{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/linear-warmup-with-cosine-annealing/papers/36","list_of":"/method/linear-warmup-with-cosine-annealing","method":"Linear Warmup With Cosine Annealing","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":36,"pages_in_order":38,"rows_per_page":100,"rows":[3501,3600],"of":3797,"counts":{"archive_papers_tagged":3797,"with_a_code_link":1655,"where_syntology_ran_a_sample":602,"not_listed_spam_title":0,"listed":3797,"listed_where_code_ran":602,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":490,"every_run_a_failure_of_syntologys_instrument":112,"listed_with_a_run_with_no_instrument_failure":490,"listed_every_run_a_failure_of_syntologys_instrument":112,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/linear-warmup-with-cosine-annealing","prev":"/method/linear-warmup-with-cosine-annealing/papers/35","next":"/method/linear-warmup-with-cosine-annealing/papers/37","papers":[{"paper":null,"slug":"ki-bert-infusing-knowledge-context-for-better","title":"KI-BERT: Infusing Knowledge Context for Better Language and Domain Understanding","date":"2021-04-09","arxiv_id":"2104.08145","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-aware-graph-enhanced-gpt-2-for","slug":"knowledge-aware-graph-enhanced-gpt-2-for","title":"Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking","date":"2021-04-09","arxiv_id":"2104.04466","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-gpt-2-to-create-synthetic-data-to","title":"Using GPT-2 to Create Synthetic Data to Improve the Prediction Performance of NLP Machine Learning Classification Models","date":"2021-04-02","arxiv_id":"2104.10658","n_code_links":0,"syntology":null},{"paper":"/paper/russian-paraphrasers-paraphrase-with","slug":"russian-paraphrasers-paraphrase-with","title":"Russian Paraphrasers: Paraphrase with Transformers","date":"2021-04-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"automatic-graph-partitioning-for-very-large","title":"Automatic Graph Partitioning for Very Large-scale Deep Learning","date":"2021-03-30","arxiv_id":"2103.16063","n_code_links":0,"syntology":null},{"paper":"/paper/fastmoe-a-fast-mixture-of-expert-training","slug":"fastmoe-a-fast-mixture-of-expert-training","title":"FastMoE: A Fast Mixture-of-Expert Training System","date":"2021-03-24","arxiv_id":"2103.13262","n_code_links":3,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["davidmrau/mixture-of-experts","laekov/fastmoe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"thinking-aloud-dynamic-context-generation","title":"Thinking Aloud: Dynamic Context Generation Improves Zero-Shot Reasoning Performance of GPT-2","date":"2021-03-24","arxiv_id":"2103.13033","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-hate-speech-with-gpt-3","slug":"detecting-hate-speech-with-gpt-3","title":"Detecting Hate Speech with GPT-3","date":"2021-03-23","arxiv_id":"2103.12407","n_code_links":2,"syntology":null},{"paper":null,"slug":"the-nlp-cookbook-modern-recipes-for","title":"The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures","date":"2021-03-23","arxiv_id":"2104.10640","n_code_links":0,"syntology":null},{"paper":null,"slug":"play-the-shannon-game-with-language-models-a","title":"Play the Shannon Game With Language Models: A Human-Free Approach to Summary Evaluation","date":"2021-03-19","arxiv_id":"2103.10918","n_code_links":0,"syntology":null},{"paper":"/paper/all-nlp-tasks-are-generation-tasks-a-general","slug":"all-nlp-tasks-are-generation-tasks-a-general","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","date":"2021-03-18","arxiv_id":"2103.10360","n_code_links":8,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["THUDM/GLM"],"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/gpt-understands-too","slug":"gpt-understands-too","title":"GPT Understands, Too","date":"2021-03-18","arxiv_id":"2103.10385","n_code_links":10,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["THUDM/P-tuning"],"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":["listed","official"]}}},{"paper":"/paper/language-models-have-a-moral-dimension","slug":"language-models-have-a-moral-dimension","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","date":"2021-03-08","arxiv_id":"2103.11790","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":["ml-research/MoRT_NMI"],"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":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":"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":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":"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/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":"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/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":"/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":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":"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":"/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":"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":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":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":null,"slug":"adaptive-semiparametric-language-models","title":"Adaptive Semiparametric Language