{"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/layer-normalization/papers/207","list_of":"/method/layer-normalization","method":"Layer Normalization","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":207,"pages_in_order":250,"rows_per_page":100,"rows":[20601,20700],"of":24980,"counts":{"archive_papers_tagged":24980,"with_a_code_link":11273,"where_syntology_ran_a_sample":3471,"not_listed_spam_title":0,"listed":24980,"listed_where_code_ran":3471,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2923,"every_run_a_failure_of_syntologys_instrument":548,"listed_with_a_run_with_no_instrument_failure":2923,"listed_every_run_a_failure_of_syntologys_instrument":548,"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/layer-normalization","prev":"/method/layer-normalization/papers/206","next":"/method/layer-normalization/papers/208","papers":[{"paper":"/paper/less-is-more-pay-less-attention-in-vision","slug":"less-is-more-pay-less-attention-in-vision","title":"Less is More: Pay Less Attention in Vision Transformers","date":"2021-05-29","arxiv_id":"2105.14217","n_code_links":2,"syntology":null},{"paper":"/paper/sentiment-analysis-in-tweets-an-assessment","slug":"sentiment-analysis-in-tweets-an-assessment","title":"Sentiment analysis in tweets: an assessment study from classical to modern text representation models","date":"2021-05-29","arxiv_id":"2105.14373","n_code_links":1,"syntology":null},{"paper":null,"slug":"ufc-bert-unifying-multi-modal-controls-for","title":"M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers","date":"2021-05-29","arxiv_id":"2105.14211","n_code_links":0,"syntology":null},{"paper":"/paper/accelerating-bert-inference-for-sequence","slug":"accelerating-bert-inference-for-sequence","title":"Accelerating BERT Inference for Sequence Labeling via Early-Exit","date":"2021-05-28","arxiv_id":"2105.13878","n_code_links":1,"syntology":null},{"paper":"/paper/an-attention-free-transformer-1","slug":"an-attention-free-transformer-1","title":"An Attention Free Transformer","date":"2021-05-28","arxiv_id":"2105.14103","n_code_links":11,"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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/byt5-towards-a-token-free-future-with-pre","slug":"byt5-towards-a-token-free-future-with-pre","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","date":"2021-05-28","arxiv_id":"2105.13626","n_code_links":5,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["google-research/byt5"],"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":["listed","official"]}}},{"paper":"/paper/compositionally-restricted-attention-based","slug":"compositionally-restricted-attention-based","title":"Compositionally restricted attention-based network for materials property predictions","date":"2021-05-28","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"domain-adaptive-pretraining-methods-for","title":"Domain-Adaptive Pretraining Methods for Dialogue Understanding","date":"2021-05-28","arxiv_id":"2105.13665","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-transformer-encoders-for","slug":"hierarchical-transformer-encoders-for","title":"Hierarchical Transformer Encoders for Vietnamese Spelling Correction","date":"2021-05-28","arxiv_id":"2105.13578","n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-inheritance-for-pre-trained","slug":"knowledge-inheritance-for-pre-trained","title":"Knowledge Inheritance for Pre-trained Language Models","date":"2021-05-28","arxiv_id":"2105.13880","n_code_links":2,"syntology":null},{"paper":"/paper/kvt-k-nn-attention-for-boosting-vision","slug":"kvt-k-nn-attention-for-boosting-vision","title":"KVT: k-NN Attention for Boosting Vision Transformers","date":"2021-05-28","arxiv_id":"2106.00515","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":["damo-cv/kvt"],"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/mixergan-an-mlp-based-architecture-for","slug":"mixergan-an-mlp-based-architecture-for","title":"MixerGAN: An MLP-Based Architecture for Unpaired Image-to-Image Translation","date":"2021-05-28","arxiv_id":"2105.14110","n_code_links":1,"syntology":null},{"paper":"/paper/ptnet-a-high-resolution-infant-mri","slug":"ptnet-a-high-resolution-infant-mri","title":"PTNet: A High-Resolution Infant MRI Synthesizer Based on Transformer","date":"2021-05-28","arxiv_id":"2105.13993","n_code_links":1,"syntology":null},{"paper":null,"slug":"reinforcement-learning-for-on-line-sequence","title":"Reinforcement Learning for on-line Sequence Transformation","date":"2021-05-28","arxiv_id":"2105.14097","n_code_links":0,"syntology":null},{"paper":"/paper/rest-an-efficient-transformer-for-visual","slug":"rest-an-efficient-transformer-for-visual","title":"ResT: An