{"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/72","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":72,"pages_in_order":109,"rows_per_page":100,"rows":[7101,7200],"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/71","next":"/method/attention-dropout/papers/73","papers":[{"paper":"/paper/a-multi-task-semi-supervised-framework-for","slug":"a-multi-task-semi-supervised-framework-for","title":"A multi-task semi-supervised framework for Text2Graph & Graph2Text","date":"2022-02-12","arxiv_id":"2202.06041","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-issue-classifier-a-transfer","slug":"automatic-issue-classifier-a-transfer","title":"Automatic Issue Classifier: A Transfer Learning Framework for Classifying Issue Reports","date":"2022-02-12","arxiv_id":"2202.06149","n_code_links":1,"syntology":null},{"paper":"/paper/maximizing-communication-efficiency-for-large","slug":"maximizing-communication-efficiency-for-large","title":"Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam","date":"2022-02-12","arxiv_id":"2202.06009","n_code_links":1,"syntology":null},{"paper":null,"slug":"hat5-hate-language-identification-using-text","title":"HaT5: Hate Language Identification using Text-to-Text Transfer Transformer","date":"2022-02-11","arxiv_id":"2202.05690","n_code_links":0,"syntology":null},{"paper":"/paper/white-box-attacks-on-hate-speech-bert","slug":"white-box-attacks-on-hate-speech-bert","title":"White-Box Attacks on Hate-speech BERT Classifiers in German with Explicit and Implicit Character Level Defense","date":"2022-02-11","arxiv_id":"2202.05778","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-task-learning-framework-for-product","title":"A Multi-task Learning Framework for Product Ranking with BERT","date":"2022-02-10","arxiv_id":"2202.05317","n_code_links":0,"syntology":null},{"paper":null,"slug":"slovene-superglue-benchmark-translation-and","title":"Slovene SuperGLUE Benchmark: Translation and Evaluation","date":"2022-02-10","arxiv_id":"2202.04994","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-open-domain-question-answering-systems","title":"Can Open Domain Question Answering Systems Answer Visual Knowledge Questions?","date":"2022-02-09","arxiv_id":"2202.04306","n_code_links":0,"syntology":null},{"paper":null,"slug":"merit-based-fusion-of-nlp-techniques-for","title":"Social Media as an Instant Source of Feedback on Water Quality","date":"2022-02-09","arxiv_id":"2202.04462","n_code_links":0,"syntology":null},{"paper":"/paper/pnlp-mixer-an-efficient-all-mlp-architecture","slug":"pnlp-mixer-an-efficient-all-mlp-architecture","title":"pNLP-Mixer: an Efficient all-MLP Architecture for Language","date":"2022-02-09","arxiv_id":"2202.04350","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-language-models-learn-position-role","title":"Do Language Models Learn Position-Role Mappings?","date":"2022-02-08","arxiv_id":"2202.03611","n_code_links":0,"syntology":null},{"paper":"/paper/histbert-a-pre-trained-language-model-for","slug":"histbert-a-pre-trained-language-model-for","title":"HistBERT: A Pre-trained Language Model for Diachronic Lexical Semantic Analysis","date":"2022-02-08","arxiv_id":"2202.03612","n_code_links":1,"syntology":null},{"paper":null,"slug":"logical-reasoning-for-task-oriented-dialogue","title":"Logical Reasoning for Task Oriented Dialogue Systems","date":"2022-02-08","arxiv_id":"2202.04161","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-features-of-object-concepts","slug":"semantic-features-of-object-concepts","title":"Semantic features of object concepts generated with GPT-3","date":"2022-02-08","arxiv_id":"2202.03753","n_code_links":1,"syntology":null},{"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/cedille-a-large-autoregressive-french","slug":"cedille-a-large-autoregressive-french","title":"Cedille: A large autoregressive French language model","date":"2022-02-07","arxiv_id":"2202.03371","n_code_links":1,"syntology":null},{"paper":"/paper/unifying-architectures-tasks-and-modalities","slug":"unifying-architectures-tasks-and-modalities","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","date":"2022-02-07","arxiv_id":"2202.03052","n_code_links":4,"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":["ofa-sys/ofa"],"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/evaluating-natural-language-processing-models","slug":"evaluating-natural-language-processing-models","title":"Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data","date":"2022-02-06","arxiv_id":"2202.02842","n_code_links":1,"syntology":null},{"paper":null,"slug":"classification-on-sentence-embeddings-for","title":"Classification