{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/linear-layer/papers/212","list_of":"/method/linear-layer","method":"Linear Layer","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":212,"pages_in_order":255,"rows_per_page":100,"rows":[21101,21200],"of":25421,"counts":{"archive_papers_tagged":25421,"with_a_code_link":11479,"where_syntology_ran_a_sample":3523,"not_listed_spam_title":0,"listed":25421,"listed_where_code_ran":3523,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2976,"every_run_a_failure_of_syntologys_instrument":547,"listed_with_a_run_with_no_instrument_failure":2976,"listed_every_run_a_failure_of_syntologys_instrument":547,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/linear-layer","prev":"/method/linear-layer/papers/211","next":"/method/linear-layer/papers/213","papers":[{"paper":"/paper/incorporating-transformer-and-lstm-to-kalman","slug":"incorporating-transformer-and-lstm-to-kalman","title":"Incorporating Transformer and LSTM to Kalman Filter with EM algorithm for state estimation","date":"2021-05-01","arxiv_id":"2105.00250","n_code_links":1,"syntology":null},{"paper":"/paper/mrcbert-a-machine-reading","slug":"mrcbert-a-machine-reading","title":"MRCBert: A Machine Reading ComprehensionApproach for Unsupervised Summarization","date":"2021-05-01","arxiv_id":"2105.00239","n_code_links":1,"syntology":null},{"paper":"/paper/svt-net-a-super-light-weight-network-for","slug":"svt-net-a-super-light-weight-network-for","title":"SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition","date":"2021-05-01","arxiv_id":"2105.00149","n_code_links":0,"syntology":null},{"paper":"/paper/when-to-fold-em-how-to-answer-unanswerable","slug":"when-to-fold-em-how-to-answer-unanswerable","title":"When to Fold'em: How to answer Unanswerable questions","date":"2021-05-01","arxiv_id":"2105.00328","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-meets-relational-db-contextual","title":"BERT Meets Relational DB: Contextual Representations of Relational Databases","date":"2021-04-30","arxiv_id":"2104.14914","n_code_links":0,"syntology":null},{"paper":null,"slug":"cat-cross-attention-transformer-for-one-shot","title":"CAT: Cross-Attention Transformer for One-Shot Object Detection","date":"2021-04-30","arxiv_id":"2104.14984","n_code_links":0,"syntology":null},{"paper":null,"slug":"chop-chop-bert-visual-question-answering-by","title":"Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads","date":"2021-04-30","arxiv_id":"2104.14741","n_code_links":0,"syntology":null},{"paper":null,"slug":"cosformer-detecting-co-salient-object-with","title":"CoSformer: Detecting Co-Salient Object with Transformers","date":"2021-04-30","arxiv_id":"2104.14729","n_code_links":0,"syntology":null},{"paper":"/paper/ctlr-wic-tsv-target-sense-verification-using","slug":"ctlr-wic-tsv-target-sense-verification-using","title":"CTLR@WiC-TSV: Target Sense Verification using Marked Inputs andPre-trained Models","date":"2021-04-30","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"gtn-ed-event-detection-using-graph","title":"GTN-ED: Event Detection Using Graph Transformer Networks","date":"2021-04-30","arxiv_id":"2104.15104","n_code_links":0,"syntology":null},{"paper":null,"slug":"mitigating-political-bias-in-language-models","title":"Mitigating Political Bias in Language Models Through Reinforced Calibration","date":"2021-04-30","arxiv_id":"2104.14795","n_code_links":0,"syntology":null},{"paper":"/paper/word-sense-disambiguation-with-transformer","slug":"word-sense-disambiguation-with-transformer","title":"Word Sense Disambiguation with Transformer Models","date":"2021-04-30","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/amr-parsing-with-action-pointer-transformer","slug":"amr-parsing-with-action-pointer-transformer","title":"AMR Parsing with Action-Pointer Transformer","date":"2021-04-29","arxiv_id":"2104.14674","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":null}},{"paper":"/paper/emerging-properties-in-self-supervised-vision","slug":"emerging-properties-in-self-supervised-vision","title":"Emerging Properties in Self-Supervised Vision Transformers","date":"2021-04-29","arxiv_id":"2104.14294","n_code_links":32,"syntology":{"ran":14,"of":20,"n_ran_checked":10,"n_instrument":4,"unverified":6,"pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","official":{"repos":["facebookresearch/dino"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":"/paper/entailment-as-few-shot-learner","slug":"entailment-as-few-shot-learner","title":"Entailment