Efficient Transformer for Visual Recognition","date":"2021-05-28","arxiv_id":"2105.13677","n_code_links":5,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":9,"phrase":"9 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wofmanaf/ResT"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/scifive-a-text-to-text-transformer-model-for","slug":"scifive-a-text-to-text-transformer-model-for","title":"SciFive: a text-to-text transformer model for biomedical literature","date":"2021-05-28","arxiv_id":"2106.03598","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["justinphan3110/SciFive"],"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":["official"]}}},{"paper":"/paper/towards-mental-time-travel-a-hierarchical","slug":"towards-mental-time-travel-a-hierarchical","title":"Towards mental time travel: a hierarchical memory for reinforcement learning agents","date":"2021-05-28","arxiv_id":"2105.14039","n_code_links":5,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"3 ran (of which 2 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) · 3 unverified","official":{"repos":["deepmind/deepmind-research","deepmind/dm_fast_mapping"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"transcamp-graph-transformer-for-6-dof-camera","title":"TransCamP: Graph Transformer for 6-DoF Camera Pose Estimation","date":"2021-05-28","arxiv_id":"2105.14065","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-source-free-domain","slug":"transformer-based-source-free-domain","title":"Transformer-Based Source-Free Domain Adaptation","date":"2021-05-28","arxiv_id":"2105.14138","n_code_links":1,"syntology":null},{"paper":"/paper/weighted-training-for-cross-task-learning","slug":"weighted-training-for-cross-task-learning","title":"Weighted Training for Cross-Task Learning","date":"2021-05-28","arxiv_id":"2105.14095","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: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["HornHehhf/TAWT"],"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":null,"slug":"contrastive-fine-tuning-improves-robustness","title":"Contrastive Fine-tuning Improves Robustness for Neural Rankers","date":"2021-05-27","arxiv_id":"2105.12932","n_code_links":0,"syntology":null},{"paper":null,"slug":"diagnosing-transformers-in-task-oriented","title":"Diagnosing Transformers in Task-Oriented Semantic Parsing","date":"2021-05-27","arxiv_id":"2105.13496","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-adversarial-imitation-learning-for","title":"Generative Adversarial Imitation Learning for Empathy-based AI","date":"2021-05-27","arxiv_id":"2105.13328","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-does-distilled-data-complexity-impact-the","title":"How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation?","date":"2021-05-27","arxiv_id":"2105.12900","n_code_links":0,"syntology":null},{"paper":"/paper/learning-dynamic-graph-representation-of","slug":"learning-dynamic-graph-representation-of","title":"Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention","date":"2021-05-27","arxiv_id":"2105.13495","n_code_links":2,"syntology":{"ran":13,"of":15,"n_ran_checked":13,"n_instrument":0,"unverified":2,"pointer_only":15,"phrase":"13 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["egyptdj/stagin"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"leveraging-linguistic-coordination-in","title":"Leveraging Linguistic Coordination in Reranking N-Best Candidates For End-to-End Response Selection Using BERT","date":"2021-05-27","arxiv_id":"2105.13479","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixqa-embedding-and-answer-mixing-for","title":"MixQA: Embedding and Answer Mixing for Question Answering","date":"2021-05-27","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"path-based-knowledge-reasoning-with-textual","title":"Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion","date":"2021-05-27","arxiv_id":"2105.13074","n_code_links":0,"syntology":null},{"paper":"/paper/raw-c-relatedness-of-ambiguous-words-in","slug":"raw-c-relatedness-of-ambiguous-words-in","title":"RAW-C: Relatedness of Ambiguous Words--in Context (A New Lexical Resource for English)","date":"2021-05-27","arxiv_id":"2105.13266","n_code_links":1,"syntology":null},{"paper":"/paper/selective-knowledge-distillation-for-neural","slug":"selective-knowledge-distillation-for-neural","title":"Selective Knowledge Distillation for Neural Machine Translation","date":"2021-05-27","arxiv_id":"2105.12967","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"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) · 1 unverified","official":{"repos":["LeslieOverfitting/selective_distillation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"verb-sense-clustering-using-contextualized","title":"Verb