Models","date":"2021-02-04","arxiv_id":"2102.02557","n_code_links":0,"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":"/paper/pitfalls-of-static-language-modelling","slug":"pitfalls-of-static-language-modelling","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","date":"2021-02-03","arxiv_id":"2102.01951","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":"synthesizing-monolingual-data-for-neural","title":"Synthesizing Monolingual Data for Neural Machine Translation","date":"2021-01-29","arxiv_id":"2101.12462","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-transformer-model-for-detecting-arabic","title":"BERT Transformer model for Detecting Arabic GPT2 Auto-Generated Tweets","date":"2021-01-22","arxiv_id":"2101.09345","n_code_links":0,"syntology":null},{"paper":"/paper/towards-facilitating-empathic-conversations","slug":"towards-facilitating-empathic-conversations","title":"Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach","date":"2021-01-19","arxiv_id":"2101.07714","n_code_links":1,"syntology":null},{"paper":"/paper/persistent-anti-muslim-bias-in-large-language","slug":"persistent-anti-muslim-bias-in-large-language","title":"Persistent Anti-Muslim Bias in Large Language Models","date":"2021-01-14","arxiv_id":"2101.05783","n_code_links":1,"syntology":null},{"paper":null,"slug":"adding-recurrence-to-pretrained-transformers-1","title":"Adding Recurrence to Pretrained Transformers","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cluster-former-clustering-based-sparse-1","title":"Cluster-Former: Clustering-based Sparse Transformer for Question Answering","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"how-multipurpose-are-language-models","title":"How Multipurpose Are Language Models?","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ketg-a-knowledge-enhanced-text-generation","title":"KETG: A Knowledge Enhanced Text Generation Framework","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/polyjuice-automated-general-purpose","slug":"polyjuice-automated-general-purpose","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","date":"2021-01-01","arxiv_id":"2101.00288","n_code_links":1,"syntology":null},{"paper":"/paper/prefix-tuning-optimizing-continuous-prompts","slug":"prefix-tuning-optimizing-continuous-prompts","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","date":"2021-01-01","arxiv_id":"2101.00190","n_code_links":13,"syntology":{"ran":4,"of":6,"n_ran_checked":2,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["XiangLi1999/PrefixTuning"],"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":"pretrain-knowledge-aware-language-models","title":"Pretrain Knowledge-Aware Language Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/subformer-a-parameter-reduced-transformer","slug":"subformer-a-parameter-reduced-transformer","title":"Subformer: A Parameter Reduced Transformer","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/visualsparta-sparse-transformer-fragment","slug":"visualsparta-sparse-transformer-fragment","title":"VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words","date":"2021-01-01","arxiv_id":"2101.00265","n_code_links":1,"syntology":null},{"paper":"/paper/warp-word-level-adversarial-reprogramming","slug":"warp-word-level-adversarial-reprogramming","title":"WARP: Word-level Adversarial ReProgramming","date":"2021-01-01","arxiv_id":"2101.00121","n_code_links":1,"syntology":null},{"paper":null,"slug":"conditional-generation-of-temporally-ordered","title":"Conditional Generation of Temporally-ordered Event Sequences","date":"2020-12-31","arxiv_id":"2012.15786","n_code_links":0,"syntology":null},{"paper":"/paper/directed-beam-search-plug-and-play-lexically","slug":"directed-beam-search-plug-and-play-lexically","title":"Directed Beam Search: Plug-and-Play Lexically Constrained Language Generation","date":"2020-12-31","arxiv_id":"2012.15416","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dapascual/DirectedBeamSearch"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/making-pre-trained-language-models-better-few","slug":"making-pre-trained-language-models-better-few","title":"Making Pre-trained Language Models Better Few-shot Learners","date":"2020-12-31","arxiv_id":"2012.15723","n_code_links":9,"syntology":{"ran":2,"of":9,"n_ran_checked":2,"n_instrument":0,"unverified":7,"pointer_only":7,"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) · 7 unverified","official":{"repos":["princeton-nlp/LM-BFF"],"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/the-pile-an-800gb-dataset-of-diverse-text-for","slug":"the-pile-an-800gb-dataset-of-diverse-text-for","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","date":"2020-12-31","arxiv_id":"2101.00027","n_code_links":22,"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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["EleutherAI/The-Pile"],"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/robust-dialogue-utterance-rewriting-as","slug":"robust-dialogue-utterance-rewriting-as","title":"Robust Dialogue Utterance Rewriting as Sequence Tagging","date":"2020-12-29","arxiv_id":"2012.14535","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncertainty-and-surprisal-jointly-deliver-the","title":"Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition","date":"2020-12-22","arxiv_id":"2012.12007","n_code_links":0,"syntology":null},{"paper":null,"slug":"controllable-and-contextualised-writing-tool","title":"Breaking