{"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/68","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":68,"pages_in_order":109,"rows_per_page":100,"rows":[6701,6800],"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/67","next":"/method/attention-dropout/papers/69","papers":[{"paper":null,"slug":"urdu-news-article-recommendation-model-using","title":"Urdu News Article Recommendation Model using Natural Language Processing Techniques","date":"2022-05-29","arxiv_id":"2206.11862","n_code_links":0,"syntology":null},{"paper":"/paper/teaching-models-to-express-their-uncertainty","slug":"teaching-models-to-express-their-uncertainty","title":"Teaching Models to Express Their Uncertainty in Words","date":"2022-05-28","arxiv_id":"2205.14334","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["sylinrl/calibratedmath"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/flashattention-fast-and-memory-efficient","slug":"flashattention-fast-and-memory-efficient","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","date":"2022-05-27","arxiv_id":"2205.14135","n_code_links":13,"syntology":{"ran":24,"of":30,"n_ran_checked":18,"n_instrument":6,"unverified":6,"pointer_only":1,"phrase":"24 ran (of which 2 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 1 violated, 17 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified","official":{"repos":["dao-ailab/flash-attention"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","listed"]}}},{"paper":"/paper/multimodal-masked-autoencoders-learn","slug":"multimodal-masked-autoencoders-learn","title":"Multimodal Masked Autoencoders Learn Transferable Representations","date":"2022-05-27","arxiv_id":"2205.14204","n_code_links":3,"syntology":{"ran":12,"of":12,"n_ran_checked":9,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["young-geng/m3ae_public"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/nearest-neighbor-zero-shot-inference","slug":"nearest-neighbor-zero-shot-inference","title":"kNN-Prompt: Nearest Neighbor Zero-Shot Inference","date":"2022-05-27","arxiv_id":"2205.13792","n_code_links":1,"syntology":null},{"paper":"/paper/what-dense-graph-do-you-need-for-self","slug":"what-dense-graph-do-you-need-for-self","title":"What Dense Graph Do You Need for Self-Attention?","date":"2022-05-27","arxiv_id":"2205.14014","n_code_links":1,"syntology":null},{"paper":null,"slug":"federated-split-bert-for-heterogeneous-text","title":"Federated Split BERT for Heterogeneous Text Classification","date":"2022-05-26","arxiv_id":"2205.13299","n_code_links":0,"syntology":null},{"paper":"/paper/learning-dialogue-representations-from","slug":"learning-dialogue-representations-from","title":"Learning Dialogue Representations from Consecutive Utterances","date":"2022-05-26","arxiv_id":"2205.13568","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-dependency-grammar-for-fine","slug":"leveraging-dependency-grammar-for-fine","title":"Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks","date":"2022-05-26","arxiv_id":"2205.13164","n_code_links":1,"syntology":null},{"paper":"/paper/the-document-vectors-using-cosine-similarity-1","slug":"the-document-vectors-using-cosine-similarity-1","title":"The Document Vectors Using Cosine Similarity Revisited","date":"2022-05-26","arxiv_id":"2205.13357","n_code_links":1,"syntology":null},{"paper":"/paper/training-and-inference-on-any-order","slug":"training-and-inference-on-any-order","title":"Training and Inference on Any-Order Autoregressive Models the Right Way","date":"2022-05-26","arxiv_id":"2205.13554","n_code_links":1,"syntology":null},{"paper":"/paper/bit-robustly-binarized-multi-distilled","slug":"bit-robustly-binarized-multi-distilled","title":"BiT: Robustly Binarized Multi-distilled Transformer","date":"2022-05-25","arxiv_id":"2205.13016","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/bit"],"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":["listed","official"]}}},{"paper":null,"slug":"conditional-set-generation-using-seq2seq-1","title":"Conditional set generation using Seq2seq models","date":"2022-05-25","arxiv_id":"2205.12485","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-are-zero-shot-clinical","title":"Large Language Models are Few-Shot Clinical Information Extractors","date":"2022-05-25","arxiv_id":"2205.12689","n_code_links":0,"syntology":null},{"paper":null,"slug":"lifelong-learning-natural-language-processing","title":"Lifelong Learning Natural Language Processing Approach for Multilingual Data