{"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/attention-dropout/papers/88","list_of":"/method/attention-dropout","method":"Attention Dropout","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":88,"pages_in_order":109,"rows_per_page":100,"rows":[8701,8800],"of":10892,"counts":{"archive_papers_tagged":10892,"with_a_code_link":4634,"where_syntology_ran_a_sample":1270,"not_listed_spam_title":0,"listed":10892,"listed_where_code_ran":1270,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1043,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1043,"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/attention-dropout","prev":"/method/attention-dropout/papers/87","next":"/method/attention-dropout/papers/89","papers":[{"paper":null,"slug":"skillbert-skilling-the-bert-to-classify-1","title":"SKILLBERT: “SKILLING” THE BERT TO CLASSIFY SKILLS!","date":"2021-03-08","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/syntax-bert-improving-pre-trained","slug":"syntax-bert-improving-pre-trained","title":"Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees","date":"2021-03-07","arxiv_id":"2103.04350","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-pretrained-multilingual-bert","title":"Fine-tuning Pretrained Multilingual BERT Model for Indonesian Aspect-based Sentiment Analysis","date":"2021-03-05","arxiv_id":"2103.03732","n_code_links":0,"syntology":null},{"paper":null,"slug":"malbert-using-transformers-for-cybersecurity","title":"MalBERT: Using Transformers for Cybersecurity and Malicious Software Detection","date":"2021-03-05","arxiv_id":"2103.03806","n_code_links":0,"syntology":null},{"paper":null,"slug":"non-invasive-self-attention-for-side","title":"Non-invasive Self-attention for Side Information Fusion in Sequential Recommendation","date":"2021-03-05","arxiv_id":"2103.03578","n_code_links":0,"syntology":null},{"paper":null,"slug":"hardware-acceleration-of-fully-quantized-bert","title":"Hardware Acceleration of Fully Quantized BERT for Efficient Natural Language Processing","date":"2021-03-04","arxiv_id":"2103.02800","n_code_links":0,"syntology":null},{"paper":null,"slug":"few-shot-learning-for-slot-tagging-with","title":"Few-shot Learning for Slot Tagging with Attentive Relational Network","date":"2021-03-03","arxiv_id":"2103.02333","n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-language-understanding-for","title":"Natural Language Understanding for Argumentative Dialogue Systems in the Opinion Building Domain","date":"2021-03-03","arxiv_id":"2103.02691","n_code_links":0,"syntology":null},{"paper":null,"slug":"decomposing-lexical-and-compositional-syntax","title":"Disentangling Syntax and Semantics in the Brain with Deep Networks","date":"2021-03-02","arxiv_id":"2103.01620","n_code_links":0,"syntology":null},{"paper":null,"slug":"hate-towards-the-political-opponent-a-twitter","title":"Hate Towards the Political Opponent: A Twitter Corpus Study of the 2020 US Elections on the Basis of Offensive Speech and Stance Detection","date":"2021-03-02","arxiv_id":"2103.01664","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-based-knowledge-extraction-method-of","title":"BERT-based knowledge extraction method of unstructured domain text","date":"2021-03-01","arxiv_id":"2103.00728","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-based-patent-novelty-search-by-training","title":"BERT based patent novelty search by training claims to their own description","date":"2021-03-01","arxiv_id":"2103.01126","n_code_links":0,"syntology":null},{"paper":null,"slug":"combat-covid-19-infodemic-using-explainable","title":"Combat COVID-19 Infodemic Using Explainable Natural Language Processing Models","date":"2021-03-01","arxiv_id":"2103.00747","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-document-summarization-in-a-low-resource","title":"Long Document Summarization in a Low Resource Setting using Pretrained Language Models","date":"2021-03-01","arxiv_id":"2103.00751","n_code_links":0,"syntology":null},{"paper":"/paper/nlp-cuet-dravidianlangtech-eacl2021-offensive","slug":"nlp-cuet-dravidianlangtech-eacl2021-offensive","title":"NLP-CUET@DravidianLangTech-EACL2021: Offensive Language Detection from Multilingual Code-Mixed Text using Transformers","date":"2021-02-28","arxiv_id":"2103.00455","n_code_links":1,"syntology":null},{"paper":"/paper/nlp-cuet-lt-edi-eacl2021-multilingual-code","slug":"nlp-cuet-lt-edi-eacl2021-multilingual-code","title":"NLP-CUET@LT-EDI-EACL2021: Multilingual Code-Mixed Hope Speech Detection using Cross-lingual Representation Learner","date":"2021-02-28","arxiv_id":"2103.00464","n_code_links":1,"syntology":null},{"paper":"/paper/covid-19-tweets-analysis-through-transformer","slug":"covid-19-tweets-analysis-through-transformer","title":"COVID-19 Tweets Analysis through Transformer Language Models","date":"2021-02-27","arxiv_id":"2103.00199","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-in-transformer","slug":"transformer-in-transformer","title":"Transformer in Transformer","date":"2021-02-27","arxiv_id":"2103.00112","n_code_links":12,"syntology":{"ran":16,"of":24,"n_ran_checked":15,"n_instrument":1,"unverified":8,"pointer_only":5,"phrase":"16 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 1 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","official":{"repos":["huawei-noah/CV-backbones"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"transformers-with-competitive-ensembles-of-1","title":"Transformers with Competitive Ensembles of Independent Mechanisms","date":"2021-02-27","arxiv_id":"2103.00336","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-transfer-learning-for-finding","title":"Multi-task transfer learning for finding actionable information from crisis-related messages on social media","date":"2021-02-26","arxiv_id":"2102.13395","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-based-acronym-disambiguation-with","title":"BERT-based Acronym Disambiguation with Multiple Training Strategies","date":"2021-02-25","arxiv_id":"2103.00488","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-aware-emotion-agnostic-or-automatic","title":"Emotion-Aware, Emotion-Agnostic, or Automatic: Corpus Creation Strategies to Obtain Cognitive Event Appraisal Annotations","date":"2021-02-25","arxiv_id":"2102.12858","n_code_links":0,"syntology":null},{"paper":null,"slug":"pharmke-knowledge-extraction-platform-for","title":"PharmKE: Knowledge Extraction Platform for Pharmaceutical Texts using Transfer Learning","date":"2021-02-25","arxiv_id":"2102.13139","n_code_links":0,"syntology":null},{"paper":"/paper/sentiment-analysis-of-persian-english-code","slug":"sentiment-analysis-of-persian-english-code","title":"Sentiment Analysis of Persian-English Code-mixed Texts","date":"2021-02-25","arxiv_id":"2102.12700","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-universal-language-model-to-downstream","title":"From Universal Language Model to Downstream Task: Improving RoBERTa-Based Vietnamese Hate Speech Detection","date":"2021-02-24","arxiv_id":"2102.12162","n_code_links":0,"syntology":null},{"paper":null,"slug":"hopeful-men-lt-edi-eacl2021-hope-speech","title":"Hopeful_Men@LT-EDI-EACL2021: Hope Speech Detection Using Indic Transliteration and Transformers","date":"2021-02-24","arxiv_id":"2102.12082","n_code_links":0,"syntology":null},{"paper":"/paper/lrg-at-semeval-2021-task-4-improving-reading","slug":"lrg-at-semeval-2021-task-4-improving-reading","title":"LRG at SemEval-2021 Task 4: Improving Reading Comprehension with Abstract Words using Augmentation, Linguistic Features and Voting","date":"2021-02-24","arxiv_id":"2102.12255","n_code_links":1,"syntology":null},{"paper":"/paper/nlrg-at-semeval-2021-task-5-toxic-spans","slug":"nlrg-at-semeval-2021-task-5-toxic-spans","title":"NLRG at SemEval-2021 Task 5: Toxic Spans Detection Leveraging BERT-based Token Classification and Span Prediction Techniques","date":"2021-02-24","arxiv_id":"2102.12254","n_code_links":1,"syntology":null},{"paper":"/paper/pada-a-prompt-based-autoregressive-approach","slug":"pada-a-prompt-based-autoregressive-approach","title":"PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains","date":"2021-02-24","arxiv_id":"2102.12206","n_code_links":1,"syntology":null},{"paper":null,"slug":"task-specific-pre-training-and-cross-lingual","title":"Task-Specific Pre-Training and Cross Lingual Transfer for Code-Switched Data","date":"2021-02-24","arxiv_id":"2102.12407","n_code_links":0,"syntology":null},{"paper":null,"slug":"minimally-supervised-structure-rich-text","title":"Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks","date":"2021-02-23","arxiv_id":"2102.11479","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-and-transferable-anomaly-detection-in","title":"Robust and Transferable Anomaly Detection in Log Data using Pre-Trained Language