{"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/66","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":66,"pages_in_order":108,"rows_per_page":100,"rows":[6501,6600],"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/65","next":"/method/weight-decay/papers/67","papers":[{"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},{"paper":null,"slug":"exploring-artificial-intelligence-as-a","title":"Measuring artificial intelligence: a systematic assessment and implications for governance","date":"2022-04-21","arxiv_id":"2204.10304","n_code_links":0,"syntology":null},{"paper":"/paper/is-neural-topic-modelling-better-than-1","slug":"is-neural-topic-modelling-better-than-1","title":"Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics","date":"2022-04-21","arxiv_id":"2204.09874","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":["hyintell/topicx"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/revisiting-gaussian-mixture-critic-in-off","slug":"revisiting-gaussian-mixture-critic-in-off","title":"Revisiting Gaussian mixture critics in off-policy reinforcement learning: a sample-based approach","date":"2022-04-21","arxiv_id":"2204.10256","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-meets-nonparametric-regression","title":"Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive?","date":"2022-04-20","arxiv_id":"2204.09664","n_code_links":0,"syntology":null},{"paper":"/paper/is-bert-robust-to-label-noise-a-study-on","slug":"is-bert-robust-to-label-noise-a-study-on","title":"Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification","date":"2022-04-20","arxiv_id":"2204.09371","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["uds-lsv/bert-lnl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/albeto-and-distilbeto-lightweight-spanish","slug":"albeto-and-distilbeto-lightweight-spanish","title":"ALBETO and DistilBETO: Lightweight Spanish Language Models","date":"2022-04-19","arxiv_id":"2204.09145","n_code_links":2,"syntology":null},{"paper":null,"slug":"codexdb-generating-code-for-processing-sql","title":"CodexDB: Generating Code for Processing SQL Queries using GPT-3 Codex","date":"2022-04-19","arxiv_id":"2204.08941","n_code_links":0,"syntology":null},{"paper":null,"slug":"decbert-enhancing-the-language-understanding","title":"DecBERT: Enhancing the Language Understanding of BERT with Causal Attention Masks","date":"2022-04-19","arxiv_id":"2204.08688","n_code_links":0,"syntology":null},{"paper":null,"slug":"impact-of-tokenization-on-language-models-an-1","title":"Impact of Tokenization on Language Models: An Analysis for Turkish","date":"2022-04-19","arxiv_id":"2204.08832","n_code_links":0,"syntology":null},{"paper":"/paper/litmc-bert-transformer-based-multi-label","slug":"litmc-bert-transformer-based-multi-label","title":"LitMC-BERT: transformer-based multi-label classification of biomedical literature with an application on COVID-19 literature curation","date":"2022-04-19","arxiv_id":"2204.08649","n_code_links":1,"syntology":null},{"paper":null,"slug":"mono-vs-multilingual-bert-for-hate-speech","title":"Mono vs Multilingual BERT for Hate Speech Detection and Text Classification: A Case Study in Marathi","date":"2022-04-19","arxiv_id":"2204.08669","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-hate-speech-detection-from-bengali","slug":"multimodal-hate-speech-detection-from-bengali","title":"Multimodal Hate Speech Detection from Bengali Memes and Texts","date":"2022-04-19","arxiv_id":"2204.10196","n_code_links":1,"syntology":null},{"paper":null,"slug":"probing-for-the-usage-of-grammatical-number","title":"Probing for the Usage of Grammatical Number","date":"2022-04-19","arxiv_id":"2204.08831","n_code_links":0,"syntology":null},{"paper":"/paper/ingredient-extraction-from-text-in-the-recipe","slug":"ingredient-extraction-from-text-in-the-recipe","title":"Ingredient Extraction from Text in the Recipe Domain","date":"2022-04-18","arxiv_id":"2204.08137","n_code_links":1,"syntology":null},{"paper":"/paper/l3cube-hingcorpus-and-hingbert-a-code-mixed","slug":"l3cube-hingcorpus-and-hingbert-a-code-mixed","title":"L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models","date":"2022-04-18","arxiv_id":"2204.08398","n_code_links":1,"syntology":null},{"paper":"/paper/utnlp-at-semeval-2022-task-6-a-comparative","slug":"utnlp-at-semeval-2022-task-6-a-comparative","title":"UTNLP at SemEval-2022 Task 6: A Comparative Analysis of Sarcasm Detection Using Generative-based and Mutation-based Data Augmentation","date":"2022-04-18","arxiv_id":"2204.08198","n_code_links":2,"syntology":null},{"paper":null,"slug":"zero-shot-entity-and-tweet-characterization","title":"Zero-shot Entity and Tweet Characterization