Classification","date":"2022-05-25","arxiv_id":"2206.11867","n_code_links":0,"syntology":null},{"paper":"/paper/naturalprover-grounded-mathematical-proof","slug":"naturalprover-grounded-mathematical-proof","title":"NaturalProver: Grounded Mathematical Proof Generation with Language Models","date":"2022-05-25","arxiv_id":"2205.12910","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":["wellecks/naturalprover"],"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":"orca-interpreting-prompted-language-models","title":"ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data","date":"2022-05-25","arxiv_id":"2205.12600","n_code_links":0,"syntology":null},{"paper":"/paper/robustlr-evaluating-robustness-to-logical","slug":"robustlr-evaluating-robustness-to-logical","title":"RobustLR: Evaluating Robustness to Logical Perturbation in Deductive Reasoning","date":"2022-05-25","arxiv_id":"2205.12598","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["ink-usc/robustlr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/tacube-pre-computing-data-cubes-for-answering","slug":"tacube-pre-computing-data-cubes-for-answering","title":"TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data","date":"2022-05-25","arxiv_id":"2205.12682","n_code_links":1,"syntology":null},{"paper":null,"slug":"text-to-face-generation-with-stylegan2","title":"Text-to-Face Generation with StyleGAN2","date":"2022-05-25","arxiv_id":"2205.12512","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-understanding-label-regularization","title":"Do we need Label Regularization to Fine-tune Pre-trained Language Models?","date":"2022-05-25","arxiv_id":"2205.12428","n_code_links":0,"syntology":null},{"paper":null,"slug":"train-flat-then-compress-sharpness-aware","title":"Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models","date":"2022-05-25","arxiv_id":"2205.12694","n_code_links":0,"syntology":null},{"paper":"/paper/transcormer-transformer-for-sentence-scoring","slug":"transcormer-transformer-for-sentence-scoring","title":"Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling","date":"2022-05-25","arxiv_id":"2205.12986","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"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":null}},{"paper":"/paper/vulberta-simplified-source-code-pre-training","slug":"vulberta-simplified-source-code-pre-training","title":"VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection","date":"2022-05-25","arxiv_id":"2205.12424","n_code_links":1,"syntology":null},{"paper":null,"slug":"edit5-semi-autoregressive-text-editing-with","title":"EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start","date":"2022-05-24","arxiv_id":"2205.12209","n_code_links":0,"syntology":null},{"paper":"/paper/flute-figurative-language-understanding-and","slug":"flute-figurative-language-understanding-and","title":"FLUTE: Figurative Language Understanding through Textual Explanations","date":"2022-05-24","arxiv_id":"2205.12404","n_code_links":1,"syntology":null},{"paper":"/paper/formulating-few-shot-fine-tuning-towards","slug":"formulating-few-shot-fine-tuning-towards","title":"Formulating Few-shot Fine-tuning Towards Language Model Pre-training: A Pilot Study on Named Entity Recognition","date":"2022-05-24","arxiv_id":"2205.11799","n_code_links":1,"syntology":null},{"paper":"/paper/garden-path-traversal-within-gpt-2","slug":"garden-path-traversal-within-gpt-2","title":"Garden-Path Traversal in GPT-2","date":"2022-05-24","arxiv_id":"2205.12302","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wjurayj/garden-path-gpt2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/geomlama-geo-diverse-commonsense-probing-on","slug":"geomlama-geo-diverse-commonsense-probing-on","title":"GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models","date":"2022-05-24","arxiv_id":"2205.12247","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-human-is-human-evaluation-improving-the","title":"The Authenticity Gap in Human Evaluation","date":"2022-05-24","arxiv_id":"2205.11930","n_code_links":0,"syntology":null},{"paper":"/paper/k-12bert-bert-for-k-12-education","slug":"k-12bert-bert-for-k-12-education","title":"K-12BERT: BERT for K-12 education","date":"2022-05-24","arxiv_id":"2205.12335","n_code_links":1,"syntology":null},{"paper":null,"slug":"medical-scientific-table-to-text-generation","title":"Medical Scientific Table-to-Text Generation with Human-in-the-Loop under the Data Sparsity Constraint","date":"2022-05-24","arxiv_id":"2205.12368","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-role-of-bidirectionality-in-language","title":"On