BERT: a Pre-trained Clinical Language Model for Early Prediction of Acute Kidney Injury","date":"2022-05-07","arxiv_id":"2205.03695","n_code_links":1,"syntology":null},{"paper":"/paper/emotionflow-capture-the-dialogue-level","slug":"emotionflow-capture-the-dialogue-level","title":"EmotionFlow: Capture the Dialogue Level Emotion Transitions","date":"2022-05-07","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"number-entity-recognition","title":"Improving Downstream Task Performance by Treating Numbers as Entities","date":"2022-05-07","arxiv_id":"2205.03559","n_code_links":0,"syntology":null},{"paper":"/paper/a-data-cartography-based-mixup-for-pre","slug":"a-data-cartography-based-mixup-for-pre","title":"A Data Cartography based MixUp for Pre-trained Language Models","date":"2022-05-06","arxiv_id":"2205.03403","n_code_links":1,"syntology":null},{"paper":"/paper/stock-price-prediction-based-on-natural","slug":"stock-price-prediction-based-on-natural","title":"Stock Price Prediction Based on Natural Language Processing","date":"2022-05-06","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/bort-back-and-denoising-reconstruction-for-1","slug":"bort-back-and-denoising-reconstruction-for-1","title":"BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog","date":"2022-05-05","arxiv_id":"2205.02471","n_code_links":1,"syntology":null},{"paper":"/paper/exploiting-global-and-local-hierarchies-for","slug":"exploiting-global-and-local-hierarchies-for","title":"Exploiting Global and Local Hierarchies for Hierarchical Text Classification","date":"2022-05-05","arxiv_id":"2205.02613","n_code_links":1,"syntology":null},{"paper":"/paper/hyperbolic-relevance-matching-for-neural","slug":"hyperbolic-relevance-matching-for-neural","title":"Hyperbolic Relevance Matching for Neural Keyphrase Extraction","date":"2022-05-04","arxiv_id":"2205.02047","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-virtual-edges-to-extract-keywords-from","title":"Using virtual edges to extract keywords from texts modeled as complex networks","date":"2022-05-04","arxiv_id":"2205.02172","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-fine-tuning-of-bert-models-on-the","title":"Efficient Fine-Tuning of BERT Models on the Edge","date":"2022-05-03","arxiv_id":"2205.01541","n_code_links":0,"syntology":null},{"paper":null,"slug":"explain-and-conquer-personalised-text-based","title":"Explain and Conquer: Personalised Text-based Reviews to Achieve Transparency","date":"2022-05-03","arxiv_id":"2205.01759","n_code_links":0,"syntology":null},{"paper":null,"slug":"finding-patterns-in-knowledge-attribution-for","title":"Finding patterns in Knowledge Attribution for Transformers","date":"2022-05-03","arxiv_id":"2205.01366","n_code_links":0,"syntology":null},{"paper":"/paper/predicting-issue-types-with-sebert","slug":"predicting-issue-types-with-sebert","title":"Predicting Issue Types with seBERT","date":"2022-05-03","arxiv_id":"2205.01335","n_code_links":1,"syntology":null},{"paper":"/paper/semattack-natural-textual-attacks-via-1","slug":"semattack-natural-textual-attacks-via-1","title":"SemAttack: Natural Textual Attacks via Different Semantic Spaces","date":"2022-05-03","arxiv_id":"2205.01287","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ai-secure/semattack"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/bertops-studying-bert-representations-under-a","slug":"bertops-studying-bert-representations-under-a","title":"BERTops: Studying BERT Representations under a Topological Lens","date":"2022-05-02","arxiv_id":"2205.00953","n_code_links":1,"syntology":null},{"paper":"/paper/entity-aware-transformers-for-entity-search","slug":"entity-aware-transformers-for-entity-search","title":"Entity-aware Transformers for Entity Search","date":"2022-05-02","arxiv_id":"2205.00820","n_code_links":1,"syntology":null},{"paper":null,"slug":"gradient-descent-stochastic-optimization-and","title":"Gradient Descent, Stochastic Optimization, and Other Tales","date":"2022-05-02","arxiv_id":"2205.00832","n_code_links":0,"syntology":null},{"paper":"/paper/improving-students-academic-performance-with","slug":"improving-students-academic-performance-with","title":"Improving Students' Academic Performance with AI and Semantic Technologies","date":"2022-05-02","arxiv_id":"2206.03213","n_code_links":1,"syntology":null},{"paper":null,"slug":"detecting-covid-19-conspiracy-theories-with","title":"Detecting COVID-19 Conspiracy Theories with Transformers and TF-IDF","date":"2022-05-01","arxiv_id":"2205.00377","n_code_links":0,"syntology":null},{"paper":"/paper/storseismic-a-new-paradigm-in-deep-learning","slug":"storseismic-a-new-paradigm-in-deep-learning","title":"StorSeismic: A new paradigm in deep learning for seismic processing","date":"2022-04-30","arxiv_id":"2205.00222","n_code_links":1,"syntology":null},{"paper":"/paper/exaasc-a-general-target-based-stance","slug":"exaasc-a-general-target-based-stance","title":"ExaASC: A General Target-Based Stance Detection Corpus in Arabic Language","date":"2022-04-29","arxiv_id":"2204.13979","n_code_links":1,"syntology":null},{"paper":null,"slug":"qrelscore-better-evaluating-generated","title":"QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance","date":"2022-04-29","arxiv_id":"2204.13921","n_code_links":0,"syntology":null},{"paper":null,"slug":"robbertje-a-distilled-dutch-bert-model","title":"RobBERTje: a Distilled Dutch BERT Model","date":"2022-04-28","arxiv_id":"2204.13511","n_code_links":0,"syntology":null},{"paper":null,"slug":"better-query-graph-selection-for-knowledge","title":"Better Query Graph Selection for Knowledge Base Question Answering","date":"2022-04-27","arxiv_id":"2204.12662","n_code_links":0,"syntology":null},{"paper":"/paper/modern-baselines-for-sparql-semantic-parsing","slug":"modern-baselines-for-sparql-semantic-parsing","title":"Modern Baselines for SPARQL Semantic Parsing","date":"2022-04-27","arxiv_id":"2204.12793","n_code_links":1,"syntology":null},{"paper":null,"slug":"rigoberta-a-state-of-the-art-language-model","title":"RigoBERTa: A State-of-the-Art Language Model For Spanish","date":"2022-04-27","arxiv_id":"2205.10233","n_code_links":0,"syntology":null},{"paper":"/paper/skillspan-hard-and-soft-skill-extraction-from","slug":"skillspan-hard-and-soft-skill-extraction-from","title":"SkillSpan: Hard and Soft Skill Extraction from English Job Postings","date":"2022-04-27","arxiv_id":"2204.12811","n_code_links":1,"syntology":null},{"paper":null,"slug":"timebert-enhancing-pre-trained-language","title":"BiTimeBERT: Extending Pre-Trained Language Representations with Bi-Temporal Information","date":"2022-04-27","arxiv_id":"2204.13032","n_code_links":0,"syntology":null},{"paper":"/paper/miles-visual-bert-pre-training-with-injected","slug":"miles-visual-bert-pre-training-with-injected","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","date":"2022-04-26","arxiv_id":"2204.12408","n_code_links":1,"syntology":null},{"paper":"/paper/plod-an-abbreviation-detection-dataset-for","slug":"plod-an-abbreviation-detection-dataset-for","title":"PLOD: An Abbreviation Detection Dataset for Scientific Documents","date":"2022-04-26","arxiv_id":"2204.12061","n_code_links":1,"syntology":null},{"paper":null,"slug":"pretraining-chinese-bert-for-detecting-word","title":"Pretraining Chinese BERT for Detecting Word Insertion and Deletion Errors","date":"2022-04-26","arxiv_id":"2204.12052","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-extrapolation-performance-of-dense","slug":"evaluating-extrapolation-performance-of-dense","title":"Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models","date":"2022-04-25","arxiv_id":"2204.11447","n_code_links":1,"syntology":null},{"paper":"/paper/groupwise-query-performance-prediction-with","slug":"groupwise-query-performance-prediction-with","title":"Groupwise Query Performance Prediction with BERT","date":"2022-04-25","arxiv_id":"2204.11489","n_code_links":1,"syntology":null},{"paper":"/paper/faster-learned-sparse-retrieval-with-guided","slug":"faster-learned-sparse-retrieval-with-guided","title":"Faster Learned Sparse Retrieval with Guided Traversal","date":"2022-04-24","arxiv_id":"2204.11314","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-win-lottery-tickets-in-bert-1","slug":"learning-to-win-lottery-tickets-in-bert-1","title":"Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training","date":"2022-04-24","arxiv_id":"2204.11218","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-bert-models-to-classify","title":"Fine-Tuning BERT Models to Classify Misinformation on Garlic and COVID-19 on Twitter","date":"2022-04-22","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"taygete-at-semeval-2022-task-4-roberta-based","title":"Taygete at SemEval-2022 Task 4: RoBERTa based models for detecting Patronising and Condescending Language","date":"2022-04-22","arxiv_id":"2204.10519","n_code_links":0,"syntology":null},{"paper":null,"slug":"wabert-a-low-resource-end-to-end-model-for","title":"WaBERT: A Low-resource End-to-end Model for Spoken Language Understanding and Speech-to-BERT Alignment","date":"2022-04-22","arxiv_id":"2204.10461","n_code_links":0,"syntology":null}],"record_sha256":"842575f17fa415c80193d7ee3b8db96462e8cf82fc6e4a19895f08689f245fed","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}