with Designed Conditional Prompts and Contexts","date":"2022-04-18","arxiv_id":"2204.08405","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-effectively-learning-of-knowledge-in","title":"Knowledgeable Salient Span Mask for Enhancing Language Models as Knowledge Base","date":"2022-04-17","arxiv_id":"2204.07994","n_code_links":0,"syntology":null},{"paper":null,"slug":"pathologies-of-pre-trained-language-models-in","title":"Pathologies of Pre-trained Language Models in Few-shot Fine-tuning","date":"2022-04-17","arxiv_id":"2204.08039","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-script-knowledge-from-pre-trained","title":"Probing Script Knowledge from Pre-Trained Models","date":"2022-04-16","arxiv_id":"2204.10176","n_code_links":0,"syntology":null},{"paper":null,"slug":"simplebert-a-pre-trained-model-that-learns-to","title":"SimpleBERT: A Pre-trained Model That Learns to Generate Simple Words","date":"2022-04-16","arxiv_id":"2204.07779","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-pre-trained-language-models-with","title":"Improving Pre-trained Language Models with Syntactic Dependency Prediction Task for Chinese Semantic Error Recognition","date":"2022-04-15","arxiv_id":"2204.07464","n_code_links":0,"syntology":null},{"paper":"/paper/mgpt-few-shot-learners-go-multilingual","slug":"mgpt-few-shot-learners-go-multilingual","title":"mGPT: Few-Shot Learners Go Multilingual","date":"2022-04-15","arxiv_id":"2204.07580","n_code_links":1,"syntology":null},{"paper":"/paper/polling-latent-opinions-a-method-for-1","slug":"polling-latent-opinions-a-method-for-1","title":"Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models","date":"2022-04-15","arxiv_id":"2204.07483","n_code_links":1,"syntology":null},{"paper":null,"slug":"resource-aware-distributed-submodular","title":"Resource-Aware Distributed Submodular Maximization: A Paradigm for Multi-Robot Decision-Making","date":"2022-04-15","arxiv_id":"2204.07520","n_code_links":0,"syntology":null},{"paper":null,"slug":"brazilian-court-documents-clustered-by","title":"Analysing similarities between legal court documents using natural language processing approaches based on Transformers","date":"2022-04-14","arxiv_id":"2204.07182","n_code_links":0,"syntology":null},{"paper":"/paper/calbert-code-mixed-adaptive-language-1","slug":"calbert-code-mixed-adaptive-language-1","title":"CalBERT - Code-mixed Adaptive Language representations using BERT","date":"2022-04-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"does-bert-really-agree-fine-grained-analysis-1","title":"Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic Task","date":"2022-04-14","arxiv_id":"2204.06889","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-neox-20b-an-open-source-autoregressive-1","slug":"gpt-neox-20b-an-open-source-autoregressive-1","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","date":"2022-04-14","arxiv_id":"2204.06745","n_code_links":11,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["eleutherai/gpt-neox"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/latent-aspect-detection-from-online","slug":"latent-aspect-detection-from-online","title":"Latent Aspect Detection from Online Unsolicited Customer Reviews","date":"2022-04-14","arxiv_id":"2204.06964","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-label-topic-classification-for-covid-19","title":"Multi-label topic classification for COVID-19 literature with Bioformer","date":"2022-04-14","arxiv_id":"2204.06758","n_code_links":0,"syntology":null},{"paper":null,"slug":"rows-from-many-sources-enriching-row","title":"Rows from Many Sources: Enriching row completions from Wikidata with a pre-trained Language Model","date":"2022-04-14","arxiv_id":"2204.07014","n_code_links":0,"syntology":null},{"paper":"/paper/hubert-ee-early-exiting-hubert-for-efficient","slug":"hubert-ee-early-exiting-hubert-for-efficient","title":"HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition","date":"2022-04-13","arxiv_id":"2204.06328","n_code_links":1,"syntology":null},{"paper":null,"slug":"iiitdwd-shankarb-dravidian-codemixi-hasoc2021","title":"IIITDWD-ShankarB@ Dravidian-CodeMixi-HASOC2021: mBERT based model for identification of offensive content in south Indian languages","date":"2022-04-13","arxiv_id":"2204.10195","n_code_links":0,"syntology":null},{"paper":null,"slug":"metro-efficient-denoising-pretraining-of","title":"METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals","date":"2022-04-13","arxiv_id":"2204.06644","n_code_links":0,"syntology":null},{"paper":"/paper/probing-for-constituency-structure-in-neural","slug":"probing-for-constituency-structure-in-neural","title":"Probing for Constituency Structure in Neural