as Few-Shot Learner","date":"2021-04-29","arxiv_id":"2104.14690","n_code_links":3,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"gashis-transformer-a-multi-scale-visual","title":"GasHis-Transformer: A Multi-scale Visual Transformer Approach for Gastric Histopathological Image Detection","date":"2021-04-29","arxiv_id":"2104.14528","n_code_links":0,"syntology":null},{"paper":"/paper/handsformer-keypoint-transformer-for","slug":"handsformer-keypoint-transformer-for","title":"Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation","date":"2021-04-29","arxiv_id":"2104.14639","n_code_links":1,"syntology":null},{"paper":"/paper/let-s-play-mono-poly-bert-can-reveal-words","slug":"let-s-play-mono-poly-bert-can-reveal-words","title":"Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses","date":"2021-04-29","arxiv_id":"2104.14694","n_code_links":1,"syntology":null},{"paper":null,"slug":"pyramid-medical-transformer-for-medical-image","title":"Pyramid Medical Transformer for Medical Image Segmentation","date":"2021-04-29","arxiv_id":"2104.14702","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-adaptive-gradient-for-texture-learning","title":"Using Adaptive Gradient for Texture Learning in Single-View 3D Reconstruction","date":"2021-04-29","arxiv_id":"2104.14169","n_code_links":0,"syntology":null},{"paper":"/paper/an-attention-based-deep-learning-approach-for","slug":"an-attention-based-deep-learning-approach-for","title":"An Attention-Based Deep Learning Approach for Sleep Stage Classification With Single-Channel EEG","date":"2021-04-28","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/improving-bert-model-using-contrastive","slug":"improving-bert-model-using-contrastive","title":"Improving BERT Model Using Contrastive Learning for Biomedical Relation Extraction","date":"2021-04-28","arxiv_id":"2104.13913","n_code_links":1,"syntology":null},{"paper":"/paper/inpainting-transformer-for-anomaly-detection","slug":"inpainting-transformer-for-anomaly-detection","title":"Inpainting Transformer for Anomaly Detection","date":"2021-04-28","arxiv_id":"2104.13897","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"medical-transformer-universal-brain-encoder","title":"Medical Transformer: Universal Brain Encoder for 3D MRI Analysis","date":"2021-04-28","arxiv_id":"2104.13633","n_code_links":0,"syntology":null},{"paper":"/paper/melbert-metaphor-detection-via-contextualized","slug":"melbert-metaphor-detection-via-contextualized","title":"MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories","date":"2021-04-28","arxiv_id":"2104.13615","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["jin530/MelBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"multi-task-learning-of-query-intent-and-named","title":"Multi-Task Learning of Query Intent and Named Entities using Transfer Learning","date":"2021-04-28","arxiv_id":"2105.03316","n_code_links":0,"syntology":null},{"paper":null,"slug":"point-cloud-learning-with-transformer","title":"Point Cloud Learning with Transformer","date":"2021-04-28","arxiv_id":"2104.13636","n_code_links":0,"syntology":null},{"paper":"/paper/societal-biases-in-retrieved-contents","slug":"societal-biases-in-retrieved-contents","title":"Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation for BERT Rankers","date":"2021-04-28","arxiv_id":"2104.13640","n_code_links":1,"syntology":null},{"paper":"/paper/twins-revisiting-spatial-attention-design-in","slug":"twins-revisiting-spatial-attention-design-in","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","date":"2021-04-28","arxiv_id":"2104.13840","n_code_links":9,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["Meituan-AutoML/Twins"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dual-transformer-for-point-cloud-analysis","title":"Dual Transformer for Point Cloud Analysis","date":"2021-04-27","arxiv_id":"2104.13044","n_code_links":0,"syntology":null},{"paper":null,"slug":"extractive-and-abstractive-explanations-for","title":"Extractive and Abstractive Explanations for Fact-Checking and Evaluation of News","date":"2021-04-27","arxiv_id":"2104.12918","n_code_links":0,"syntology":null},{"paper":"/paper/generating-lead-sheets-with-affect-a-novel","slug":"generating-lead-sheets-with-affect-a-novel","title":"Generating Lead Sheets with Affect: A Novel Conditional seq2seq Framework","date":"2021-04-27","arxiv_id":"2104.13056","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-class-text-classification-using-bert","title":"Multi-class Text