{"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/gpt/papers/12","list_of":"/method/gpt","method":"GPT","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":12,"pages_in_order":13,"rows_per_page":100,"rows":[1101,1200],"of":1212,"counts":{"archive_papers_tagged":1212,"with_a_code_link":453,"where_syntology_ran_a_sample":152,"not_listed_spam_title":0,"listed":1212,"listed_where_code_ran":152,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":130,"every_run_a_failure_of_syntologys_instrument":22,"listed_with_a_run_with_no_instrument_failure":130,"listed_every_run_a_failure_of_syntologys_instrument":22,"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/gpt","prev":"/method/gpt/papers/11","next":"/method/gpt/papers/13","papers":[{"paper":"/paper/nlx-gpt-a-model-for-natural-language","slug":"nlx-gpt-a-model-for-natural-language","title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","date":"2022-03-09","arxiv_id":"2203.05081","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-and-adapting-chinese-gpt-to-pinyin-1","slug":"exploring-and-adapting-chinese-gpt-to-pinyin-1","title":"Exploring and Adapting Chinese GPT to Pinyin Input Method","date":"2022-03-01","arxiv_id":"2203.00249","n_code_links":1,"syntology":null},{"paper":null,"slug":"consistent-dropout-for-policy-gradient","title":"Consistent Dropout for Policy Gradient Reinforcement Learning","date":"2022-02-23","arxiv_id":"2202.11818","n_code_links":0,"syntology":null},{"paper":"/paper/sgpt-gpt-sentence-embeddings-for-semantic","slug":"sgpt-gpt-sentence-embeddings-for-semantic","title":"SGPT: GPT Sentence Embeddings for Semantic Search","date":"2022-02-17","arxiv_id":"2202.08904","n_code_links":1,"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":["muennighoff/sgpt"],"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/what-are-the-best-systems-new-perspectives-on","slug":"what-are-the-best-systems-new-perspectives-on","title":"What are the best systems? New perspectives on NLP Benchmarking","date":"2022-02-08","arxiv_id":"2202.03799","n_code_links":1,"syntology":null},{"paper":"/paper/l3cube-mahacorpus-and-mahabert-marathi","slug":"l3cube-mahacorpus-and-mahabert-marathi","title":"L3Cube-MahaCorpus and MahaBERT: Marathi Monolingual Corpus, Marathi BERT Language Models, and Resources","date":"2022-02-02","arxiv_id":"2202.01159","n_code_links":1,"syntology":null},{"paper":null,"slug":"vc-gpt-visual-conditioned-gpt-for-end-to-end","title":"A Frustratingly Simple Approach for End-to-End Image Captioning","date":"2022-01-30","arxiv_id":"2201.12723","n_code_links":0,"syntology":null},{"paper":null,"slug":"dnnfuser-generative-pre-trained-transformer","title":"DNNFuser: Generative Pre-Trained Transformer as a Generalized Mapper for Layer Fusion in DNN Accelerators","date":"2022-01-26","arxiv_id":"2201.11218","n_code_links":0,"syntology":null},{"paper":null,"slug":"polling-latent-opinions-a-method-for","title":"Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"provably-confidential-language-modelling","title":"Provably Confidential Language Modelling","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/dense-to-sparse-gate-for-mixture-of-experts-1","slug":"dense-to-sparse-gate-for-mixture-of-experts-1","title":"EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate","date":"2021-12-29","arxiv_id":"2112.14397","n_code_links":2,"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: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["codecaution/evomoe"],"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/think-big-teach-small-do-language-models","slug":"think-big-teach-small-do-language-models","title":"Think Big, Teach Small: Do Language Models Distil Occam’s Razor?","date":"2021-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"chemical-identification-and-indexing-in","title":"Chemical Identification and Indexing in PubMed Articles via BERT and Text-to-Text Approaches","date":"2021-11-30","arxiv_id":"2111.15622","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-korean-pretrained-language","title":"Transformer-based Korean Pretrained Language Models: A Survey on Three Years of Progress","date":"2021-11-25","arxiv_id":"2112.03014","n_code_links":0,"syntology":null},{"paper":"/paper/building-chinese-biomedical-language-models-1","slug":"building-chinese-biomedical-language-models-1","title":"Building Chinese Biomedical Language Models via Multi-Level Text Discrimination","date":"2021-11-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"create-a-benchmark-for-chinese-short-video","title":"CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"elle-efficient-lifelong-pre-training-for","title":"ELLE: Efficient Lifelong Pre-training for Emerging