the Role of Bidirectionality in Language Model Pre-Training","date":"2022-05-24","arxiv_id":"2205.11726","n_code_links":0,"syntology":null},{"paper":"/paper/partial-input-baselines-show-that-nli-models","slug":"partial-input-baselines-show-that-nli-models","title":"Partial-input baselines show that NLI models can ignore context, but they don't","date":"2022-05-24","arxiv_id":"2205.12181","n_code_links":1,"syntology":null},{"paper":"/paper/retromae-pre-training-retrieval-oriented","slug":"retromae-pre-training-retrieval-oriented","title":"RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder","date":"2022-05-24","arxiv_id":"2205.12035","n_code_links":1,"syntology":null},{"paper":"/paper/sparse-mixers-combining-moe-and-mixing-to","slug":"sparse-mixers-combining-moe-and-mixing-to","title":"Sparse Mixers: Combining MoE and Mixing to build a more efficient BERT","date":"2022-05-24","arxiv_id":"2205.12399","n_code_links":1,"syntology":null},{"paper":null,"slug":"word-order-typology-in-multilingual-bert-a","title":"Word-order typology in Multilingual BERT: A case study in subordinate-clause detection","date":"2022-05-24","arxiv_id":"2205.11987","n_code_links":0,"syntology":null},{"paper":"/paper/workflow-discovery-from-dialogues-in-the-low","slug":"workflow-discovery-from-dialogues-in-the-low","title":"Workflow Discovery from Dialogues in the Low Data Regime","date":"2022-05-24","arxiv_id":"2205.11690","n_code_links":1,"syntology":null},{"paper":"/paper/a-question-answer-driven-approach-to-reveal","slug":"a-question-answer-driven-approach-to-reveal","title":"A Question-Answer Driven Approach to Reveal Affirmative Interpretations from Verbal Negations","date":"2022-05-23","arxiv_id":"2205.11467","n_code_links":1,"syntology":null},{"paper":"/paper/artificial-intelligence-for-topic-modelling","slug":"artificial-intelligence-for-topic-modelling","title":"Artificial intelligence for topic modelling in Hindu philosophy: mapping themes between the Upanishads and the Bhagavad Gita","date":"2022-05-23","arxiv_id":"2205.11020","n_code_links":1,"syntology":null},{"paper":"/paper/banglanlg-benchmarks-and-resources-for","slug":"banglanlg-benchmarks-and-resources-for","title":"BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla","date":"2022-05-23","arxiv_id":"2205.11081","n_code_links":2,"syntology":null},{"paper":null,"slug":"improving-short-text-classification-with","title":"Improving Short Text Classification With Augmented Data Using GPT-3","date":"2022-05-23","arxiv_id":"2205.10981","n_code_links":0,"syntology":null},{"paper":"/paper/kold-korean-offensive-language-dataset","slug":"kold-korean-offensive-language-dataset","title":"KOLD: Korean Offensive Language Dataset","date":"2022-05-23","arxiv_id":"2205.11315","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-ignore-adversarial-attacks-1","title":"Learning to Ignore Adversarial Attacks","date":"2022-05-23","arxiv_id":"2205.11551","n_code_links":0,"syntology":null},{"paper":"/paper/looking-for-a-handsome-carpenter-debiasing","slug":"looking-for-a-handsome-carpenter-debiasing","title":"Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements","date":"2022-05-23","arxiv_id":"2205.11374","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-paradox-of-learning-to-reason-from","slug":"on-the-paradox-of-learning-to-reason-from","title":"On the Paradox of Learning to Reason from Data","date":"2022-05-23","arxiv_id":"2205.11502","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":7,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"7 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["joshuacnf/paradox-learning2reason"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/outliers-dimensions-that-disrupt-transformers","slug":"outliers-dimensions-that-disrupt-transformers","title":"Outliers Dimensions that Disrupt Transformers Are Driven by Frequency","date":"2022-05-23","arxiv_id":"2205.11380","n_code_links":1,"syntology":{"ran":8,"of":16,"n_ran_checked":8,"n_instrument":0,"unverified":8,"pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["gpucce/outliersvsfreq"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/parameter-efficient-sparsity-for-large","slug":"parameter-efficient-sparsity-for-large","title":"Parameter-Efficient Sparsity for Large Language Models Fine-Tuning","date":"2022-05-23","arxiv_id":"2205.11005","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["alibaba/AliceMind","yuchaoli/pst"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"penguins-don-t-fly-reasoning-about-generics","title":"Penguins