Models","date":"2021-02-23","arxiv_id":"2102.11570","n_code_links":0,"syntology":null},{"paper":"/paper/visualchexbert-addressing-the-discrepancy","slug":"visualchexbert-addressing-the-discrepancy","title":"VisualCheXbert: Addressing the Discrepancy Between Radiology Report Labels and Image Labels","date":"2021-02-23","arxiv_id":"2102.11467","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":["stanfordmlgroup/VisualCheXbert"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/do-we-really-need-explicit-position-encodings","slug":"do-we-really-need-explicit-position-encodings","title":"Conditional Positional Encodings for Vision Transformers","date":"2021-02-22","arxiv_id":"2102.10882","n_code_links":2,"syntology":null},{"paper":"/paper/evaluating-contextualized-language-models-for","slug":"evaluating-contextualized-language-models-for","title":"Evaluating Contextualized Language Models for Hungarian","date":"2021-02-22","arxiv_id":"2102.10848","n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-human-readable-transcript-for","title":"Generating Human Readable Transcript for Automatic Speech Recognition with Pre-trained Language Model","date":"2021-02-22","arxiv_id":"2102.11114","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixup-training-leads-to-reduced-overfitting","title":"MixUp Training Leads to Reduced Overfitting and Improved Calibration for the Transformer Architecture","date":"2021-02-22","arxiv_id":"2102.11402","n_code_links":0,"syntology":null},{"paper":"/paper/parallelizing-legendre-memory-unit-training","slug":"parallelizing-legendre-memory-unit-training","title":"Parallelizing Legendre Memory Unit Training","date":"2021-02-22","arxiv_id":"2102.11417","n_code_links":2,"syntology":null},{"paper":null,"slug":"rubert-a-bilingual-roman-urdu-bert-using","title":"RUBERT: A Bilingual Roman Urdu BERT Using Cross Lingual Transfer Learning","date":"2021-02-22","arxiv_id":"2102.11278","n_code_links":0,"syntology":null},{"paper":"/paper/using-prior-knowledge-to-guide-bert-s","slug":"using-prior-knowledge-to-guide-bert-s","title":"Using Prior Knowledge to Guide BERT's Attention in Semantic Textual Matching Tasks","date":"2021-02-22","arxiv_id":"2102.10934","n_code_links":1,"syntology":null},{"paper":null,"slug":"pre-training-bert-on-arabic-tweets-practical","title":"Pre-Training BERT on Arabic Tweets: Practical Considerations","date":"2021-02-21","arxiv_id":"2102.10684","n_code_links":0,"syntology":null},{"paper":null,"slug":"web-based-application-for-detecting","title":"Web-based Application for Detecting Indonesian Clickbait Headlines using IndoBERT","date":"2021-02-21","arxiv_id":"2102.10601","n_code_links":0,"syntology":null},{"paper":"/paper/calibrate-before-use-improving-few-shot","slug":"calibrate-before-use-improving-few-shot","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","date":"2021-02-19","arxiv_id":"2102.09690","n_code_links":5,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"0 ran · 4 unverified","official":{"repos":["tonyzhaozh/few-shot-learning"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":null,"slug":"learning-dynamic-bert-via-trainable-gate","title":"Learning Dynamic BERT via Trainable Gate Variables and a Bi-modal Regularizer","date":"2021-02-19","arxiv_id":"2102.09727","n_code_links":0,"syntology":null},{"paper":"/paper/towards-emotion-recognition-in-hindi-english","slug":"towards-emotion-recognition-in-hindi-english","title":"Towards Emotion Recognition in Hindi-English Code-Mixed Data: A Transformer Based Approach","date":"2021-02-19","arxiv_id":"2102.09943","n_code_links":1,"syntology":null},{"paper":"/paper/using-transformer-based-ensemble-learning-to","slug":"using-transformer-based-ensemble-learning-to","title":"Using Transformer based Ensemble Learning to classify Scientific Articles","date":"2021-02-19","arxiv_id":"2102.09991","n_code_links":2,"syntology":null},{"paper":"/paper/analysis-of-contextual-and-non-contextual","slug":"analysis-of-contextual-and-non-contextual","title":"Analysis Of Contextual and Non-Contextual Word Embedding Models For Hindi NER With Web Application For Data Collection","date":"2021-02-18","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/quiz-style-question-generation-for-news","slug":"quiz-style-question-generation-for-news","title":"Quiz-Style Question Generation for News Stories","date":"2021-02-18","arxiv_id":"2102.09094","n_code_links":2,"syntology":null},{"paper":"/paper/training-microsoft-news-recommenders-with","slug":"training-microsoft-news-recommenders-with","title":"Training