Data","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-and-adapting-chinese-gpt-to-pinyin","title":"Exploring and Adapting Chinese GPT to Pinyin Input Method","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"glm-general-language-model-pretraining-with","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"impact-of-tokenization-on-language-models-an","title":"Impact of Tokenization on Language Models: An Analysis for Turkish","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"life-after-bert-what-do-other-muppets","title":"Life after BERT: What do Other Muppets Understand about Language?","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/colossal-ai-a-unified-deep-learning-system","slug":"colossal-ai-a-unified-deep-learning-system","title":"Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training","date":"2021-10-28","arxiv_id":"2110.14883","n_code_links":1,"syntology":null},{"paper":"/paper/fast-model-editing-at-scale-1","slug":"fast-model-editing-at-scale-1","title":"Fast Model Editing at Scale","date":"2021-10-21","arxiv_id":"2110.11309","n_code_links":3,"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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["eric-mitchell/mend"],"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/illiterate-dall-cdot-e-learns-to-compose-1","slug":"illiterate-dall-cdot-e-learns-to-compose-1","title":"Illiterate DALL-E Learns to Compose","date":"2021-10-17","arxiv_id":"2110.11405","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["singhgautam/slate"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pagnol-an-extra-large-french-generative-model","title":"PAGnol: An Extra-Large French Generative Model","date":"2021-10-16","arxiv_id":"2110.08554","n_code_links":0,"syntology":null},{"paper":null,"slug":"kronecker-decomposition-for-gpt-compression","title":"Kronecker Decomposition for GPT Compression","date":"2021-10-15","arxiv_id":"2110.08152","n_code_links":0,"syntology":null},{"paper":"/paper/building-chinese-biomedical-language-models","slug":"building-chinese-biomedical-language-models","title":"Building Chinese Biomedical Language Models via Multi-Level Text Discrimination","date":"2021-10-14","arxiv_id":"2110.07244","n_code_links":1,"syntology":null},{"paper":"/paper/lightseq-accelerated-training-for-transformer","slug":"lightseq-accelerated-training-for-transformer","title":"LightSeq2: Accelerated Training for Transformer-based Models on GPUs","date":"2021-10-12","arxiv_id":"2110.05722","n_code_links":1,"syntology":null},{"paper":"/paper/vector-quantized-image-modeling-with-improved-1","slug":"vector-quantized-image-modeling-with-improved-1","title":"Vector-quantized Image Modeling with Improved VQGAN","date":"2021-10-09","arxiv_id":"2110.04627","n_code_links":5,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"adversarial-examples-generation-for-reducing","title":"Adversarial Examples Generation for Reducing Implicit Gender Bias in Pre-trained Models","date":"2021-10-03","arxiv_id":"2110.01094","n_code_links":0,"syntology":null},{"paper":null,"slug":"illiterate-dall-cdot-e-learns-to-compose","title":"Illiterate DALL$\\cdot$E Learns to Compose","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"seqpate-differentially-private-text","title":"SeqPATE: Differentially Private Text Generation via Knowledge Distillation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-as-recommender-systems","title":"Language Models as Recommender Systems: Evaluations and Limitations","date":"2021-09-22","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/language-models-are-few-shot-multilingual","slug":"language-models-are-few-shot-multilingual","title":"Language Models are Few-shot Multilingual Learners","date":"2021-09-16","arxiv_id":"2109.07684","n_code_links":1,"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":["gentaiscool/few-shot-lm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/multilingual-translation-via-grafting-pre","slug":"multilingual-translation-via-grafting-pre","title":"Multilingual Translation via Grafting Pre-trained Language Models","date":"2021-09-11","arxiv_id":"2109.05256","n_code_links":1,"syntology":null},{"paper":null,"slug":"topicrefine-joint-topic-prediction-and","title":"TopicRefine: Joint Topic Prediction and Dialogue Response Generation for Multi-turn End-to-End Dialogue System","date":"2021-09-11","arxiv_id":"2109.05187","n_code_links":0,"syntology":null},{"paper":"/paper/variational-latent-state-gpt-for-semi","slug":"variational-latent-state-gpt-for-semi","title":"Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems","date":"2021-09-09","arxiv_id":"2109.04314","n_code_links":2,"syntology":null},{"paper":null,"slug":"numgpt-improving-numeracy-ability-of","title":"NumGPT: Improving Numeracy Ability of Generative Pre-trained Models","date":"2021-09-07","arxiv_id":"2109.03137","n_code_links":0,"syntology":null},{"paper":"/paper/codet5-identifier-aware-unified-pre-trained","slug":"codet5-identifier-aware-unified-pre-trained","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","date":"2021-09-02","arxiv_id":"2109.00859","n_code_links":5,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":0,"phrase":"6 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; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["salesforce/codet5"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"fight-fire-with-fire-fine-tuning-hate","title":"Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate Speech","date":"2021-09-01","arxiv_id":"2109.00591","n_code_links":0,"syntology":null},{"paper":"/paper/curriculum-learning-a-regularization-method","slug":"curriculum-learning-a-regularization-method","title":"The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models","date":"2021-08-13","arxiv_id":"2108.06084","n_code_links":1,"syntology":null},{"paper":"/paper/ammus-a-survey-of-transformer-based","slug":"ammus-a-survey-of-transformer-based","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","date":"2021-08-12","arxiv_id":"2108.05542","n_code_links":1,"syntology":null},{"paper":"/paper/patrickstar-parallel-training-of-pre-trained","slug":"patrickstar-parallel-training-of-pre-trained","title":"PatrickStar: Parallel Training of Pre-trained Models via Chunk-based Memory Management","date":"2021-08-12","arxiv_id":"2108.05818","n_code_links":1,"syntology":null},{"paper":null,"slug":"rockgpt-reconstructing-three-dimensional","title":"RockGPT: Reconstructing three-dimensional digital rocks from single two-dimensional slice from the perspective of video generation","date":"2021-08-05","arxiv_id":"2108.03132","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-gpt-gpt-2-and-bert-language-models","title":"Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition","date":"2021-07-29","arxiv_id":"2108.07789","n_code_links":0,"syntology":null},{"paper":"/paper/scalable-memory-protection-in-the-penglai","slug":"scalable-memory-protection-in-the-penglai","title":"Scalable Memory Protection in the PENGLAI Enclave","date":"2021-07-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-large-language-models-trained-on","slug":"evaluating-large-language-models-trained-on","title":"Evaluating Large Language Models Trained on Code","date":"2021-07-07","arxiv_id":"2107.03374","n_code_links":13,"syntology":{"ran":26,"of":39,"n_ran_checked":24,"n_instrument":2,"unverified":13,"pointer_only":4,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 0 violated, 23 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified","official":{"repos":["openai/human-eval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["found_in_text","listed","official"]}}},{"paper":"/paper/symbolicgpt-a-generative-transformer-model","slug":"symbolicgpt-a-generative-transformer-model","title":"SymbolicGPT: A Generative Transformer Model for Symbolic Regression","date":"2021-06-27","arxiv_id":"2106.14131","n_code_links":2,"syntology":{"ran":9,"of":9,"n_ran_checked":8,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["git.uwaterloo.ca/data-analytics-lab/symbolicgpt2"],"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":"pre-trained-models-past-present-and-future","title":"Pre-Trained Models: Past, Present and Future","date":"2021-06-14","arxiv_id":"2106.07139","n_code_links":0,"syntology":null},{"paper":null,"slug":"engines-of-power-electricity-ai-and-general","title":"Engines of Power: Electricity, AI, and General-Purpose Military Transformations","date":"2021-06-08","arxiv_id":"2106.04338","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-syntactic-probes-probe-syntax-experiments","title":"Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing","date":"2021-06-04","arxiv_id":"2106.02559","n_code_links":0,"syntology":null},{"paper":"/paper/data-curation-and-quality-assurance-for","slug":"data-curation-and-quality-assurance-for","title":"Data Curation and Quality Assurance for Machine Learning-based Cyber Intrusion Detection","date":"2021-05-20","arxiv_id":"2105.10041","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-covid-19-tweets-with-transformer","title":"Analyzing COVID-19 Tweets with Transformer-based Language Models","date":"2021-04-20","arxiv_id":"2104.10259","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-transformers-for-bot-detection","slug":"understanding-transformers-for-bot-detection","title":"Understanding Transformers for Bot Detection in