on Sentence Embeddings for Legal Assistance","date":"2022-02-05","arxiv_id":"2202.02639","n_code_links":0,"syntology":null},{"paper":null,"slug":"ethics-rules-of-engagement-and-ai-neural","title":"Ethics, Rules of Engagement, and AI: Neural Narrative Mapping Using Large Transformer Language Models","date":"2022-02-05","arxiv_id":"2202.02647","n_code_links":0,"syntology":null},{"paper":"/paper/a-benchmark-corpus-for-the-detection-of","slug":"a-benchmark-corpus-for-the-detection-of","title":"A Benchmark Corpus for the Detection of Automatically Generated Text in Academic Publications","date":"2022-02-04","arxiv_id":"2202.02013","n_code_links":1,"syntology":null},{"paper":null,"slug":"stonkbert-can-language-models-predict-medium","title":"StonkBERT: Can Language Models Predict Medium-Run Stock Price Movements?","date":"2022-02-04","arxiv_id":"2202.02268","n_code_links":0,"syntology":null},{"paper":"/paper/temporal-attention-for-language-models","slug":"temporal-attention-for-language-models","title":"Temporal Attention for Language Models","date":"2022-02-04","arxiv_id":"2202.02093","n_code_links":1,"syntology":null},{"paper":null,"slug":"asr-aware-end-to-end-neural-diarization","title":"ASR-Aware End-to-end Neural Diarization","date":"2022-02-02","arxiv_id":"2202.01286","n_code_links":0,"syntology":null},{"paper":"/paper/co-training-improves-prompt-based-learning","slug":"co-training-improves-prompt-based-learning","title":"Co-training Improves Prompt-based Learning for Large Language Models","date":"2022-02-02","arxiv_id":"2202.00828","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"pointer_only":0,"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) · 5 unverified","official":{"repos":["clinicalml/cotrain-prompting"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/gatortron-a-large-clinical-language-model-to","slug":"gatortron-a-large-clinical-language-model-to","title":"GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records","date":"2022-02-02","arxiv_id":"2203.03540","n_code_links":0,"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":"rescorebert-discriminative-speech-recognition","title":"RescoreBERT: Discriminative Speech Recognition Rescoring with BERT","date":"2022-02-02","arxiv_id":"2202.01094","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-training-of-neural-networks-using","title":"Robust Training of Neural Networks Using Scale Invariant Architectures","date":"2022-02-02","arxiv_id":"2202.00980","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-flexible-clustering-pipeline-for-mining","title":"An Adaptive Deep Clustering Pipeline to Inform Text Labeling at Scale","date":"2022-02-01","arxiv_id":"2202.01211","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-semi-supervised-deep-clustering-pipeline","title":"A Semi-Supervised Deep Clustering Pipeline for Mining Intentions From Texts","date":"2022-02-01","arxiv_id":"2202.00802","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-bert-based-query-by-document","title":"Improving BERT-based Query-by-Document Retrieval with Multi-Task Optimization","date":"2022-02-01","arxiv_id":"2202.00373","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-models-of-text","title":"Transformer-based Models of Text Normalization for Speech Applications","date":"2022-02-01","arxiv_id":"2202.00153","n_code_links":0,"syntology":null},{"paper":"/paper/boat-bilateral-local-attention-vision","slug":"boat-bilateral-local-attention-vision","title":"BOAT: Bilateral Local Attention Vision Transformer","date":"2022-01-31","arxiv_id":"2201.13027","n_code_links":1,"syntology":null},{"paper":"/paper/memory-efficient-backpropagation-through","slug":"memory-efficient-backpropagation-through","title":"Memory-Efficient Backpropagation through Large Linear Layers","date":"2022-01-31","arxiv_id":"2201.13195","n_code_links":2,"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":"/paper/chain-of-thought-prompting-elicits-reasoning","slug":"chain-of-thought-prompting-elicits-reasoning","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","date":"2022-01-28","arxiv_id":"2201.11903","n_code_links":19,"syntology":{"ran":5,"of":7,"n_ran_checked":4,"n_instrument":1,"unverified":2,"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) · 2 unverified","official":null}},{"paper":null,"slug":"electra-conditional-generative-model-based","title":"Electra: Conditional Generative Model based