Language Models","date":"2022-04-13","arxiv_id":"2204.06201","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":["davidarps/constptbprobing"],"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":null,"slug":"tangobert-reducing-inference-cost-by-using","title":"TangoBERT: Reducing Inference Cost by using Cascaded Architecture","date":"2022-04-13","arxiv_id":"2204.06271","n_code_links":0,"syntology":null},{"paper":null,"slug":"team-ufal-at-cmcl-2022-shared-task-figuring","title":"Team ÚFAL at CMCL 2022 Shared Task: Figuring out the correct recipe for predicting Eye-Tracking features using Pretrained Language Models","date":"2022-04-11","arxiv_id":"2204.04998","n_code_links":0,"syntology":null},{"paper":null,"slug":"tokenwise-contrastive-pretraining-for-finer","title":"Tokenwise Contrastive Pretraining for Finer Speech-to-BERT Alignment in End-to-End Speech-to-Intent Systems","date":"2022-04-11","arxiv_id":"2204.05188","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-generalizeable-semantic-product","title":"Towards Generalizable Semantic Product Search by Text Similarity Pre-training on Search Click Logs","date":"2022-04-11","arxiv_id":"2204.05231","n_code_links":0,"syntology":null},{"paper":"/paper/uniform-complexity-for-text-generation","slug":"uniform-complexity-for-text-generation","title":"Uniform Complexity for Text Generation","date":"2022-04-11","arxiv_id":"2204.05185","n_code_links":1,"syntology":null},{"paper":"/paper/confidence-estimation-transformer-for-long","slug":"confidence-estimation-transformer-for-long","title":"Confidence Estimation Transformer for Long-term Renewable Energy Forecasting in Reinforcement Learning-based Power Grid Dispatching","date":"2022-04-10","arxiv_id":"2204.04612","n_code_links":1,"syntology":null},{"paper":null,"slug":"fake-news-detection-using-parallel-bert-deep","title":"Fake news detection using parallel BERT deep neural networks","date":"2022-04-10","arxiv_id":"2204.04793","n_code_links":0,"syntology":null},{"paper":"/paper/few-shot-cross-lingual-transfer-for-coarse","slug":"few-shot-cross-lingual-transfer-for-coarse","title":"Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts","date":"2022-04-10","arxiv_id":"2204.04775","n_code_links":1,"syntology":null},{"paper":null,"slug":"ma-dreamer-coordination-and-communication","title":"MA-Dreamer: Coordination and communication through shared imagination","date":"2022-04-10","arxiv_id":"2204.04687","n_code_links":0,"syntology":null},{"paper":null,"slug":"pushing-on-personality-detection-from-verbal","title":"Pushing on Personality Detection from Verbal Behavior: A Transformer Meets Text Contours of Psycholinguistic Features","date":"2022-04-10","arxiv_id":"2204.04629","n_code_links":0,"syntology":null},{"paper":null,"slug":"foundationlayernorm-scaling-bert-and-gpt-to","title":"FoundationLayerNorm: Scaling BERT and GPT to 1,000 Layers","date":"2022-04-09","arxiv_id":"2204.04477","n_code_links":0,"syntology":null},{"paper":"/paper/modeling-multi-granularity-hierarchical-1","slug":"modeling-multi-granularity-hierarchical-1","title":"Modeling Multi-Granularity Hierarchical Features for Relation Extraction","date":"2022-04-09","arxiv_id":"2204.04437","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 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["xnliang98/sms"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/bag-of-words-vs-sequence-vs-graph-vs","slug":"bag-of-words-vs-sequence-vs-graph-vs","title":"Are We Really Making Much Progress in Text Classification? A Comparative Review","date":"2022-04-08","arxiv_id":"2204.03954","n_code_links":1,"syntology":null},{"paper":"/paper/contextual-representation-learning-beyond-1","slug":"contextual-representation-learning-beyond-1","title":"Contextual Representation Learning beyond Masked Language Modeling","date":"2022-04-08","arxiv_id":"2204.04163","n_code_links":1,"syntology":null},{"paper":"/paper/infusing-knowledge-from-wikipedia-to-enhance","slug":"infusing-knowledge-from-wikipedia-to-enhance","title":"Infusing Knowledge from Wikipedia to Enhance Stance Detection","date":"2022-04-08","arxiv_id":"2204.03839","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-understanding-large-scale-discourse-1","title":"Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language Models","date":"2022-04-08","arxiv_id":"2204.04289","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-attention-through-gradient-based","title":"Accelerating Attention through Gradient-Based Learned Runtime Pruning","date":"2022-04-07","arxiv_id":"2204.03227","n_code_links":0,"syntology":null},{"paper":null,"slug":"autoencoding-language-model-based-ensemble","title":"Autoencoding Language Model Based Ensemble Learning