Twitter","date":"2021-04-13","arxiv_id":"2104.06182","n_code_links":1,"syntology":null},{"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":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":"/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":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":"/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":"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":"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":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/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/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":"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":"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":null,"slug":"prior-art-search-and-reranking-for-generated","title":"Prior Art Search and Reranking for Generated Patent Text","date":"2020-09-19","arxiv_id":"2009.09132","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-gpt-with-congruent-transformers","title":"Hierarchical GPT with Congruent Transformers for Multi-Sentence Language Models","date":"2020-09-18","arxiv_id":"2009.08636","n_code_links":0,"syntology":null},{"paper":"/paper/comparative-evaluation-of-pretrained-transfer","slug":"comparative-evaluation-of-pretrained-transfer","title":"Comparative Evaluation of Pretrained Transfer Learning Models on Automatic Short Answer Grading","date":"2020-09-02","arxiv_id":"2009.01303","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-efficient-deep-learning-for-natural","title":"Knowledge Efficient Deep Learning for Natural Language Processing","date":"2020-08-28","arxiv_id":"2008.12878","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamics-of-feed-forward-induced-interference","title":"Dynamics of feed forward induced interference training","date":"2020-08-24","arxiv_id":"2008.11111","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-fly-information-retrieval-augmentation-1","title":"On-The-Fly Information Retrieval Augmentation for Language Models","date":"2020-07-03","arxiv_id":"2007.01528","n_code_links":0,"syntology":null},{"paper":"/paper/roles-and-utilization-of-attention-heads-in","slug":"roles-and-utilization-of-attention-heads-in","title":"Roles and Utilization of Attention Heads in Transformer-based Neural Language Models","date":"2020-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/memory-efficient-pipeline-parallel-dnn","slug":"memory-efficient-pipeline-parallel-dnn","title":"Memory-Efficient Pipeline-Parallel DNN Training","date":"2020-06-16","arxiv_id":"2006.09503","n_code_links":1,"syntology":{"ran":2,"of":10,"n_ran_checked":2,"n_instrument":0,"unverified":8,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":null}},{"paper":"/paper/emergence-of-separable-manifolds-in-deep","slug":"emergence-of-separable-manifolds-in-deep","title":"Emergence of Separable Manifolds in Deep Language Representations","date":"2020-06-01","arxiv_id":"2006.01095","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-generation-of-medical-dialogues-for","title":"On the Generation of Medical Dialogues for COVID-19","date":"2020-05-11","arxiv_id":"2005.05442","n_code_links":0,"syntology":null},{"paper":"/paper/spying-on-your-neighbors-fine-grained-probing","slug":"spying-on-your-neighbors-fine-grained-probing","title":"Spying on your neighbors: Fine-grained probing of contextual embeddings for information about surrounding words","date":"2020-05-04","arxiv_id":"2005.01810","n_code_links":0,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":null}},{"paper":null,"slug":"multilingual-corpus-creation-for-multilingual","title":"Multilingual Corpus Creation for Multilingual Semantic Similarity Task","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/electra-pre-training-text-encoders-as-1","slug":"electra-pre-training-text-encoders-as-1","title":"ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators","date":"2020-03-23","arxiv_id":"2003.10555","n_code_links":19,"syntology":{"ran":31,"of":40,"n_ran_checked":18,"n_instrument":13,"unverified":9,"pointer_only":10,"phrase":"31 ran (of which 7 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 2 violated, 14 with no contract checked; 13 where Syntology's instrument failed) · 9 unverified","official":{"repos":["google-research/electra"],"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":["listed","unlocated"]}}},{"paper":"/paper/training-large-neural-networks-with-constant","slug":"training-large-neural-networks-with-constant","title":"Training Large Neural Networks with Constant Memory using a New Execution Algorithm","date":"2020-02-13","arxiv_id":"2002.05645","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"joint-contextual-modeling-for-asr-correction","title":"Joint Contextual Modeling for ASR Correction