Don't Fly: Reasoning about Generics through Instantiations and Exceptions","date":"2022-05-23","arxiv_id":"2205.11658","n_code_links":0,"syntology":null},{"paper":"/paper/prompt-tuning-for-discriminative-pre-trained-1","slug":"prompt-tuning-for-discriminative-pre-trained-1","title":"Prompt Tuning for Discriminative Pre-trained Language Models","date":"2022-05-23","arxiv_id":"2205.11166","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":5,"n_instrument":2,"unverified":5,"pointer_only":0,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["thunlp/dpt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"rl-with-kl-penalties-is-better-viewed-as","title":"RL with KL penalties is better viewed as Bayesian inference","date":"2022-05-23","arxiv_id":"2205.11275","n_code_links":0,"syntology":null},{"paper":null,"slug":"scholarbert-bigger-is-not-always-better","title":"The Diminishing Returns of Masked Language Models to Science","date":"2022-05-23","arxiv_id":"2205.11342","n_code_links":0,"syntology":null},{"paper":null,"slug":"simple-recurrence-improves-masked-language","title":"Simple Recurrence Improves Masked Language Models","date":"2022-05-23","arxiv_id":"2205.11588","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-graph-enhanced-bert-model-for-event-2","title":"A Graph Enhanced BERT Model for Event Prediction","date":"2022-05-22","arxiv_id":"2205.10822","n_code_links":0,"syntology":null},{"paper":"/paper/graphmae-self-supervised-masked-graph","slug":"graphmae-self-supervised-masked-graph","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","date":"2022-05-22","arxiv_id":"2205.10803","n_code_links":3,"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: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["thudm/graphmae"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/instruction-induction-from-few-examples-to","slug":"instruction-induction-from-few-examples-to","title":"Instruction Induction: From Few Examples to Natural Language Task Descriptions","date":"2022-05-22","arxiv_id":"2205.10782","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["orhonovich/instruction-induction"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/deeper-vs-wider-a-revisit-of-transformer","slug":"deeper-vs-wider-a-revisit-of-transformer","title":"A Study on Transformer Configuration and Training Objective","date":"2022-05-21","arxiv_id":"2205.10505","n_code_links":0,"syntology":null},{"paper":"/paper/least-to-most-prompting-enables-complex","slug":"least-to-most-prompting-enables-complex","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","date":"2022-05-21","arxiv_id":"2205.10625","n_code_links":1,"syntology":null},{"paper":"/paper/life-after-bert-what-do-other-muppets-2","slug":"life-after-bert-what-do-other-muppets-2","title":"Life after BERT: What do Other Muppets Understand about Language?","date":"2022-05-21","arxiv_id":"2205.10696","n_code_links":1,"syntology":null},{"paper":"/paper/pre-training-data-quality-and-quantity-for-a","slug":"pre-training-data-quality-and-quantity-for-a","title":"Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese","date":"2022-05-21","arxiv_id":"2205.10517","n_code_links":1,"syntology":null},{"paper":null,"slug":"current-trends-and-approaches-in-synonyms","title":"Current Trends and Approaches in Synonyms Extraction: Potential Adaptation to Arabic","date":"2022-05-20","arxiv_id":"2205.10412","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-extreme-parameter-compression-for-1","slug":"exploring-extreme-parameter-compression-for-1","title":"Exploring Extreme Parameter Compression for Pre-trained Language Models","date":"2022-05-20","arxiv_id":"2205.10036","n_code_links":1,"syntology":null},{"paper":"/paper/pre-training-transformer-models-with-sentence","slug":"pre-training-transformer-models-with-sentence","title":"Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection","date":"2022-05-20","arxiv_id":"2205.10455","n_code_links":0,"syntology":null},{"paper":"/paper/progressive-class-semantic-matching-for-semi-1","slug":"progressive-class-semantic-matching-for-semi-1","title":"Progressive Class Semantic Matching for Semi-supervised Text Classification","date":"2022-05-20","arxiv_id":"2205.10189","n_code_links":1,"syntology":null},{"paper":"/paper/prototypical-calibration-for-few-shot","slug":"prototypical-calibration-for-few-shot","title":"Prototypical Calibration for Few-shot Learning of Language