for Commonsense Validation and Explanation","date":"2022-04-07","arxiv_id":"2204.03324","n_code_links":0,"syntology":null},{"paper":null,"slug":"bertuit-understanding-spanish-language-in","title":"BERTuit: Understanding Spanish language in Twitter through a native transformer","date":"2022-04-07","arxiv_id":"2204.03465","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-semantic-code-search-with","title":"CoCoSoDa: Effective Contrastive Learning for Code Search","date":"2022-04-07","arxiv_id":"2204.03293","n_code_links":0,"syntology":null},{"paper":"/paper/palbert-teaching-albert-to-ponder-1","slug":"palbert-teaching-albert-to-ponder-1","title":"PALBERT: Teaching ALBERT to Ponder","date":"2022-04-07","arxiv_id":"2204.03276","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["tinkoff-ai/palbert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/pretraining-text-encoders-with-adversarial-1","slug":"pretraining-text-encoders-with-adversarial-1","title":"Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators","date":"2022-04-07","arxiv_id":"2204.03243","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":2,"n_instrument":2,"unverified":4,"pointer_only":2,"phrase":"4 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["microsoft/amos"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/testing-the-limits-of-natural-language-models","slug":"testing-the-limits-of-natural-language-models","title":"Testing the limits of natural language models for predicting human language judgments","date":"2022-04-07","arxiv_id":"2204.03592","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-effects-of-regularization-and-data","title":"The Effects of Regularization and Data Augmentation are Class Dependent","date":"2022-04-07","arxiv_id":"2204.03632","n_code_links":0,"syntology":null},{"paper":null,"slug":"drsphelps-at-semeval-2022-task-2-learning","title":"drsphelps at SemEval-2022 Task 2: Learning idiom representations using BERTRAM","date":"2022-04-06","arxiv_id":"2204.02821","n_code_links":0,"syntology":null},{"paper":"/paper/fusing-finetuned-models-for-better","slug":"fusing-finetuned-models-for-better","title":"Fusing finetuned models for better pretraining","date":"2022-04-06","arxiv_id":"2204.03044","n_code_links":2,"syntology":null},{"paper":"/paper/knowledge-infused-decoding-1","slug":"knowledge-infused-decoding-1","title":"Knowledge Infused Decoding","date":"2022-04-06","arxiv_id":"2204.03084","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":["microsoft/kid"],"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":"paying-more-attention-to-self-attention","title":"Paying More Attention to Self-attention: Improving Pre-trained Language Models via Attention Guiding","date":"2022-04-06","arxiv_id":"2204.02922","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-synthetic-data-for-conversational","title":"Using Synthetic Data for Conversational Response Generation in Low-resource Settings","date":"2022-04-06","arxiv_id":"2204.02653","n_code_links":0,"syntology":null},{"paper":null,"slug":"abstractive-summarization-of-hospitalisation","title":"Abstractive summarization of hospitalisation histories with transformer networks","date":"2022-04-05","arxiv_id":"2204.02208","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exploratory-study-on-code-attention-in","title":"An Exploratory Study on Code Attention in BERT","date":"2022-04-05","arxiv_id":"2204.10200","n_code_links":0,"syntology":null},{"paper":"/paper/data-augmentation-for-intent-classification-1","slug":"data-augmentation-for-intent-classification-1","title":"Data Augmentation for Intent Classification with Off-the-shelf Large Language Models","date":"2022-04-05","arxiv_id":"2204.01959","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":6,"n_instrument":1,"unverified":3,"pointer_only":2,"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) · 3 unverified","official":{"repos":["elementai/data-augmentation-with-llms"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/how-different-are-pre-trained-transformers","slug":"how-different-are-pre-trained-transformers","title":"How Different are Pre-trained Transformers for Text Ranking?","date":"2022-04-05","arxiv_id":"2204.07233","n_code_links":1,"syntology":null},{"paper":"/paper/multilinguals-at-semeval-2022-task-11","slug":"multilinguals-at-semeval-2022-task-11","title":"Multilinguals at SemEval-2022 Task 11: Transformer Based Architecture for Complex NER","date":"2022-04-05","arxiv_id":"2204.02173","n_code_links":1,"syntology":null},{"paper":"/paper/pos-bert-point-cloud-one-stage-bert-pre","slug":"pos-bert-point-cloud-one-stage-bert-pre","title":"POS-BERT: Point Cloud One-Stage BERT