Predicate-Aware Query Approximation","date":"2022-01-28","arxiv_id":"2201.12420","n_code_links":0,"syntology":null},{"paper":"/paper/summarizing-differences-between-text","slug":"summarizing-differences-between-text","title":"Describing Differences between Text Distributions with Natural Language","date":"2022-01-28","arxiv_id":"2201.12323","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ruiqi-zhong/describedistributionaldifferences"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/clinical-longformer-and-clinical-bigbird","slug":"clinical-longformer-and-clinical-bigbird","title":"Clinical-Longformer and Clinical-BigBird: Transformers for long clinical sequences","date":"2022-01-27","arxiv_id":"2201.11838","n_code_links":1,"syntology":null},{"paper":"/paper/going-extreme-comparative-analysis-of-hate","slug":"going-extreme-comparative-analysis-of-hate","title":"Going Extreme: Comparative Analysis of Hate Speech in Parler and Gab","date":"2022-01-27","arxiv_id":"2201.11770","n_code_links":1,"syntology":null},{"paper":"/paper/grad2task-improved-few-shot-text-1","slug":"grad2task-improved-few-shot-text-1","title":"Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation","date":"2022-01-27","arxiv_id":"2201.11576","n_code_links":1,"syntology":null},{"paper":"/paper/a-comprehensive-study-of-image-classification","slug":"a-comprehensive-study-of-image-classification","title":"A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes","date":"2022-01-26","arxiv_id":"2201.10766","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["mmoayeri/rival10"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/discoscore-evaluating-text-generation-with","slug":"discoscore-evaluating-text-generation-with","title":"DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence","date":"2022-01-26","arxiv_id":"2201.11176","n_code_links":1,"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":"/paper/fincat-financial-numeral-claim-analysis-tool","slug":"fincat-financial-numeral-claim-analysis-tool","title":"FiNCAT: Financial Numeral Claim Analysis Tool","date":"2022-01-26","arxiv_id":"2202.00631","n_code_links":1,"syntology":null},{"paper":"/paper/neural-grapheme-to-phoneme-conversion-with","slug":"neural-grapheme-to-phoneme-conversion-with","title":"Neural Grapheme-to-Phoneme Conversion with Pre-trained Grapheme Models","date":"2022-01-26","arxiv_id":"2201.10716","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-supervised-3d-semantic-representation","title":"Self-supervised 3D Semantic Representation Learning for Vision-and-Language Navigation","date":"2022-01-26","arxiv_id":"2201.10788","n_code_links":0,"syntology":null},{"paper":"/paper/synchromesh-reliable-code-generation-from-pre-1","slug":"synchromesh-reliable-code-generation-from-pre-1","title":"Synchromesh: Reliable code generation from pre-trained language models","date":"2022-01-26","arxiv_id":"2201.11227","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":"/paper/bertha-video-captioning-evaluation-via","slug":"bertha-video-captioning-evaluation-via","title":"BERTHA: Video Captioning Evaluation Via Transfer-Learned Human Assessment","date":"2022-01-25","arxiv_id":"2201.10243","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-non-autoregressive-end-to-end","title":"Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models","date":"2022-01-25","arxiv_id":"2201.10103","n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-trained-language-transformers-are","title":"Pre-Trained Language Transformers are Universal Image Classifiers","date":"2022-01-25","arxiv_id":"2201.10182","n_code_links":0,"syntology":null},{"paper":null,"slug":"whose-language-counts-as-high-quality","title":"Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection","date":"2022-01-25","arxiv_id":"2201.10474","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-based-modeling-of-mental-disorders-on","title":"Emotion-based Modeling of Mental Disorders on Social Media","date":"2022-01-24","arxiv_id":"2201.09451","n_code_links":0,"syntology":null},{"paper":null,"slug":"polyphone-disambiguation-and-accent","title":"Polyphone disambiguation and accent prediction using pre-trained language models in Japanese TTS front-end","date":"2022-01-24","arxiv_id":"2201.09427","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthetic-books","title":"Synthetic Books","date":"2022-01-24","arxiv_id":"2201.09518","n_code_links":0,"syntology":null},{"paper":"/paper/unified-multimodal-punctuation-restoration","slug":"unified-multimodal-punctuation-restoration","title":"Unified