Models","date":"2022-05-20","arxiv_id":"2205.10183","n_code_links":1,"syntology":null},{"paper":null,"slug":"arabglossbert-fine-tuning-bert-on-context-1","title":"ArabGlossBERT: Fine-Tuning BERT on Context-Gloss Pairs for WSD","date":"2022-05-19","arxiv_id":"2205.09685","n_code_links":0,"syntology":null},{"paper":"/paper/automated-scoring-for-reading-comprehension","slug":"automated-scoring-for-reading-comprehension","title":"Automated Scoring for Reading Comprehension via In-context BERT Tuning","date":"2022-05-19","arxiv_id":"2205.09864","n_code_links":1,"syntology":null},{"paper":"/paper/overcoming-language-disparity-in-online","slug":"overcoming-language-disparity-in-online","title":"Overcoming Language Disparity in Online Content Classification with Multimodal Learning","date":"2022-05-19","arxiv_id":"2205.09744","n_code_links":1,"syntology":null},{"paper":"/paper/psychiatric-scale-guided-risky-post-screening","slug":"psychiatric-scale-guided-risky-post-screening","title":"Psychiatric Scale Guided Risky Post Screening for Early Detection of Depression","date":"2022-05-19","arxiv_id":"2205.09497","n_code_links":1,"syntology":null},{"paper":"/paper/towards-understanding-gender-seniority","slug":"towards-understanding-gender-seniority","title":"Towards Understanding Gender-Seniority Compound Bias in Natural Language Generation","date":"2022-05-19","arxiv_id":"2205.09830","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-transfer-learning-for-polish-1","title":"Evaluation of Transfer Learning for Polish with a Text-to-Text Model","date":"2022-05-18","arxiv_id":"2205.08808","n_code_links":0,"syntology":null},{"paper":"/paper/lerac-learning-rate-curriculum","slug":"lerac-learning-rate-curriculum","title":"Learning Rate Curriculum","date":"2022-05-18","arxiv_id":"2205.09180","n_code_links":1,"syntology":null},{"paper":null,"slug":"pash-at-trec-2021-deep-learning-track","title":"PASH at TREC 2021 Deep Learning Track: Generative Enhanced Model for Multi-stage Ranking","date":"2022-05-18","arxiv_id":"2205.11245","n_code_links":0,"syntology":null},{"paper":"/paper/persian-natural-language-inference-a-meta-1","slug":"persian-natural-language-inference-a-meta-1","title":"Persian Natural Language Inference: A Meta-learning approach","date":"2022-05-18","arxiv_id":"2205.08755","n_code_links":1,"syntology":null},{"paper":null,"slug":"feature-aggregation-in-zero-shot-cross","title":"Feature Aggregation in Zero-Shot Cross-Lingual Transfer Using Multilingual BERT","date":"2022-05-17","arxiv_id":"2205.08497","n_code_links":0,"syntology":null},{"paper":null,"slug":"m6-rec-generative-pretrained-language-models","title":"M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems","date":"2022-05-17","arxiv_id":"2205.08084","n_code_links":0,"syntology":null},{"paper":null,"slug":"samu-xlsr-semantically-aligned-multimodal","title":"SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation","date":"2022-05-17","arxiv_id":"2205.08180","n_code_links":0,"syntology":null},{"paper":"/paper/semi-fnd-stacked-ensemble-based-multimodal","slug":"semi-fnd-stacked-ensemble-based-multimodal","title":"SEMI-FND: Stacked Ensemble Based Multimodal Inference For Faster Fake News Detection","date":"2022-05-17","arxiv_id":"2205.08159","n_code_links":0,"syntology":null},{"paper":null,"slug":"skill-structured-knowledge-infusion-for-large","title":"SKILL: Structured Knowledge Infusion for Large Language Models","date":"2022-05-17","arxiv_id":"2205.08184","n_code_links":0,"syntology":null},{"paper":"/paper/viralbert-a-user-focused-bert-based-approach","slug":"viralbert-a-user-focused-bert-based-approach","title":"ViralBERT: A User Focused BERT-Based Approach to Virality Prediction","date":"2022-05-17","arxiv_id":"2206.10298","n_code_links":1,"syntology":null},{"paper":"/paper/chemical-transformer-compression-for","slug":"chemical-transformer-compression-for","title":"Chemical transformer compression for accelerating both training and inference of molecular modeling","date":"2022-05-16","arxiv_id":"2205.07582","n_code_links":1,"syntology":null},{"paper":null,"slug":"harnessing-multilingual-resources-to-question","title":"Harnessing Multilingual Resources to Question Answering in Arabic","date":"2022-05-16","arxiv_id":"2205.08024","n_code_links":0,"syntology":null},{"paper":null,"slug":"heroes-villains-and-victims-and-gpt-3","title":"Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data","date":"2022-05-16","arxiv_id":"2205.07557","n_code_links":0,"syntology":null},{"paper":"/paper/the-ai-teacher-test-measuring-the-pedagogical","slug":"the-ai-teacher-test-measuring-the-pedagogical","title":"The