Sense Clustering using Contextualized Word Representations for Semantic Frame Induction","date":"2021-05-27","arxiv_id":"2105.13465","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-full-stack-accelerator-search-technique-for","title":"A Full-Stack Search Technique for Domain Optimized Deep Learning Accelerators","date":"2021-05-26","arxiv_id":"2105.12842","n_code_links":0,"syntology":null},{"paper":"/paper/aggregating-nested-transformers","slug":"aggregating-nested-transformers","title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding","date":"2021-05-26","arxiv_id":"2105.12723","n_code_links":6,"syntology":{"ran":19,"of":26,"n_ran_checked":18,"n_instrument":1,"unverified":7,"pointer_only":6,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 1 violated, 16 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","official":{"repos":["google-research/nested-transformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/bertifying-the-hidden-markov-model-for-multi","slug":"bertifying-the-hidden-markov-model-for-multi","title":"BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition","date":"2021-05-26","arxiv_id":"2105.12848","n_code_links":2,"syntology":{"ran":10,"of":20,"n_ran_checked":10,"n_instrument":0,"unverified":10,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","official":{"repos":["Yinghao-Li/CHMM-ALT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/bilingual-mutual-information-based-adaptive","slug":"bilingual-mutual-information-based-adaptive","title":"Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation","date":"2021-05-26","arxiv_id":"2105.12523","n_code_links":1,"syntology":null},{"paper":null,"slug":"bionavi-np-biosynthesis-navigator-for-natural","title":"BioNavi-NP: Biosynthesis Navigator for Natural Products","date":"2021-05-26","arxiv_id":"2105.13121","n_code_links":0,"syntology":null},{"paper":"/paper/cogview-mastering-text-to-image-generation","slug":"cogview-mastering-text-to-image-generation","title":"CogView: Mastering Text-to-Image Generation via Transformers","date":"2021-05-26","arxiv_id":"2105.13290","n_code_links":4,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["THUDM/CogView"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deception-detection-in-text-and-its-relation","title":"Deception detection in text and its relation to the cultural dimension of individualism/collectivism","date":"2021-05-26","arxiv_id":"2105.12530","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequence-parallelism-making-4d-parallelism","title":"Sequence Parallelism: Long Sequence Training from System Perspective","date":"2021-05-26","arxiv_id":"2105.13120","n_code_links":0,"syntology":null},{"paper":"/paper/trade-the-event-corporate-events-detection","slug":"trade-the-event-corporate-events-detection","title":"Trade the Event: Corporate Events Detection for News-Based Event-Driven Trading","date":"2021-05-26","arxiv_id":"2105.12825","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Zhihan1996/TradeTheEvent"],"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":null,"slug":"zero-shot-medical-entity-retrieval-without","title":"Zero-shot Medical Entity Retrieval without Annotation: Learning From Rich Knowledge Graph Semantics","date":"2021-05-26","arxiv_id":"2105.12682","n_code_links":0,"syntology":null},{"paper":"/paper/consert-a-contrastive-framework-for-self","slug":"consert-a-contrastive-framework-for-self","title":"ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer","date":"2021-05-25","arxiv_id":"2105.11741","n_code_links":1,"syntology":null},{"paper":null,"slug":"context-sensitive-visualization-of-deep","title":"Context-Sensitive Visualization of Deep Learning Natural Language Processing Models","date":"2021-05-25","arxiv_id":"2105.12202","n_code_links":0,"syntology":null},{"paper":"/paper/enhance-multimodal-model-performance-with","slug":"enhance-multimodal-model-performance-with","title":"Enhance Multimodal Model Performance with Data Augmentation: Facebook Hateful Meme Challenge Solution","date":"2021-05-25","arxiv_id":"2105.13132","n_code_links":1,"syntology":null},{"paper":null,"slug":"extending-the-abstraction-of-personality","title":"Extending the Abstraction of Personality Types based on MBTI with Machine Learning and Natural Language Processing","date":"2021-05-25","arxiv_id":"2105.11798","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-learning-of-generation-and","title":"Multi-Task Learning of Generation and Classification for Emotion-Aware Dialogue Response Generation","date":"2021-05-25","arxiv_id":"2105.11696","n_code_links":0,"syntology":null},{"paper":null,"slug":"nukelm-pre-trained-and-fine-tuned-language","title":"NukeLM: Pre-Trained and Fine-Tuned Language Models for the Nuclear and Energy Domains","date":"2021-05-25","arxiv_id":"2105.12192","n_code_links":0,"syntology":null},{"paper":"/paper/personalized-transformer-for-explainable","slug":"personalized-transformer-for-explainable","title":"Personalized Transformer for Explainable Recommendation","date":"2021-05-25","arxiv_id":"2105.11601","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":5,"n_instrument":1,"unverified":2,"pointer_only":8,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["lileipisces/PETER"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"temporal-action-proposal-generation-with","title":"Temporal Action Proposal Generation with Transformers","date":"2021-05-25","arxiv_id":"2105.12043","n_code_links":0,"syntology":null},{"paper":null,"slug":"topic-modeling-and-progression-of-american","title":"Topic Modeling and Progression of American Digital News Media During the Onset of the COVID-19 Pandemic","date":"2021-05-25","arxiv_id":"2106.09572","n_code_links":0,"syntology":null},{"paper":"/paper/tr-bert-dynamic-token-reduction-for","slug":"tr-bert-dynamic-token-reduction-for","title":"TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference","date":"2021-05-25","arxiv_id":"2105.11618","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-mobile-gui-from-pixel-words-to","title":"Understanding Mobile GUI: from Pixel-Words to Screen-Sentences","date":"2021-05-25","arxiv_id":"2105.11941","n_code_links":0,"syntology":null},{"paper":null,"slug":"vibertgrid-a-jointly-trained-multi-modal-2d","title":"ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents","date":"2021-05-25","arxiv_id":"2105.11672","n_code_links":0,"syntology":null},{"paper":null,"slug":"classifying-math-kcs-via-task-adaptive-pre","title":"Classifying Math KCs via Task-Adaptive Pre-Trained BERT","date":"2021-05-24","arxiv_id":"2105.11343","n_code_links":0,"syntology":null},{"paper":"/paper/dan-danish-nested-named-entities-and-lexical","slug":"dan-danish-nested-named-entities-and-lexical","title":"DaN+: Danish Nested Named Entities and Lexical Normalization","date":"2021-05-24","arxiv_id":"2105.11301","n_code_links":1,"syntology":null},{"paper":"/paper/de-identification-of-privacy-related-entities","slug":"de-identification-of-privacy-related-entities","title":"De-identification of Privacy-related Entities in Job Postings","date":"2021-05-24","arxiv_id":"2105.11223","n_code_links":1,"syntology":null},{"paper":"/paper/diacritics-restoration-using-bert-with","slug":"diacritics-restoration-using-bert-with","title":"Diacritics Restoration using BERT with Analysis on Czech language","date":"2021-05-24","arxiv_id":"2105.11408","n_code_links":1,"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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ufal/bert-diacritics-restoration"],"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/fine-grained-post-training-for-improving","slug":"fine-grained-post-training-for-improving","title":"Fine-grained Post-training for Improving Retrieval-based Dialogue Systems","date":"2021-05-24","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/multi-modal-understanding-and-generation-for","slug":"multi-modal-understanding-and-generation-for","title":"Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training","date":"2021-05-24","arxiv_id":"2105.11333","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["SuperSupermoon/MedViLL"],"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/neural-language-models-for-nineteenth-century","slug":"neural-language-models-for-nineteenth-century","title":"Neural Language Models for Nineteenth-Century English","date":"2021-05-24","arxiv_id":"2105.11321","n_code_links":2,"syntology":null},{"paper":"/paper/prevent-the-language-model-from-being","slug":"prevent-the-language-model-from-being","title":"Prevent the Language Model from being Overconfident in Neural Machine Translation","date":"2021-05-24","arxiv_id":"2105.11098","n_code_links":1,"syntology":null},{"paper":"/paper/robeczech-czech-roberta-a-monolingual","slug":"robeczech-czech-roberta-a-monolingual","title":"RobeCzech: Czech RoBERTa, a monolingual contextualized language representation model","date":"2021-05-24","arxiv_id":"2105.11314","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-adversarial-attacks-to-reveal-the","title":"Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models","date":"2021-05-24","arxiv_id":"2105.11136","n_code_links":0,"syntology":null},{"paper":"/paper/citeworth-cite-worthiness-detection-for","slug":"citeworth-cite-worthiness-detection-for","title":"CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding","date":"2021-05-23","arxiv_id":"2105.10912","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-video-object-detection-with","slug":"end-to-end-video-object-detection-with","title":"End-to-End