Classification using BERT-based Active Learning","date":"2021-04-27","arxiv_id":"2104.14289","n_code_links":0,"syntology":null},{"paper":null,"slug":"semi-supervised-interactive-intent-labeling","title":"Semi-supervised Interactive Intent Labeling","date":"2021-04-27","arxiv_id":"2104.13406","n_code_links":0,"syntology":null},{"paper":null,"slug":"uot-uwf-partai-at-semeval-2021-task-5-self","title":"UoT-UWF-PartAI at SemEval-2021 Task 5: Self Attention Based Bi-GRU with Multi-Embedding Representation for Toxicity Highlighter","date":"2021-04-27","arxiv_id":"2104.13164","n_code_links":0,"syntology":null},{"paper":null,"slug":"accounting-for-agreement-phenomena-in","title":"Accounting for Agreement Phenomena in Sentence Comprehension with Transformer Language Models: Effects of Similarity-based Interference on Surprisal and Attention","date":"2021-04-26","arxiv_id":"2104.12874","n_code_links":0,"syntology":null},{"paper":null,"slug":"diverse-image-inpainting-with-bidirectional","title":"Diverse Image Inpainting with Bidirectional and Autoregressive Transformers","date":"2021-04-26","arxiv_id":"2104.12335","n_code_links":0,"syntology":null},{"paper":"/paper/easy-and-efficient-transformer-scalable","slug":"easy-and-efficient-transformer-scalable","title":"Easy and Efficient Transformer : Scalable Inference Solution For large NLP model","date":"2021-04-26","arxiv_id":"2104.12470","n_code_links":1,"syntology":null},{"paper":"/paper/focused-attention-improves-document-grounded","slug":"focused-attention-improves-document-grounded","title":"Focused Attention Improves Document-Grounded Generation","date":"2021-04-26","arxiv_id":"2104.12714","n_code_links":1,"syntology":null},{"paper":null,"slug":"head-synchronous-decoding-for-transformer","title":"Head-synchronous Decoding for Transformer-based Streaming ASR","date":"2021-04-26","arxiv_id":"2104.12631","n_code_links":0,"syntology":null},{"paper":"/paper/improve-vision-transformers-training-by","slug":"improve-vision-transformers-training-by","title":"Vision Transformers with Patch Diversification","date":"2021-04-26","arxiv_id":"2104.12753","n_code_links":1,"syntology":null},{"paper":"/paper/mdetr-modulated-detection-for-end-to-end","slug":"mdetr-modulated-detection-for-end-to-end","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","date":"2021-04-26","arxiv_id":"2104.12763","n_code_links":5,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ashkamath/mdetr"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/pangu-a-large-scale-autoregressive-pretrained","slug":"pangu-a-large-scale-autoregressive-pretrained","title":"PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","date":"2021-04-26","arxiv_id":"2104.12369","n_code_links":5,"syntology":null},{"paper":"/paper/phrase-break-prediction-with-bidirectional","slug":"phrase-break-prediction-with-bidirectional","title":"Phrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesis","date":"2021-04-26","arxiv_id":"2104.12395","n_code_links":1,"syntology":null},{"paper":"/paper/rich-semantics-improve-few-shot-learning","slug":"rich-semantics-improve-few-shot-learning","title":"Rich Semantics Improve Few-shot Learning","date":"2021-04-26","arxiv_id":"2104.12709","n_code_links":0,"syntology":null},{"paper":"/paper/visformer-the-vision-friendly-transformer","slug":"visformer-the-vision-friendly-transformer","title":"Visformer: The Vision-friendly Transformer","date":"2021-04-26","arxiv_id":"2104.12533","n_code_links":5,"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":["danczs/Visformer"],"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/potential-idiomatic-expression-pie-english","slug":"potential-idiomatic-expression-pie-english","title":"Potential Idiomatic Expression (PIE)-English: Corpus for Classes of Idioms","date":"2021-04-25","arxiv_id":"2105.03280","n_code_links":2,"syntology":null},{"paper":"/paper/transformer-meets-dcfam-a-novel-semantic","slug":"transformer-meets-dcfam-a-novel-semantic","title":"A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images","date":"2021-04-25","arxiv_id":"2104.12137","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["WangLibo1995/GeoSeg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/visual-saliency-transformer","slug":"visual-saliency-transformer","title":"Visual Saliency Transformer","date":"2021-04-25","arxiv_id":"2104.12099","n_code_links":2,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":11,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":null}},{"paper":"/paper/baller2vec-a-look-ahead-multi-entity","slug":"baller2vec-a-look-ahead-multi-entity","title":"baller2vec++: A Look-Ahead Multi-Entity Transformer For Modeling Coordinated Agents","date":"2021-04-24","arxiv_id":"2104.11980","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["airalcorn2/baller2vecplusplus"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"extract-then-distill-efficient-and-effective","title":"Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation","date":"2021-04-24","arxiv_id":"2104.11928","n_code_links":0,"syntology":null},{"paper":"/paper/learning-passage-impacts-for-inverted-indexes","slug":"learning-passage-impacts-for-inverted-indexes","title":"Learning Passage Impacts for Inverted Indexes","date":"2021-04-24","arxiv_id":"2104.12016","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["DI4IR/SIGIR2021"],"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":"analysing-cyberbullying-using-natural","title":"Analysing Cyberbullying using Natural Language Processing by Understanding Jargon in Social Media","date":"2021-04-23","arxiv_id":"2107.08902","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-coqac-bert-based-conversational-question","title":"BERT-CoQAC: BERT-based Conversational Question Answering in Context","date":"2021-04-23","arxiv_id":"2104.11394","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-machine-learning-and","title":"Comparative Analysis of Machine Learning and Deep Learning Algorithms for Detection of Online Hate Speech","date":"2021-04-23","arxiv_id":"2108.01063","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-cluster-faces-via-transformer","title":"Learning to Cluster Faces via Transformer","date":"2021-04-23","arxiv_id":"2104.11502","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-fusion-with-bert-and-attention","slug":"multimodal-fusion-with-bert-and-attention","title":"Multimodal Fusion with BERT and Attention Mechanism for Fake News Detection","date":"2021-04-23","arxiv_id":"2104.11476","n_code_links":1,"syntology":null},{"paper":"/paper/optimizing-small-berts-trained-for-german-ner","slug":"optimizing-small-berts-trained-for-german-ner","title":"Optimizing small BERTs trained for German NER","date":"2021-04-23","arxiv_id":"2104.11559","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-trustworthy-deception-detection","title":"Towards Trustworthy Deception Detection: Benchmarking Model Robustness across Domains, Modalities, and Languages","date":"2021-04-23","arxiv_id":"2104.11761","n_code_links":0,"syntology":null},{"paper":"/paper/vidtr-video-transformer-without-convolutions","slug":"vidtr-video-transformer-without-convolutions","title":"VidTr: Video Transformer Without Convolutions","date":"2021-04-23","arxiv_id":"2104.11746","n_code_links":0,"syntology":null},{"paper":"/paper/on-geodesic-distances-and-contextual","slug":"on-geodesic-distances-and-contextual","title":"On Geodesic Distances and Contextual Embedding Compression for Text Classification","date":"2021-04-22","arxiv_id":"2104.11295","n_code_links":1,"syntology":null},{"paper":"/paper/so-vit-mind-visual-tokens-for-vision","slug":"so-vit-mind-visual-tokens-for-vision","title":"So-ViT: Mind Visual Tokens for Vision Transformer","date":"2021-04-22","arxiv_id":"2104.10935","n_code_links":1,"syntology":null},{"paper":"/paper/token-labeling-training-a-85-5-top-1-accuracy","slug":"token-labeling-training-a-85-5-top-1-accuracy","title":"All Tokens Matter: Token Labeling for Training Better Vision Transformers","date":"2021-04-22","arxiv_id":"2104.10858","n_code_links":7,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zihangJiang/TokenLabeling"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/vatt-transformers-for-multimodal-self","slug":"vatt-transformers-for-multimodal-self","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","date":"2021-04-22","arxiv_id":"2104.11178","n_code_links":5,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":8,"phrase":"5 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"3kg-contrastive-learning-of-12-lead","title":"3KG: Contrastive Learning of 12-Lead Electrocardiograms using Physiologically-Inspired Augmentations","date":"2021-04-21","arxiv_id":"2106.04452","n_code_links":0,"syntology":null},{"paper":null,"slug":"carbon-emissions-and-large-neural-network","title":"Carbon Emissions and Large Neural Network Training","date":"2021-04-21","arxiv_id":"2104.10350","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-transform-and-metric-learning-networks","title":"Deep