AI Teacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialogues","date":"2022-05-16","arxiv_id":"2205.07540","n_code_links":1,"syntology":null},{"paper":"/paper/what-gpt-knows-about-who-is-who-1","slug":"what-gpt-knows-about-who-is-who-1","title":"What GPT Knows About Who is Who","date":"2022-05-16","arxiv_id":"2205.07407","n_code_links":1,"syntology":null},{"paper":null,"slug":"discovering-latent-concepts-learned-in-bert-1","title":"Discovering Latent Concepts Learned in BERT","date":"2022-05-15","arxiv_id":"2205.07237","n_code_links":0,"syntology":null},{"paper":"/paper/downstream-transformer-generation-of-question","slug":"downstream-transformer-generation-of-question","title":"Downstream Transformer Generation of Question-Answer Pairs with Preprocessing and Postprocessing Pipelines","date":"2022-05-15","arxiv_id":"2205.07387","n_code_links":1,"syntology":null},{"paper":"/paper/learning-lip-based-audio-visual-speaker","slug":"learning-lip-based-audio-visual-speaker","title":"Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT","date":"2022-05-15","arxiv_id":"2205.07180","n_code_links":1,"syntology":null},{"paper":null,"slug":"fake-news-quick-detection-on-dynamic","title":"Fake News Quick Detection on Dynamic Heterogeneous Information Networks","date":"2022-05-14","arxiv_id":"2205.07039","n_code_links":0,"syntology":null},{"paper":"/paper/naturalistic-causal-probing-for-morpho-syntax","slug":"naturalistic-causal-probing-for-morpho-syntax","title":"Naturalistic Causal Probing for Morpho-Syntax","date":"2022-05-14","arxiv_id":"2205.07043","n_code_links":1,"syntology":null},{"paper":"/paper/rasat-integrating-relational-structures-into","slug":"rasat-integrating-relational-structures-into","title":"RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL","date":"2022-05-14","arxiv_id":"2205.06983","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["lumia-group/rasat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-study-of-the-attention-abnormality-in-1","slug":"a-study-of-the-attention-abnormality-in-1","title":"A Study of the Attention Abnormality in Trojaned BERTs","date":"2022-05-13","arxiv_id":"2205.08305","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":["weimin17/attention_abnormality_in_trojaned_berts"],"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":"improving-contextual-representation-with-1","title":"Improving Contextual Representation with Gloss Regularized Pre-training","date":"2022-05-13","arxiv_id":"2205.06603","n_code_links":0,"syntology":null},{"paper":null,"slug":"apptek-s-submission-to-the-iwslt-2022","title":"AppTek's Submission to the IWSLT 2022 Isometric Spoken Language Translation Task","date":"2022-05-12","arxiv_id":"2205.05807","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-the-computation-of-abstract-sameness","title":"Is the Computation of Abstract Sameness Relations Human-Like in Neural Language Models?","date":"2022-05-12","arxiv_id":"2205.06149","n_code_links":0,"syntology":null},{"paper":null,"slug":"ner-mqmrc-formulating-named-entity","title":"NER-MQMRC: Formulating Named Entity Recognition as Multi Question Machine Reading Comprehension","date":"2022-05-12","arxiv_id":"2205.05904","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-time-varying-study-of-chinese-investor","title":"A time-varying study of Chinese investor sentiment, stock market liquidity and volatility: Based on deep learning BERT model and TVP-VAR model","date":"2022-05-11","arxiv_id":"2205.05719","n_code_links":0,"syntology":null},{"paper":"/paper/clinical-prompt-learning-with-frozen-language","slug":"clinical-prompt-learning-with-frozen-language","title":"Clinical Prompt Learning with Frozen Language Models","date":"2022-05-11","arxiv_id":"2205.05535","n_code_links":1,"syntology":null},{"paper":"/paper/query-based-keyphrase-extraction-from-long","slug":"query-based-keyphrase-extraction-from-long","title":"Query-Based Keyphrase Extraction from Long Documents","date":"2022-05-11","arxiv_id":"2205.05391","n_code_links":1,"syntology":null},{"paper":"/paper/towards-the-generation-of-musical","slug":"towards-the-generation-of-musical","title":"Towards the Generation of Musical Explanations with GPT-3","date":"2022-05-11","arxiv_id":"2206.08264","n_code_links":1,"syntology":null}],"record_sha256":"f6c1d978e05c3874116a6a929967f4a1cbd795be36eb864fdb4c617e7a467551","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}