{"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/bert/papers/31","list_of":"/method/bert","method":"BERT","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":31,"pages_in_order":70,"rows_per_page":100,"rows":[3001,3100],"of":6938,"counts":{"archive_papers_tagged":6938,"with_a_code_link":2862,"where_syntology_ran_a_sample":640,"not_listed_spam_title":0,"listed":6938,"listed_where_code_ran":640,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":520,"every_run_a_failure_of_syntologys_instrument":120,"listed_with_a_run_with_no_instrument_failure":520,"listed_every_run_a_failure_of_syntologys_instrument":120,"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/bert","prev":"/method/bert/papers/30","next":"/method/bert/papers/32","papers":[{"paper":"/paper/understanding-int4-quantization-for","slug":"understanding-int4-quantization-for","title":"Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases","date":"2023-01-27","arxiv_id":"2301.12017","n_code_links":1,"syntology":null},{"paper":"/paper/a-benchmark-for-toxic-comment-classification","slug":"a-benchmark-for-toxic-comment-classification","title":"A benchmark for toxic comment classification on Civil Comments dataset","date":"2023-01-26","arxiv_id":"2301.11125","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-embedding-and-citation-network-analysis","title":"BERT-Embedding and Citation Network Analysis based Query Expansion Technique for Scholarly Search","date":"2023-01-26","arxiv_id":"2301.11069","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-stability-analysis-of-fine-tuning-a-pre","title":"A Stability Analysis of Fine-Tuning a Pre-Trained Model","date":"2023-01-24","arxiv_id":"2301.09820","n_code_links":0,"syntology":null},{"paper":null,"slug":"multitask-instruction-based-prompting-for","title":"Multitask Instruction-based Prompting for Fallacy Recognition","date":"2023-01-24","arxiv_id":"2301.09992","n_code_links":0,"syntology":null},{"paper":"/paper/injecting-the-bm25-score-as-text-improves","slug":"injecting-the-bm25-score-as-text-improves","title":"Injecting the BM25 Score as Text Improves BERT-Based Re-rankers","date":"2023-01-23","arxiv_id":"2301.09728","n_code_links":1,"syntology":null},{"paper":"/paper/stockemotions-discover-investor-emotions-for","slug":"stockemotions-discover-investor-emotions-for","title":"StockEmotions: Discover Investor Emotions for Financial Sentiment Analysis and Multivariate Time Series","date":"2023-01-23","arxiv_id":"2301.09279","n_code_links":2,"syntology":null},{"paper":null,"slug":"stress-test-for-bert-and-deep-models","title":"Stress Test for BERT and Deep Models: Predicting Words from Italian Poetry","date":"2023-01-21","arxiv_id":"2302.09303","n_code_links":0,"syntology":null},{"paper":"/paper/phoneme-level-bert-for-enhanced-prosody-of","slug":"phoneme-level-bert-for-enhanced-prosody-of","title":"Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions","date":"2023-01-20","arxiv_id":"2301.08810","n_code_links":2,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":null}},{"paper":null,"slug":"which-features-are-learned-by-codebert-an","title":"Which Features are Learned by CodeBert: An Empirical Study of the BERT-based Source Code Representation Learning","date":"2023-01-20","arxiv_id":"2301.08427","n_code_links":0,"syntology":null},{"paper":"/paper/an-error-guided-correction-model-for-chinese","slug":"an-error-guided-correction-model-for-chinese","title":"An Error-Guided Correction Model for Chinese Spelling Error Correction","date":"2023-01-16","arxiv_id":"2301.06323","n_code_links":1,"syntology":null},{"paper":"/paper/tedb-system-description-to-a-shared-task-on","slug":"tedb-system-description-to-a-shared-task-on","title":"TEDB System Description to a Shared Task on Euphemism Detection 2022","date":"2023-01-16","arxiv_id":"2301.06602","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-noise-robustness-for-spoken-content","title":"Improving Noise Robustness for Spoken Content Retrieval using Semi-supervised ASR and N-best Transcripts for BERT-based Ranking Models","date":"2023-01-15","arxiv_id":"2301.06056","n_code_links":0,"syntology":null},{"paper":"/paper/narrowbert-accelerating-masked-language-model","slug":"narrowbert-accelerating-masked-language-model","title":"NarrowBERT: Accelerating Masked Language Model Pretraining and Inference","date":"2023-01-11","arxiv_id":"2301.04761","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["lihaoxin2020/narrowbert"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"topics-in-contextualised-attention-embeddings","title":"Topics in Contextualised Attention Embeddings","date":"2023-01-11","arxiv_id":"2301.04339","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-sounds-the-death-knell-of","title":"Language Models sounds the Death Knell of Knowledge Graphs","date":"2023-01-10","arxiv_id":"2301.03980","n_code_links":0,"syntology":null},{"paper":"/paper/designing-bert-for-convolutional-networks","slug":"designing-bert-for-convolutional-networks","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","date":"2023-01-09","arxiv_id":"2301.03580","n_code_links":2,"syntology":{"ran":13,"of":14,"n_ran_checked":12,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["keyu-tian/spark"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"online-fake-review-detection-using-supervised","title":"Online