Video Object Detection with Spatial-Temporal Transformers","date":"2021-05-23","arxiv_id":"2105.10920","n_code_links":1,"syntology":null},{"paper":null,"slug":"killing-two-birds-with-one-stone-stealing","title":"Killing One Bird with Two Stones: Model Extraction and Attribute Inference Attacks against BERT-based APIs","date":"2021-05-23","arxiv_id":"2105.10909","n_code_links":0,"syntology":null},{"paper":"/paper/autolrs-automatic-learning-rate-schedule-by-1","slug":"autolrs-automatic-learning-rate-schedule-by-1","title":"AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly","date":"2021-05-22","arxiv_id":"2105.10762","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"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":["YuchenJin/autolrs"],"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/denoising-noisy-neural-networks-a-bayesian","slug":"denoising-noisy-neural-networks-a-bayesian","title":"Denoising Noisy Neural Networks: A Bayesian Approach with Compensation","date":"2021-05-22","arxiv_id":"2105.10699","n_code_links":1,"syntology":null},{"paper":null,"slug":"aligning-visual-prototypes-with-bert","title":"Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learning","date":"2021-05-21","arxiv_id":"2105.10195","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-as-inference-via-fenchel-duality","title":"Attention as Inference via Fenchel Duality","date":"2021-05-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-split-task-agnostic-vision-1","title":"Federated Split Task-Agnostic Vision Transformer for COVID-19 CXR Diagnosis","date":"2021-05-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/grounding-inductive-biases-in-natural-images-1","slug":"grounding-inductive-biases-in-natural-images-1","title":"Grounding inductive biases in natural images: invariance stems from variations in data","date":"2021-05-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/probing-inter-modality-visual-parsing-with-1","slug":"probing-inter-modality-visual-parsing-with-1","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-and-Language Pre-training","date":"2021-05-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/scatterbrain-unifying-sparse-and-low-rank-1","slug":"scatterbrain-unifying-sparse-and-low-rank-1","title":"Scatterbrain: Unifying Sparse and Low-rank Attention","date":"2021-05-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"stance-detection-with-bert-embeddings-for","title":"Stance Detection with BERT Embeddings for Credibility Analysis of Information on Social Media","date":"2021-05-21","arxiv_id":"2105.10272","n_code_links":0,"syntology":null},{"paper":"/paper/towards-automatic-comparison-of-data-privacy","slug":"towards-automatic-comparison-of-data-privacy","title":"Towards Automatic Comparison of Data Privacy Documents: A Preliminary Experiment on GDPR-like Laws","date":"2021-05-21","arxiv_id":"2105.10117","n_code_links":1,"syntology":null},{"paper":null,"slug":"ufc-bert-unifying-multi-modal-controls-for-1","title":"UFC-BERT: Unifying Multi-Modal Controls for Conditional Image Synthesis","date":"2021-05-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertainty-aware-abstractive-summarization","title":"Should We Trust This Summary? Bayesian Abstractive Summarization to The Rescue","date":"2021-05-21","arxiv_id":"2105.10155","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-multilingual-sentence-embeddings-1","title":"Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Mining","date":"2021-05-21","arxiv_id":"2105.10419","n_code_links":0,"syntology":null},{"paper":"/paper/a-comprehensive-comparative-evaluation-and","slug":"a-comprehensive-comparative-evaluation-and","title":"A comparative evaluation and analysis of three generations of Distributional Semantic Models","date":"2021-05-20","arxiv_id":"2105.09825","n_code_links":1,"syntology":null},{"paper":null,"slug":"content-augmented-feature-pyramid-network","title":"Content-Augmented Feature Pyramid Network with Light Linear Spatial Transformers for Object Detection","date":"2021-05-20","arxiv_id":"2105.09464","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-learning-for-many-to-many","slug":"contrastive-learning-for-many-to-many","title":"Contrastive Learning for Many-to-many Multilingual Neural Machine Translation","date":"2021-05-20","arxiv_id":"2105.09501","n_code_links":3,"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":"/paper/deepcad-a-deep-generative-network-for","slug":"deepcad-a-deep-generative-network-for","title":"DeepCAD: A Deep