Multimodal Punctuation Restoration Framework for Mixed-Modality Corpus","date":"2022-01-24","arxiv_id":"2202.00468","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-large-and-diverse-arabic-corpus-for","title":"A Large and Diverse Arabic Corpus for Language Modeling","date":"2022-01-23","arxiv_id":"2201.09227","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-application-of-pseudo-log-likelihoods-to","title":"An Application of Pseudo-Log-Likelihoods to Natural Language Scoring","date":"2022-01-23","arxiv_id":"2201.09377","n_code_links":0,"syntology":null},{"paper":"/paper/a-comparative-study-on-language-models-for-1","slug":"a-comparative-study-on-language-models-for-1","title":"A Comparative Study on Language Models for Task-Oriented Dialogue Systems","date":"2022-01-21","arxiv_id":"2201.08687","n_code_links":1,"syntology":null},{"paper":"/paper/black-box-prompt-learning-for-pre-trained","slug":"black-box-prompt-learning-for-pre-trained","title":"Black-box Prompt Learning for Pre-trained Language Models","date":"2022-01-21","arxiv_id":"2201.08531","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["shizhediao/black-box-prompt-learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/dual-contrastive-learning-text-classification","slug":"dual-contrastive-learning-text-classification","title":"Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation","date":"2022-01-21","arxiv_id":"2201.08702","n_code_links":2,"syntology":null},{"paper":null,"slug":"less-is-less-when-are-snippets-insufficient","title":"Less is Less: When Are Snippets Insufficient for Human vs Machine Relevance Estimation?","date":"2022-01-21","arxiv_id":"2201.08721","n_code_links":0,"syntology":null},{"paper":"/paper/cheating-automatic-short-answer-grading-on","slug":"cheating-automatic-short-answer-grading-on","title":"Cheating Automatic Short Answer Grading: On the Adversarial Usage of Adjectives and Adverbs","date":"2022-01-20","arxiv_id":"2201.08318","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentiment-analysis-predicting-yelp-scores","title":"Sentiment Analysis: Predicting Yelp Scores","date":"2022-01-20","arxiv_id":"2201.07999","n_code_links":0,"syntology":null},{"paper":null,"slug":"tervit-an-efficient-ternary-vision","title":"TerViT: An Efficient Ternary Vision Transformer","date":"2022-01-20","arxiv_id":"2201.08050","n_code_links":0,"syntology":null},{"paper":"/paper/transfer-learning-approaches-for-building","slug":"transfer-learning-approaches-for-building","title":"Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models","date":"2022-01-20","arxiv_id":"2201.08471","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":["hltcoe/colbert-x"],"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/gap-gen-guided-automatic-python-code","slug":"gap-gen-guided-automatic-python-code","title":"GAP-Gen: Guided Automatic Python Code Generation","date":"2022-01-19","arxiv_id":"2201.08810","n_code_links":1,"syntology":null},{"paper":"/paper/near-optimal-sparse-allreduce-for-distributed","slug":"near-optimal-sparse-allreduce-for-distributed","title":"Near-Optimal Sparse Allreduce for Distributed Deep Learning","date":"2022-01-19","arxiv_id":"2201.07598","n_code_links":1,"syntology":null},{"paper":"/paper/q-vit-fully-differentiable-quantization-for","slug":"q-vit-fully-differentiable-quantization-for","title":"Q-ViT: Fully Differentiable Quantization for Vision Transformer","date":"2022-01-19","arxiv_id":"2201.07703","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":9,"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) · 2 unverified","official":{"repos":["zhexinli/Q-ViT-DeiT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"tourbert-a-pretrained-language-model-for-the","title":"TourBERT: A pretrained language model for the tourism industry","date":"2022-01-19","arxiv_id":"2201.07449","n_code_links":0,"syntology":null},{"paper":"/paper/coauthor-designing-a-human-ai-collaborative","slug":"coauthor-designing-a-human-ai-collaborative","title":"CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities","date":"2022-01-18","arxiv_id":"2201.06796","n_code_links":1,"syntology":null},{"paper":null,"slug":"hierarchical-neural-network-approaches-for","title":"Hierarchical Neural Network Approaches for Long Document Classification","date":"2022-01-18","arxiv_id":"2201.06774","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-vs-albert-explained","title":"BERT vs ALBERT