Fake Review Detection Using Supervised Machine Learning And BERT Model","date":"2023-01-09","arxiv_id":"2301.03225","n_code_links":0,"syntology":null},{"paper":"/paper/app-review-driven-collaborative-bug-finding","slug":"app-review-driven-collaborative-bug-finding","title":"App Review Driven Collaborative Bug Finding","date":"2023-01-07","arxiv_id":"2301.02818","n_code_links":1,"syntology":null},{"paper":"/paper/rlas-biabc-a-reinforcement-learning-based","slug":"rlas-biabc-a-reinforcement-learning-based","title":"RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm","date":"2023-01-07","arxiv_id":"2301.02807","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-trajectory-word-alignments-for-video","title":"Learning Trajectory-Word Alignments for Video-Language Tasks","date":"2023-01-05","arxiv_id":"2301.01953","n_code_links":0,"syntology":null},{"paper":null,"slug":"pie-qg-paraphrased-information-extraction-for","title":"PIE-QG: Paraphrased Information Extraction for Unsupervised Question Generation from Small Corpora","date":"2023-01-03","arxiv_id":"2301.01064","n_code_links":0,"syntology":null},{"paper":null,"slug":"floods-relevancy-and-identification-of","title":"Floods Relevancy and Identification of Location from Twitter Posts using NLP Techniques","date":"2023-01-01","arxiv_id":"2301.00321","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-semantic-representations-combined","title":"Leveraging Semantic Representations Combined with Contextual Word Representations for Recognizing Textual Entailment in Vietnamese","date":"2023-01-01","arxiv_id":"2301.00422","n_code_links":0,"syntology":null},{"paper":null,"slug":"sentiment-analysis-of-covid-19-public","title":"Sentiment Analysis of COVID-19 Public Activity Restriction (PPKM) Impact using BERT Method","date":"2022-12-31","arxiv_id":"2301.00096","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-analysis-of-attention-via-the-lens-of","title":"An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models","date":"2022-12-30","arxiv_id":"2212.14852","n_code_links":0,"syntology":null},{"paper":null,"slug":"distant-reading-of-the-german-coalition-deal","title":"Distant Reading of the German Coalition Deal: Recognizing Policy Positions with BERT-based Text Classification","date":"2022-12-30","arxiv_id":"2212.14648","n_code_links":0,"syntology":null},{"paper":"/paper/cramming-training-a-language-model-on-a","slug":"cramming-training-a-language-model-on-a","title":"Cramming: Training a Language Model on a Single GPU in One Day","date":"2022-12-28","arxiv_id":"2212.14034","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, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jonasgeiping/cramming"],"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":"a-survey-on-knowledge-enhanced-pre-trained","title":"A Survey on Knowledge-Enhanced Pre-trained Language Models","date":"2022-12-27","arxiv_id":"2212.13428","n_code_links":0,"syntology":null},{"paper":"/paper/benchmark-for-uncertainty-robustness-in-self","slug":"benchmark-for-uncertainty-robustness-in-self","title":"Benchmark for Uncertainty & Robustness in Self-Supervised Learning","date":"2022-12-23","arxiv_id":"2212.12411","n_code_links":1,"syntology":null},{"paper":"/paper/finetuning-for-sarcasm-detection-with-a","slug":"finetuning-for-sarcasm-detection-with-a","title":"Finetuning for Sarcasm Detection with a Pruned Dataset","date":"2022-12-23","arxiv_id":"2212.12213","n_code_links":1,"syntology":null},{"paper":null,"slug":"camembert-cascading-assistant-mediated","title":"CAMeMBERT: Cascading Assistant-Mediated Multilingual BERT","date":"2022-12-22","arxiv_id":"2212.11456","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-the-prediction-of-disease-outcomes","title":"Enhancing the prediction of disease outcomes using electronic health records and pretrained deep learning models","date":"2022-12-22","arxiv_id":"2212.12067","n_code_links":0,"syntology":null},{"paper":"/paper/analyzing-semantic-faithfulness-of-language","slug":"analyzing-semantic-faithfulness-of-language","title":"Analyzing Semantic Faithfulness of Language Models via Input Intervention on Question Answering","date":"2022-12-21","arxiv_id":"2212.10696","n_code_links":1,"syntology":null},{"paper":"/paper/cross-linguistic-syntactic-difference-in","slug":"cross-linguistic-syntactic-difference-in","title":"Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?","date":"2022-12-21","arxiv_id":"2212.10879","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-efficient-visual-simplification-of","title":"Towards Efficient Visual Simplification of Computational Graphs in Deep Neural Networks","date":"2022-12-21","arxiv_id":"2212.10774","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-twitter-bert-approach-for-offensive","title":"A Twitter BERT Approach for Offensive Language Detection in Marathi","date":"2022-12-20","arxiv_id":"2212.10039","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-rule-neural-coreference-resolution","title":"Hybrid Rule-Neural Coreference Resolution System based on Actor-Critic Learning","date":"2022-12-20","arxiv_id":"2212.10087","n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-and-manipulating-the-personality","title":"Identifying