Generative Network for Computer-Aided Design Models","date":"2021-05-20","arxiv_id":"2105.09492","n_code_links":1,"syntology":{"ran":2,"of":7,"n_ran_checked":2,"n_instrument":0,"unverified":5,"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) · 5 unverified","official":{"repos":["ChrisWu1997/DeepCAD"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/enhancing-cross-sectional-currency-strategies","slug":"enhancing-cross-sectional-currency-strategies","title":"Enhancing Cross-Sectional Currency Strategies by Context-Aware Learning to Rank with Self-Attention","date":"2021-05-20","arxiv_id":"2105.10019","n_code_links":1,"syntology":null},{"paper":"/paper/intra-document-cascading-learning-to-select","slug":"intra-document-cascading-learning-to-select","title":"Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking","date":"2021-05-20","arxiv_id":"2105.09816","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-automl-on-structured-tables-with","slug":"multimodal-automl-on-structured-tables-with","title":"Multimodal AutoML on Structured Tables with Text Fields","date":"2021-05-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"see-hear-read-leveraging-multimodality-with","title":"See, Hear, Read: Leveraging Multimodality with Guided Attention for Abstractive Text Summarization","date":"2021-05-20","arxiv_id":"2105.09601","n_code_links":0,"syntology":null},{"paper":null,"slug":"vtnet-visual-transformer-network-for-object-1","title":"VTNet: Visual Transformer Network for Object Goal Navigation","date":"2021-05-20","arxiv_id":"2105.09447","n_code_links":0,"syntology":null},{"paper":"/paper/do-models-learn-the-directionality-of","slug":"do-models-learn-the-directionality-of","title":"Do Models Learn the Directionality of Relations? A New Evaluation: Relation Direction Recognition","date":"2021-05-19","arxiv_id":"2105.09045","n_code_links":1,"syntology":null},{"paper":null,"slug":"explainable-health-risk-predictor-with","title":"Explainable Health Risk Predictor with Transformer-based Medicare Claim Encoder","date":"2021-05-19","arxiv_id":"2105.09428","n_code_links":0,"syntology":null},{"paper":"/paper/explainable-tsetlin-machine-framework-for","slug":"explainable-tsetlin-machine-framework-for","title":"Explainable Tsetlin Machine framework for fake news detection with credibility score assessment","date":"2021-05-19","arxiv_id":"2105.09114","n_code_links":6,"syntology":null},{"paper":"/paper/improving-adverse-drug-event-extraction-with","slug":"improving-adverse-drug-event-extraction-with","title":"Improving Adverse Drug Event Extraction with SpanBERT on Different Text Typologies","date":"2021-05-19","arxiv_id":"2105.08882","n_code_links":1,"syntology":null},{"paper":"/paper/learning-language-specific-sub-network-for","slug":"learning-language-specific-sub-network-for","title":"Learning Language Specific Sub-network for Multilingual Machine Translation","date":"2021-05-19","arxiv_id":"2105.09259","n_code_links":1,"syntology":null},{"paper":"/paper/methods-for-detoxification-of-texts-for-the","slug":"methods-for-detoxification-of-texts-for-the","title":"Methods for Detoxification of Texts for the Russian Language","date":"2021-05-19","arxiv_id":"2105.09052","n_code_links":3,"syntology":null},{"paper":null,"slug":"single-layer-vision-transformers-for-more","title":"Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead","date":"2021-05-19","arxiv_id":"2105.09121","n_code_links":0,"syntology":null},{"paper":"/paper/drill-dynamic-representations-for-imbalanced","slug":"drill-dynamic-representations-for-imbalanced","title":"DRILL: Dynamic Representations for Imbalanced Lifelong Learning","date":"2021-05-18","arxiv_id":"2105.08445","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":["knowledgetechnologyuhh/drill"],"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/effective-attention-sheds-light-on","slug":"effective-attention-sheds-light-on","title":"Effective Attention Sheds Light On Interpretability","date":"2021-05-18","arxiv_id":"2105.08855","n_code_links":1,"syntology":null},{"paper":"/paper/exploiting-adapters-for-cross-lingual-low","slug":"exploiting-adapters-for-cross-lingual-low","title":"Exploiting Adapters for Cross-lingual Low-resource Speech Recognition","date":"2021-05-18","arxiv_id":"2105.11905","n_code_links":2,"syntology":null},{"paper":null,"slug":"exploring-text-to-text-transformers-for","title":"Exploring Text-to-Text Transformers for English to Hinglish Machine Translation with Synthetic Code-Mixing","date":"2021-05-18","arxiv_id":"2105.08807","n_code_links":0,"syntology":null}],"record_sha256":"7b8504b65e779fce33eaeec16b11247e7ddb9ef6eb182198b6d4bc258a493b4a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}