Writer's Block: Low-cost Fine-tuning of Natural Language Generation Models","date":"2020-12-19","arxiv_id":"2101.03216","n_code_links":0,"syntology":null},{"paper":null,"slug":"query-expansion-with-artificially-generated","title":"Query expansion with artificially generated texts","date":"2020-12-16","arxiv_id":"2012.08787","n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-linformer-with-a-modified-self","title":"Revisiting Linformer with a modified self-attention with linear complexity","date":"2020-12-16","arxiv_id":"2101.10277","n_code_links":0,"syntology":null},{"paper":"/paper/recipenlg-a-cooking-recipes-dataset-for-semi","slug":"recipenlg-a-cooking-recipes-dataset-for-semi","title":"RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation","date":"2020-12-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/extracting-training-data-from-large-language","slug":"extracting-training-data-from-large-language","title":"Extracting Training Data from Large Language Models","date":"2020-12-14","arxiv_id":"2012.07805","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ftramer/LM_Memorization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hardware-beyond-backpropagation-a-photonic-co","title":"Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignment","date":"2020-12-11","arxiv_id":"2012.06373","n_code_links":0,"syntology":null},{"paper":"/paper/as-good-as-new-how-to-successfully-recycle","slug":"as-good-as-new-how-to-successfully-recycle","title":"As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages","date":"2020-12-10","arxiv_id":"2012.05628","n_code_links":1,"syntology":null},{"paper":"/paper/towards-neural-programming-interfaces-1","slug":"towards-neural-programming-interfaces-1","title":"Towards Neural Programming Interfaces","date":"2020-12-10","arxiv_id":"2012.05983","n_code_links":1,"syntology":null},{"paper":"/paper/cx-db8-a-queryable-extractive-summarizer-and","slug":"cx-db8-a-queryable-extractive-summarizer-and","title":"CX DB8: A queryable extractive summarizer and semantic search engine","date":"2020-12-07","arxiv_id":"2012.03942","n_code_links":2,"syntology":null},{"paper":"/paper/ubar-towards-fully-end-to-end-task-oriented","slug":"ubar-towards-fully-end-to-end-task-oriented","title":"UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2","date":"2020-12-07","arxiv_id":"2012.03539","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhanced-offensive-language-detection-through","title":"Enhanced Offensive Language Detection Through Data Augmentation","date":"2020-12-05","arxiv_id":"2012.02954","n_code_links":0,"syntology":null},{"paper":null,"slug":"relational-pretrained-transformers-towards","title":"RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation","date":"2020-12-04","arxiv_id":"2012.02469","n_code_links":0,"syntology":null},{"paper":"/paper/how-can-we-know-when-language-models-know","slug":"how-can-we-know-when-language-models-know","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","date":"2020-12-02","arxiv_id":"2012.00955","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-deep-generative-approach-to-native-language","title":"A Deep Generative Approach to Native Language Identification","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-sparse-transformer-for-time","slug":"adversarial-sparse-transformer-for-time","title":"Adversarial Sparse Transformer for Time Series Forecasting","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"comparing-probabilistic-distributional-and","title":"Comparing Probabilistic, Distributional and Transformer-Based Models on Logical Metonymy Interpretation","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cpm-a-large-scale-generative-chinese-pre","slug":"cpm-a-large-scale-generative-chinese-pre","title":"CPM: A Large-scale Generative Chinese Pre-trained Language Model","date":"2020-12-01","arxiv_id":"2012.00413","n_code_links":10,"syntology":null},{"paper":null,"slug":"hitachi-at-semeval-2020-task-11-an-empirical","title":"Hitachi at SemEval-2020 Task 11: An Empirical Study of Pre-Trained Transformer Family for Propaganda Detection","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hitachi-at-semeval-2020-task-7-stacking-at","title":"Hitachi at SemEval-2020 Task 7: Stacking at Scale with Heterogeneous Language Models for Humor Recognition","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hitachi-at-semeval-2020-task-8-simple-but","title":"Hitachi at SemEval-2020 Task 8: Simple but Effective Modality Ensemble for Meme Emotion Recognition","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/increasing-learning-efficiency-of-self","slug":"increasing-learning-efficiency-of-self","title":"Increasing Learning Efficiency of Self-Attention Networks through Direct Position Interactions, Learnable Temperature, and Convoluted Attention","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/tablegpt-few-shot-table-to-text-generation","slug":"tablegpt-few-shot-table-to-text-generation","title":"TableGPT: Few-shot Table-to-Text Generation with Table Structure Reconstruction and Content Matching","date":"2020-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"ui-at-semeval-2020-task-4-commonsense","title":"UI at SemEval-2020 Task 4: Commonsense Validation and Explanation