Transform and Metric Learning Networks","date":"2021-04-21","arxiv_id":"2104.10329","n_code_links":0,"syntology":null},{"paper":null,"slug":"discriminative-self-training-for-punctuation","title":"Discriminative Self-training for Punctuation Prediction","date":"2021-04-21","arxiv_id":"2104.10339","n_code_links":0,"syntology":null},{"paper":null,"slug":"disfluency-detection-with-unlabeled-data-and","title":"Disfluency Detection with Unlabeled Data and Small BERT Models","date":"2021-04-21","arxiv_id":"2104.10769","n_code_links":0,"syntology":null},{"paper":null,"slug":"label-synchronous-speech-to-text-alignment","title":"Label-Synchronous Speech-to-Text Alignment for ASR Using Forward and Backward Transformers","date":"2021-04-21","arxiv_id":"2104.10328","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-s-the-context-long-context-nlm","title":"Adapting Long Context NLM for ASR Rescoring in Conversational Agents","date":"2021-04-21","arxiv_id":"2104.11070","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-covid-19-tweets-with-transformer","title":"Analyzing COVID-19 Tweets with Transformer-based Language Models","date":"2021-04-20","arxiv_id":"2104.10259","n_code_links":0,"syntology":null},{"paper":"/paper/b-prop-bootstrapped-pre-training-with","slug":"b-prop-bootstrapped-pre-training-with","title":"B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval","date":"2021-04-20","arxiv_id":"2104.09791","n_code_links":1,"syntology":{"ran":10,"of":16,"n_ran_checked":7,"n_instrument":3,"unverified":6,"pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","official":{"repos":["Albert-Ma/PROP"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cate-meets-ml-the-conditional-average","title":"CATE meets ML -- The Conditional Average Treatment Effect and Machine Learning","date":"2021-04-20","arxiv_id":"2104.09935","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-pre-training-objectives-for","title":"Efficient pre-training objectives for Transformers","date":"2021-04-20","arxiv_id":"2104.09694","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-shifts-in-attitudes-towards-covid","slug":"measuring-shifts-in-attitudes-towards-covid","title":"Measuring Shifts in Attitudes Towards COVID-19 Measures in Belgium Using Multilingual BERT","date":"2021-04-20","arxiv_id":"2104.09947","n_code_links":1,"syntology":null},{"paper":"/paper/modeling-event-plausibility-with-consistent","slug":"modeling-event-plausibility-with-consistent","title":"Modeling Event Plausibility with Consistent Conceptual Abstraction","date":"2021-04-20","arxiv_id":"2104.10247","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["ianporada/modeling_event_plausibility"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/subsentence-extraction-from-text-using","slug":"subsentence-extraction-from-text-using","title":"Subsentence Extraction from Text Using Coverage-Based Deep Learning Language Models","date":"2021-04-20","arxiv_id":"2104.09777","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-transforms-salient-object","slug":"transformer-transforms-salient-object","title":"Generative Transformer for Accurate and Reliable Salient Object Detection","date":"2021-04-20","arxiv_id":"2104.10127","n_code_links":2,"syntology":null},{"paper":"/paper/uit-ise-nlp-at-semeval-2021-task-5-toxic","slug":"uit-ise-nlp-at-semeval-2021-task-5-toxic","title":"UIT-ISE-NLP at SemEval-2021 Task 5: Toxic Spans Detection with BiLSTM-CRF and ToxicBERT Comment Classification","date":"2021-04-20","arxiv_id":"2104.10100","n_code_links":1,"syntology":null},{"paper":null,"slug":"wassa-iitk-at-wassa-2021-multi-task-learning","title":"WASSA@IITK at WASSA 2021: Multi-task Learning and Transformer Finetuning for Emotion Classification and Empathy Prediction","date":"2021-04-20","arxiv_id":"2104.09827","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-time-frequency-transformer-and-its","title":"A novel time-frequency Transformer based on self-attention mechanism and its application in fault diagnosis of rolling bearings","date":"2021-04-19","arxiv_id":"2104.09079","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-long-context-end-to-end-speech","title":"Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers","date":"2021-04-19","arxiv_id":"2104.09426","n_code_links":0,"syntology":null},{"paper":"/paper/biggreen-at-semeval-2021-task-1-lexical","slug":"biggreen-at-semeval-2021-task-1-lexical","title":"BigGreen at SemEval-2021 Task 1: Lexical Complexity Prediction with