Large-Scale News Recommenders with Pretrained Language Models in the Loop","date":"2021-02-18","arxiv_id":"2102.09268","n_code_links":1,"syntology":null},{"paper":null,"slug":"unibuckernel-geolocating-swiss-german-jodels","title":"UnibucKernel: Geolocating Swiss German Jodels Using Ensemble Learning","date":"2021-02-18","arxiv_id":"2102.09379","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-query-resolution-and-reading","title":"Leveraging Query Resolution and Reading Comprehension for Conversational Passage Retrieval","date":"2021-02-17","arxiv_id":"2102.08795","n_code_links":0,"syntology":null},{"paper":"/paper/scidr-at-sdu-2020-ideas-identifying-and","slug":"scidr-at-sdu-2020-ideas-identifying-and","title":"SciDr at SDU-2020: IDEAS -- Identifying and Disambiguating Everyday Acronyms for Scientific Domain","date":"2021-02-17","arxiv_id":"2102.08818","n_code_links":2,"syntology":null},{"paper":"/paper/tcn-table-convolutional-network-for-web-table","slug":"tcn-table-convolutional-network-for-web-table","title":"TCN: Table Convolutional Network for Web Table Interpretation","date":"2021-02-17","arxiv_id":"2102.09460","n_code_links":1,"syntology":null},{"paper":null,"slug":"theaitre-1-0-interactive-generation-of","title":"THEaiTRE 1.0: Interactive generation of theatre play scripts","date":"2021-02-17","arxiv_id":"2102.08892","n_code_links":0,"syntology":null},{"paper":"/paper/coco-lm-correcting-and-contrasting-text","slug":"coco-lm-correcting-and-contrasting-text","title":"COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining","date":"2021-02-16","arxiv_id":"2102.08473","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":1,"n_instrument":4,"unverified":1,"pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/coco-lm"],"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/exploring-transformers-in-natural-language","slug":"exploring-transformers-in-natural-language","title":"Exploring Transformers in Natural Language Generation: GPT, BERT, and XLNet","date":"2021-02-16","arxiv_id":"2102.08036","n_code_links":1,"syntology":null},{"paper":null,"slug":"have-attention-heads-in-bert-learned","title":"Have Attention Heads in BERT Learned Constituency Grammar?","date":"2021-02-16","arxiv_id":"2102.07926","n_code_links":0,"syntology":null},{"paper":"/paper/non-autoregressive-text-generation-with-pre","slug":"non-autoregressive-text-generation-with-pre","title":"Non-Autoregressive Text Generation with Pre-trained Language Models","date":"2021-02-16","arxiv_id":"2102.08220","n_code_links":1,"syntology":null},{"paper":"/paper/terapipe-token-level-pipeline-parallelism-for","slug":"terapipe-token-level-pipeline-parallelism-for","title":"TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models","date":"2021-02-16","arxiv_id":"2102.07988","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":3,"n_instrument":4,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zhuohan123/terapipe"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/dobf-a-deobfuscation-pre-training-objective","slug":"dobf-a-deobfuscation-pre-training-objective","title":"DOBF: A Deobfuscation Pre-Training Objective for Programming Languages","date":"2021-02-15","arxiv_id":"2102.07492","n_code_links":2,"syntology":null},{"paper":null,"slug":"fast-end-to-end-speech-recognition-via-non","title":"Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT","date":"2021-02-15","arxiv_id":"2102.07594","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-customer-transaction-classification","title":"Improved Customer Transaction Classification using Semi-Supervised Knowledge Distillation","date":"2021-02-15","arxiv_id":"2102.07635","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-programming-for-large-language-models","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","date":"2021-02-15","arxiv_id":"2102.07350","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-corruptive-force-of-ai-generated-advice","title":"The corruptive force of AI-generated advice","date":"2021-02-15","arxiv_id":"2102.07536","n_code_links":0,"syntology":null},{"paper":null,"slug":"within-document-event-coreference-with-bert","title":"Within-Document Event Coreference with BERT-Based Contextualized Representations","date":"2021-02-15","arxiv_id":"2102.09600","n_code_links":0,"syntology":null},{"paper":"/paper/indicnlp-kgp-at-dravidianlangtech-eacl2021","slug":"indicnlp-kgp-at-dravidianlangtech-eacl2021","title":"indicnlp@kgp at DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Languages","date":"2021-02-14","arxiv_id":"2102.07150","n_code_links":1,"syntology":null},{"paper":"/paper/indicnlp-kgp-at-dravidianlangtech-eacl2021-1","slug":"indicnlp-kgp-at-dravidianlangtech-eacl2021-1","title":"indicnlp@ kgp at DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Languages","date":"2021-02-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/characterizing-english-variation-across","slug":"characterizing-english-variation-across","title":"Characterizing English Variation across Social Media Communities with BERT","date":"2021-02-12","arxiv_id":"2102.06820","n_code_links":1,"syntology":null},{"paper":null,"slug":"dancing-along-battery-enabling-transformer","title":"Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices","date":"2021-02-12","arxiv_id":"2102.06336","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-precision-analog-computing-for-neural","slug":"dynamic-precision-analog-computing-for-neural","title":"Dynamic Precision Analog Computing for Neural Networks","date":"2021-02-12","arxiv_id":"2102.06365","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-classic-and-neural-lexical","slug":"exploring-classic-and-neural-lexical","title":"Exploring Classic and Neural Lexical Translation Models for Information Retrieval: Interpretability, Effectiveness, and Efficiency Benefits","date":"2021-02-12","arxiv_id":"2102.06815","n_code_links":2,"syntology":null},{"paper":null,"slug":"multiversal-views-on-language-models","title":"Multiversal views on language models","date":"2021-02-12","arxiv_id":"2102.06391","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-inference-performance-of","title":"Optimizing Inference Performance of Transformers on CPUs","date":"2021-02-12","arxiv_id":"2102.06621","n_code_links":0,"syntology":null},{"paper":"/paper/augpt-dialogue-with-pre-trained-language","slug":"augpt-dialogue-with-pre-trained-language","title":"AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models","date":"2021-02-09","arxiv_id":"2102.05126","n_code_links":1,"syntology":null},{"paper":null,"slug":"newsbert-distilling-pre-trained-language","title":"NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application","date":"2021-02-09","arxiv_id":"2102.04887","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-approach-for-arabic","title":"Transfer Learning Approach for Arabic Offensive Language Detection System -- BERT-Based Model","date":"2021-02-09","arxiv_id":"2102.05708","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hybrid-task-oriented-dialog-system-with","title":"A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining","date":"2021-02-08","arxiv_id":"2102.04506","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-fake-cyber-threat-intelligence","title":"Generating Fake Cyber Threat Intelligence Using Transformer-Based Models","date":"2021-02-08","arxiv_id":"2102.04351","n_code_links":0,"syntology":null},{"paper":"/paper/how-true-is-gpt-2-an-empirical-analysis-of","slug":"how-true-is-gpt-2-an-empirical-analysis-of","title":"Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models","date":"2021-02-08","arxiv_id":"2102.04130","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":0,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["oxai/intersectional_gpt2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/spoiler-alert-using-natural-language","slug":"spoiler-alert-using-natural-language","title":"Spoiler Alert: Using Natural Language Processing to Detect Spoilers in Book Reviews","date":"2021-02-07","arxiv_id":"2102.03882","n_code_links":1,"syntology":null},{"paper":null,"slug":"jointly-improving-language-understanding-and","title":"Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labeling","date":"2021-02-06","arxiv_id":"2102.03551","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-data-to-text-generation-with-lm-based","title":"Neural Data-to-Text Generation with LM-based Text Augmentation","date":"2021-02-06","arxiv_id":"2102.03556","n_code_links":0,"syntology":null},{"paper":"/paper/pipetransformer-automated-elastic-pipelining","slug":"pipetransformer-automated-elastic-pipelining","title":"PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers","date":"2021-02-05","arxiv_id":"2102.03161","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":["Distributed-AI/PipeTransformer"],"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/rpbert-a-text-image-relation-propagation","slug":"rpbert-a-text-image-relation-propagation","title":"RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER","date":"2021-02-05","arxiv_id":"2102.02967","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-emails-and-drafting-responses","title":"Understanding