by Exploiting Contradiction","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-pre-training-for-paraphrase","title":"Generative Pre-training for Paraphrase Generation by Representing and Predicting Spans in Exemplars","date":"2020-11-29","arxiv_id":"2011.14344","n_code_links":0,"syntology":null},{"paper":"/paper/an-efficient-and-scalable-deep-learning","slug":"an-efficient-and-scalable-deep-learning","title":"An Efficient and Scalable Deep Learning Approach for Road Damage Detection","date":"2020-11-18","arxiv_id":"2011.09577","n_code_links":2,"syntology":null},{"paper":null,"slug":"do-fine-tuned-commonsense-language-models","title":"Do Fine-tuned Commonsense Language Models Really Generalize?","date":"2020-11-18","arxiv_id":"2011.09159","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-mechanism-transformers-bert-and-gpt","title":"Attention Mechanism, Transformers, BERT, and GPT: Tutorial and Survey","date":"2020-11-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/debatesum-a-large-scale-argument-mining-and","slug":"debatesum-a-large-scale-argument-mining-and","title":"DebateSum: A large-scale argument mining and summarization dataset","date":"2020-11-14","arxiv_id":"2011.07251","n_code_links":3,"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":["Hellisotherpeople/DebateSum","Hellisotherpeople/debate2vec","arvind-balaji/debate-cards"],"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/adapting-a-language-model-for-controlled","slug":"adapting-a-language-model-for-controlled","title":"Adapting a Language Model for Controlled Affective Text Generation","date":"2020-11-08","arxiv_id":"2011.04000","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ishikasingh/Affective-text-gen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/semi-supervised-low-resource-style-transfer","slug":"semi-supervised-low-resource-style-transfer","title":"Semi-Supervised Low-Resource Style Transfer of Indonesian Informal to Formal Language with Iterative Forward-Translation","date":"2020-11-06","arxiv_id":"2011.03286","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-rnn-transducer-with-normalized","title":"Improving RNN transducer with normalized jointer network","date":"2020-11-03","arxiv_id":"2011.01576","n_code_links":0,"syntology":null},{"paper":"/paper/tabular-transformers-for-modeling","slug":"tabular-transformers-for-modeling","title":"Tabular Transformers for Modeling Multivariate Time Series","date":"2020-11-03","arxiv_id":"2011.01843","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["IBM/TabFormer"],"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":"the-amazing-world-of-neural-language","title":"The Amazing World of Neural Language Generation","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/visually-grounded-planning-without-vision-1","slug":"visually-grounded-planning-without-vision-1","title":"Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"topic-preserving-synthetic-news-generation-an","title":"Topic-Preserving Synthetic News Generation: An Adversarial Deep Reinforcement Learning Approach","date":"2020-10-30","arxiv_id":"2010.16324","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-paraphrase-generation-via","title":"Unsupervised Paraphrasing with Pretrained Language Models","date":"2020-10-24","arxiv_id":"2010.12885","n_code_links":0,"syntology":null},{"paper":"/paper/lightseq-a-high-performance-inference-library","slug":"lightseq-a-high-performance-inference-library","title":"LightSeq: A High Performance Inference Library for Transformers","date":"2020-10-23","arxiv_id":"2010.13887","n_code_links":1,"syntology":null},{"paper":null,"slug":"topic-modeling-with-contextualized-word","title":"Topic Modeling with Contextualized Word Representation Clusters","date":"2020-10-23","arxiv_id":"2010.12626","n_code_links":0,"syntology":null},{"paper":null,"slug":"developing-real-time-streaming-transformer","title":"Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset","date":"2020-10-22","arxiv_id":"2010.11395","n_code_links":0,"syntology":null},{"paper":null,"slug":"transferable-graph-optimizers-for-ml","title":"Transferable Graph Optimizers for ML Compilers","date":"2020-10-21","arxiv_id":"2010.12438","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-of-transfer-learning-model-vs","title":"Performance of Transfer Learning Model vs. Traditional Neural Network in Low System Resource Environment","date":"2020-10-20","arxiv_id":"2011.07962","n_code_links":0,"syntology":null},{"paper":null,"slug":"better-distractions-transformer-based","title":"Better Distractions: Transformer-based Distractor Generation and Multiple Choice Question Filtering","date":"2020-10-19","arxiv_id":"2010.09598","n_code_links":0,"syntology":null},{"paper":null,"slug":"da-transformer-distance-aware-transformer","title":"DA-Transformer: Distance-aware Transformer","date":"2020-10-14","arxiv_id":"2010.06925","n_code_links":0,"syntology":null},{"paper":"/paper/decoding-methods-for-neural-narrative","slug":"decoding-methods-for-neural-narrative","title":"Decoding Methods for Neural Narrative Generation","date":"2020-10-14","arxiv_id":"2010.07375","n_code_links":2,"syntology":null}],"record_sha256":"5fede2419eb2dcb68d0d5ee90692f32fe550d94c61a198593bef1243c97ff531","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}