explained","date":"2022-01-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/mulve-a-multi-language-vocabulary-evaluation","slug":"mulve-a-multi-language-vocabulary-evaluation","title":"MuLVE, A Multi-Language Vocabulary Evaluation Data Set","date":"2022-01-17","arxiv_id":"2201.06286","n_code_links":0,"syntology":null},{"paper":null,"slug":"unintended-bias-in-language-model","title":"Unintended Bias in Language Model-driven Conversational Recommendation","date":"2022-01-17","arxiv_id":"2201.06224","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-balanced-data-approach-for-evaluating-cross","title":"A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood Bank","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-granularity-opinion-summarization","title":"A Multi-Granularity Opinion Summarization Method","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-of-pre-trained-language-models-for","title":"A Study of Pre-trained Language Models for Analogy Generation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-of-the-attention-abnormality-in","title":"A Study of the Attention Abnormality in Trojaned BERTs","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"allwoz-towards-multilingual-task-oriented-1","title":"AllWOZ: Towards Multilingual Task-Oriented Dialog Systems for All","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exploitation-of-heterogeneous-graph-neural","title":"An Exploitation of Heterogeneous Graph Neural Network for Extractive Long Document Summarization","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"applying-softtriple-loss-for-supervised-1","title":"Applying SoftTriple Loss for Supervised Language Model Fine Tuning","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"arabart-a-pretrained-arabic-sequence-to","title":"AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"are-pretrained-multilingual-models-equally","title":"Are Pretrained Multilingual Models Equally Fair Across Languages?","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"auto-regressive-text-generation-with-pre","title":"Auto-regressive Text Generation with Pre-Trained Language Models: An Empirical Study on Question-type Short Text Generation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"autoattention-automatic-attention-head","title":"AutoAttention: Automatic Attention Head Selection Through Differentiable Pruning","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bridge-the-gap-between-cv-and-nlp-a-gradient-1","title":"Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"can-bert-conduct-logical-reasoning-on-the","title":"Can BERT Conduct Logical Reasoning? On the Difficulty of Learning to Reason from Data","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"context-aware-prompt-customize-a-unique","title":"Context-Aware Prompt: Customize A Unique Prompt For Each Input","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deck-behavioral-tests-to-improve","title":"DECK: Behavioral Tests to Improve Interpretability and Generalizability of BERT Models Detecting Depression from Text","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"divide-and-conquer-text-semantic-matching","title":"Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"do-berts-learn-to-use-browser-user-interface","title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-hierarchical-domain-adaptation-for-1","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-zero-shot-semantic-parsing-with","title":"Efficient Zero-Shot Semantic Parsing with Paraphrasing from Pretrained Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"eici-a-new-method-of-dynamic-embedding","title":"EiCi: A New Method of Dynamic Embedding Incorporating Contextual Information in Chinese NER","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"elastic-weight-consolidation-for-reduction-of","title":"Elastic Weight Consolidation for Reduction of Catastrophic Forgetting in GPT-2","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"event-detection-via-derangement-reading","title":"Event Detection via Derangement Reading Comprehension","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"experiments-with-adversarial-attacks-on-text-1","title":"Experiments with adversarial attacks on text genres","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-example-selection-for-few-shot-text","title":"Exploring Example Selection for Few-shot Text-to-SQL Semantic Parsing","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"f0eb94c601a1e814beed45bb91bb5d0ebe45e681d7c807e181748aa72dc9be5b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}