Pre-Training","date":"2022-04-03","arxiv_id":"2204.00989","n_code_links":1,"syntology":null},{"paper":"/paper/bert-assisted-semantic-annotation-correction","slug":"bert-assisted-semantic-annotation-correction","title":"BERT-Assisted Semantic Annotation Correction for Emotion-Related Questions","date":"2022-04-02","arxiv_id":"2204.00916","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-comparison-of-sentence-embeddings","title":"Efficient comparison of sentence embeddings","date":"2022-04-02","arxiv_id":"2204.00820","n_code_links":0,"syntology":null},{"paper":"/paper/analyzing-how-bert-performs-entity-matching","slug":"analyzing-how-bert-performs-entity-matching","title":"Analyzing how BERT performs entity matching","date":"2022-04-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/characterbert-and-self-teaching-for-improving","slug":"characterbert-and-self-teaching-for-improving","title":"CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos","date":"2022-04-01","arxiv_id":"2204.00716","n_code_links":1,"syntology":null},{"paper":null,"slug":"cyberbullying-detection-across-social-media","title":"Cyberbullying detection across social media platforms via platform-aware adversarial encoding","date":"2022-04-01","arxiv_id":"2204.00334","n_code_links":0,"syntology":null},{"paper":null,"slug":"effect-and-analysis-of-large-scale-language","title":"Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems","date":"2022-04-01","arxiv_id":"2204.00212","n_code_links":0,"syntology":null},{"paper":"/paper/feature-structure-distillation-for-bert-1","slug":"feature-structure-distillation-for-bert-1","title":"Feature Structure Distillation with Centered Kernel Alignment in BERT Transferring","date":"2022-04-01","arxiv_id":"2204.08922","n_code_links":1,"syntology":null},{"paper":"/paper/monarch-expressive-structured-matrices-for","slug":"monarch-expressive-structured-matrices-for","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","date":"2022-04-01","arxiv_id":"2204.00595","n_code_links":2,"syntology":{"ran":15,"of":15,"n_ran_checked":14,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 1 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hazyresearch/monarch"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"syntax-informed-question-answering-with","title":"Syntax-informed Question Answering with Heterogeneous Graph Transformer","date":"2022-04-01","arxiv_id":"2204.09655","n_code_links":0,"syntology":null},{"paper":"/paper/a-baseline-readability-model-for-cebuano","slug":"a-baseline-readability-model-for-cebuano","title":"A Baseline Readability Model for Cebuano","date":"2022-03-31","arxiv_id":"2203.17225","n_code_links":1,"syntology":null},{"paper":"/paper/a-character-level-span-based-model-for","slug":"a-character-level-span-based-model-for","title":"A Character-level Span-based Model for Mandarin Prosodic Structure Prediction","date":"2022-03-31","arxiv_id":"2203.16922","n_code_links":1,"syntology":null},{"paper":"/paper/catiss-an-intelligent-tool-for-categorizing","slug":"catiss-an-intelligent-tool-for-categorizing","title":"CatIss: An Intelligent Tool for Categorizing Issues Reports using Transformers","date":"2022-03-31","arxiv_id":"2203.17196","n_code_links":1,"syntology":null},{"paper":null,"slug":"create-a-benchmark-for-chinese-short-video-1","title":"CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation","date":"2022-03-31","arxiv_id":"2203.16763","n_code_links":0,"syntology":null},{"paper":null,"slug":"esgbert-language-model-to-help-with","title":"ESGBERT: Language Model to Help with Classification Tasks Related to Companies Environmental, Social, and Governance Practices","date":"2022-03-31","arxiv_id":"2203.16788","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-pre-trained-transformers-for","title":"Generative Pre-Trained Transformers for Biologically Inspired Design","date":"2022-03-31","arxiv_id":"2204.09714","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-pre-trained-language-models-for","title":"Leveraging pre-trained language models for conversational information seeking from text","date":"2022-03-31","arxiv_id":"2204.03542","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixed-phoneme-bert-improving-bert-with-mixed","title":"Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech","date":"2022-03-31","arxiv_id":"2203.17190","n_code_links":0,"syntology":null},{"paper":null,"slug":"incorporating-dynamic-semantics-into-pre","title":"Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment Analysis","date":"2022-03-30","arxiv_id":"2203.16369","n_code_links":0,"syntology":null}],"record_sha256":"ee3979af1df35fa07135e8ef63b68f6ce9152e4719a832fd2f29853da99bad0d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}