Assembly Models","date":"2021-04-19","arxiv_id":"2104.09040","n_code_links":1,"syntology":null},{"paper":"/paper/bm-nas-bilevel-multimodal-neural-architecture","slug":"bm-nas-bilevel-multimodal-neural-architecture","title":"BM-NAS: Bilevel Multimodal Neural Architecture Search","date":"2021-04-19","arxiv_id":"2104.09379","n_code_links":1,"syntology":null},{"paper":null,"slug":"code-structure-guided-transformer-for-source","title":"Code Structure Guided Transformer for Source Code Summarization","date":"2021-04-19","arxiv_id":"2104.09340","n_code_links":0,"syntology":null},{"paper":"/paper/electramed-a-new-pre-trained-language","slug":"electramed-a-new-pre-trained-language","title":"ELECTRAMed: a new pre-trained language representation model for biomedical NLP","date":"2021-04-19","arxiv_id":"2104.09585","n_code_links":2,"syntology":null},{"paper":"/paper/extracting-temporal-event-relation-with","slug":"extracting-temporal-event-relation-with","title":"Extracting Temporal Event Relation with Syntax-guided Graph Transformer","date":"2021-04-19","arxiv_id":"2104.09570","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-transformer-kernel-ranking-model","title":"Improving Transformer-Kernel Ranking Model Using Conformer and Query Term Independence","date":"2021-04-19","arxiv_id":"2104.09393","n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-newsworthiness-for-lead-generation","title":"Modeling \"Newsworthiness\" for Lead-Generation Across Corpora","date":"2021-04-19","arxiv_id":"2104.09653","n_code_links":0,"syntology":null},{"paper":"/paper/multi-modal-fusion-transformer-for-end-to-end","slug":"multi-modal-fusion-transformer-for-end-to-end","title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","date":"2021-04-19","arxiv_id":"2104.09224","n_code_links":2,"syntology":{"ran":9,"of":15,"n_ran_checked":8,"n_instrument":1,"unverified":6,"pointer_only":0,"phrase":"9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["autonomousvision/transfuser"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"neural-language-models-with-distant","title":"Neural Language Models with Distant Supervision to Identify Major Depressive Disorder from Clinical Notes","date":"2021-04-19","arxiv_id":"2104.09644","n_code_links":0,"syntology":null},{"paper":"/paper/octis-comparing-and-optimizing-topic-models","slug":"octis-comparing-and-optimizing-topic-models","title":"OCTIS: Comparing and Optimizing Topic models is Simple!","date":"2021-04-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/operationalizing-a-national-digital-library","slug":"operationalizing-a-national-digital-library","title":"Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model","date":"2021-04-19","arxiv_id":"2104.09617","n_code_links":2,"syntology":null},{"paper":"/paper/probing-for-bridging-inference-in-transformer","slug":"probing-for-bridging-inference-in-transformer","title":"Probing for Bridging Inference in Transformer Language Models","date":"2021-04-19","arxiv_id":"2104.09400","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentiment-classification-in-swahili-language","title":"Sentiment Classification in Swahili Language Using Multilingual BERT","date":"2021-04-19","arxiv_id":"2104.09006","n_code_links":0,"syntology":null},{"paper":"/paper/teamuncc-lt-edi-eacl2021-hope-speech","slug":"teamuncc-lt-edi-eacl2021-hope-speech","title":"TeamUNCC@LT-EDI-EACL2021: Hope Speech Detection using Transfer Learning with Transformers","date":"2021-04-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/transcrowd-weakly-supervised-crowd-counting","slug":"transcrowd-weakly-supervised-crowd-counting","title":"TransCrowd: weakly-supervised crowd counting with transformers","date":"2021-04-19","arxiv_id":"2104.09116","n_code_links":1,"syntology":null},{"paper":"/paper/a-token-level-reference-free-hallucination","slug":"a-token-level-reference-free-hallucination","title":"A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation","date":"2021-04-18","arxiv_id":"2104.08704","n_code_links":2,"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":["microsoft/HaDes"],"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/attention-based-clinical-note-summarization","slug":"attention-based-clinical-note-summarization","title":"Attention-based Clinical Note Summarization","date":"2021-04-18","arxiv_id":"2104.08942","n_code_links":1,"syntology":null}],"record_sha256":"67a6d0d77939bdf89a35f14fd64ad2418e2ce52220def1bfed9884cadadea727","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}