and Manipulating the Personality Traits of Language Models","date":"2022-12-20","arxiv_id":"2212.10276","n_code_links":0,"syntology":null},{"paper":null,"slug":"in-and-out-of-domain-text-adversarial","title":"In and Out-of-Domain Text Adversarial Robustness via Label Smoothing","date":"2022-12-20","arxiv_id":"2212.10258","n_code_links":0,"syntology":null},{"paper":null,"slug":"parameter-efficient-zero-shot-transfer-for","title":"Parameter-efficient Zero-shot Transfer for Cross-Language Dense Retrieval with Adapters","date":"2022-12-20","arxiv_id":"2212.10448","n_code_links":0,"syntology":null},{"paper":"/paper/pretraining-without-attention","slug":"pretraining-without-attention","title":"Pretraining Without Attention","date":"2022-12-20","arxiv_id":"2212.10544","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["jxiw/bigs"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/do-conll-2003-named-entity-taggers-still-work","slug":"do-conll-2003-named-entity-taggers-still-work","title":"Do CoNLL-2003 Named Entity Taggers Still Work Well in 2023?","date":"2022-12-19","arxiv_id":"2212.09747","n_code_links":1,"syntology":null},{"paper":null,"slug":"enriching-relation-extraction-with-openie","title":"Enriching Relation Extraction with OpenIE","date":"2022-12-19","arxiv_id":"2212.09376","n_code_links":0,"syntology":null},{"paper":null,"slug":"less-is-more-parameter-free-text","title":"Less is More: Parameter-Free Text Classification with Gzip","date":"2022-12-19","arxiv_id":"2212.09410","n_code_links":0,"syntology":null},{"paper":null,"slug":"mantis-at-tsar-2022-shared-task-improved","title":"MANTIS at TSAR-2022 Shared Task: Improved Unsupervised Lexical Simplification with Pretrained Encoders","date":"2022-12-19","arxiv_id":"2212.09855","n_code_links":0,"syntology":null},{"paper":"/paper/bort-towards-explainable-neural-networks-with","slug":"bort-towards-explainable-neural-networks-with","title":"Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint","date":"2022-12-18","arxiv_id":"2212.09062","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":["zbr17/bort"],"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":"neural-coreference-resolution-based-on","title":"Neural Coreference Resolution based on Reinforcement Learning","date":"2022-12-18","arxiv_id":"2212.09028","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-rankers-for-effective-screening","title":"Neural Rankers for Effective Screening Prioritisation in Medical Systematic Review Literature Search","date":"2022-12-18","arxiv_id":"2212.09017","n_code_links":0,"syntology":null},{"paper":null,"slug":"legalrelectra-mixed-domain-language-modeling","title":"LegalRelectra: Mixed-domain Language Modeling for Long-range Legal Text Comprehension","date":"2022-12-16","arxiv_id":"2212.08204","n_code_links":0,"syntology":null},{"paper":null,"slug":"plansformer-generating-symbolic-plans-using","title":"Plansformer: Generating Symbolic Plans using Transformers","date":"2022-12-16","arxiv_id":"2212.08681","n_code_links":0,"syntology":null},{"paper":null,"slug":"poibert-a-transformer-based-model-for-the","title":"POIBERT: A Transformer-based Model for the Tour Recommendation Problem","date":"2022-12-16","arxiv_id":"2212.13900","n_code_links":0,"syntology":null},{"paper":"/paper/reco-reliable-causal-chain-reasoning-via","slug":"reco-reliable-causal-chain-reasoning-via","title":"ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks","date":"2022-12-16","arxiv_id":"2212.08322","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["waste-wood/reco"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"utilizing-distilbert-transformer-model-for","title":"Utilizing distilBert transformer model for sentiment classification of COVID-19's Persian open-text responses","date":"2022-12-16","arxiv_id":"2212.08407","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-pre-training-of-masked-language","slug":"efficient-pre-training-of-masked-language","title":"Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking","date":"2022-12-15","arxiv_id":"2212.07617","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":["koreamglee/concept-based-curriculum-masking"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/visually-augmented-pretrained-language-models","slug":"visually-augmented-pretrained-language-models","title":"Visually-augmented pretrained language models for NLP tasks without images","date":"2022-12-15","arxiv_id":"2212.07937","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-self-supervised-learning-with","slug":"efficient-self-supervised-learning-with","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","date":"2022-12-14","arxiv_id":"2212.07525","n_code_links":5,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["facebookresearch/fairseq"],"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":"explainability-of-text-processing-and","title":"Explainability of Text Processing and Retrieval Methods: A Critical Survey","date":"2022-12-14","arxiv_id":"2212.07126","n_code_links":0,"syntology":null},{"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":"/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}],"record_sha256":"c428a45e08b4a046f2af3a9eb61a87946dc344953986a0a05d00baec3c04778d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}