and Language Understanding","date":"2020-01-28","arxiv_id":"2002.00750","n_code_links":0,"syntology":null},{"paper":"/paper/oteann-estimating-the-transparency-of","slug":"oteann-estimating-the-transparency-of","title":"OTEANN: Estimating the Transparency of Orthographies with an Artificial Neural Network","date":"2019-12-31","arxiv_id":"1912.13321","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-pretrained-language","title":"A Comparative Study of Pretrained Language Models on Thai Social Text Categorization","date":"2019-12-03","arxiv_id":"1912.01580","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-commonsense-in-pre-trained","slug":"evaluating-commonsense-in-pre-trained","title":"Evaluating Commonsense in Pre-trained Language Models","date":"2019-11-27","arxiv_id":"1911.11931","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-paraphrase-generation-with","title":"Zero-Shot Paraphrase Generation with Multilingual Language Models","date":"2019-11-09","arxiv_id":"1911.03597","n_code_links":0,"syntology":null},{"paper":null,"slug":"inspecting-unification-of-encoding-and","title":"Inspecting Unification of Encoding and Matching with Transformer: A Case Study of Machine Reading Comprehension","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/natural-language-generation-for-effective","slug":"natural-language-generation-for-effective","title":"Natural Language Generation for Effective Knowledge Distillation","date":"2019-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"an-empirical-study-of-efficient-asr-rescoring","title":"An Empirical Study of Efficient ASR Rescoring with Transformers","date":"2019-10-24","arxiv_id":"1910.11450","n_code_links":0,"syntology":null},{"paper":null,"slug":"evolution-of-transfer-learning-in-natural","title":"Evolution of transfer learning in natural language processing","date":"2019-10-16","arxiv_id":"1910.07370","n_code_links":0,"syntology":null},{"paper":"/paper/q8bert-quantized-8bit-bert","slug":"q8bert-quantized-8bit-bert","title":"Q8BERT: Quantized 8Bit BERT","date":"2019-10-14","arxiv_id":"1910.06188","n_code_links":5,"syntology":{"ran":10,"of":11,"n_ran_checked":9,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["intellabs/model-compression-research-package","NervanaSystems/nlp-architect"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/zero-memory-optimization-towards-training-a","slug":"zero-memory-optimization-towards-training-a","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","date":"2019-10-04","arxiv_id":"1910.02054","n_code_links":10,"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":["NVIDIA/Megatron-LM","microsoft/DeepSpeed"],"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":"extreme-language-model-compression-with-1","title":"Extremely Small BERT Models from Mixed-Vocabulary Training","date":"2019-09-25","arxiv_id":"1909.11687","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-ways-to-incorporate-additional","title":"How Additional Knowledge can Improve Natural Language Commonsense Question Answering?","date":"2019-09-19","arxiv_id":"1909.08855","n_code_links":0,"syntology":null},{"paper":"/paper/reasoning-over-semantic-level-graph-for-fact","slug":"reasoning-over-semantic-level-graph-for-fact","title":"Reasoning Over Semantic-Level Graph for Fact Checking","date":"2019-09-09","arxiv_id":"1909.03745","n_code_links":0,"syntology":null},{"paper":"/paper/effective-use-of-transformer-networks-for","slug":"effective-use-of-transformer-networks-for","title":"Effective Use of Transformer Networks for Entity Tracking","date":"2019-09-05","arxiv_id":"1909.02635","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["aditya2211/transformer-entity-tracking"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/semantics-aware-bert-for-language","slug":"semantics-aware-bert-for-language","title":"Semantics-aware BERT for Language Understanding","date":"2019-09-05","arxiv_id":"1909.02209","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":5,"n_instrument":2,"unverified":5,"pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["cooelf/SemBERT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"adversarial-learning-with-contextual","title":"Adversarial Learning with Contextual Embeddings for Zero-resource Cross-lingual Classification and NER","date":"2019-08-31","arxiv_id":"1909.00153","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantity-doesnt-buy-quality-syntax-with","title":"Quantity doesn't buy quality syntax with neural language models","date":"2019-08-31","arxiv_id":"1909.00111","n_code_links":0,"syntology":null}],"record_sha256":"17ab742b24d35abe2f0579d9dae39a5ac9421db3bd52c8c27aec3b03d6563b18","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}