Emails and Drafting Responses -- An Approach Using GPT-3","date":"2021-02-05","arxiv_id":"2102.03062","n_code_links":0,"syntology":null},{"paper":"/paper/1-bit-adam-communication-efficient-large","slug":"1-bit-adam-communication-efficient-large","title":"1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed","date":"2021-02-04","arxiv_id":"2102.02888","n_code_links":2,"syntology":null},{"paper":"/paper/hierarchical-multi-head-attentive-network-for","slug":"hierarchical-multi-head-attentive-network-for","title":"Hierarchical Multi-head Attentive Network for Evidence-aware Fake News Detection","date":"2021-02-04","arxiv_id":"2102.02680","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-the-capabilities-limitations","title":"Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models","date":"2021-02-04","arxiv_id":"2102.02503","n_code_links":0,"syntology":null},{"paper":null,"slug":"bootstrapping-multilingual-amr-with","title":"Bootstrapping Multilingual AMR with Contextual Word Alignments","date":"2021-02-03","arxiv_id":"2102.02189","n_code_links":0,"syntology":null},{"paper":null,"slug":"hebert-hebemo-a-hebrew-bert-model-and-a-tool","title":"HeBERT & HebEMO: a Hebrew BERT Model and a Tool for Polarity Analysis and Emotion Recognition","date":"2021-02-03","arxiv_id":"2102.01909","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-transfer-learning-with-transformers","title":"Introduction to Neural Transfer Learning with Transformers for Social Science Text Analysis","date":"2021-02-03","arxiv_id":"2102.02111","n_code_links":0,"syntology":null},{"paper":"/paper/autofreeze-automatically-freezing-model","slug":"autofreeze-automatically-freezing-model","title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning","date":"2021-02-02","arxiv_id":"2102.01386","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["uw-mad-dash/AutoFreeze"],"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":["unlocated"]}}},{"paper":null,"slug":"clickbait-headline-detection-in-indonesian","title":"Clickbait Headline Detection in Indonesian News Sites using Multilingual Bidirectional Encoder Representations from Transformers (M-BERT)","date":"2021-02-02","arxiv_id":"2102.01497","n_code_links":0,"syntology":null},{"paper":"/paper/improving-distantly-supervised-relation-3","slug":"improving-distantly-supervised-relation-3","title":"Improving Distantly-Supervised Relation Extraction through BERT-based Label & Instance Embeddings","date":"2021-02-01","arxiv_id":"2102.01156","n_code_links":1,"syntology":null},{"paper":null,"slug":"is-depression-related-to-cannabis-a-knowledge","title":"\"Is depression related to cannabis?\": A knowledge-infused model for Entity and Relation Extraction with Limited Supervision","date":"2021-02-01","arxiv_id":"2102.01222","n_code_links":0,"syntology":null},{"paper":null,"slug":"polyphone-disambiguition-in-mandarin-chinese","title":"Polyphone Disambiguation in Mandarin Chinese with Semi-Supervised Learning","date":"2021-02-01","arxiv_id":"2102.00621","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-federated-learning-for-fine-tuning-of","title":"Scaling Federated Learning for Fine-tuning of Large Language Models","date":"2021-02-01","arxiv_id":"2102.00875","n_code_links":0,"syntology":null},{"paper":"/paper/sj-aj-dravidianlangtech-eacl2021-task","slug":"sj-aj-dravidianlangtech-eacl2021-task","title":"SJ_AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification","date":"2021-02-01","arxiv_id":"2102.01051","n_code_links":1,"syntology":null},{"paper":"/paper/text-to-hashtag-generation-using-seq2seq","slug":"text-to-hashtag-generation-using-seq2seq","title":"Text-to-hashtag Generation using Seq2seq Learning","date":"2021-02-01","arxiv_id":"2102.00904","n_code_links":1,"syntology":null},{"paper":"/paper/re-reproducing-learning-to-deceive-with","slug":"re-reproducing-learning-to-deceive-with","title":"[Re] Reproducing Learning to Deceive With Attention-Based Explanations","date":"2021-01-31","arxiv_id":null,"n_code_links":1,"syntology":null}],"record_sha256":"f1a08b88f46e01a4a51f1fc1594f2cc7f7a36ad6f559f05c65d7451eb972ccef","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}