{"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/bpe/papers/168","list_of":"/method/bpe","method":"BPE","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":168,"pages_in_order":190,"rows_per_page":100,"rows":[16701,16800],"of":18975,"counts":{"archive_papers_tagged":18975,"with_a_code_link":8675,"where_syntology_ran_a_sample":2895,"not_listed_spam_title":0,"listed":18975,"listed_where_code_ran":2895,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2443,"every_run_a_failure_of_syntologys_instrument":452,"listed_with_a_run_with_no_instrument_failure":2443,"listed_every_run_a_failure_of_syntologys_instrument":452,"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/bpe","prev":"/method/bpe/papers/167","next":"/method/bpe/papers/169","papers":[{"paper":null,"slug":"ensemble-making-few-shot-learning-stronger","title":"Ensemble Making Few-Shot Learning Stronger","date":"2021-05-12","arxiv_id":"2105.11904","n_code_links":0,"syntology":null},{"paper":"/paper/news-headline-grouping-as-a-challenging-nlu-1","slug":"news-headline-grouping-as-a-challenging-nlu-1","title":"News Headline Grouping as a Challenging NLU Task","date":"2021-05-12","arxiv_id":"2105.05391","n_code_links":1,"syntology":null},{"paper":"/paper/segmenter-transformer-for-semantic","slug":"segmenter-transformer-for-semantic","title":"Segmenter: Transformer for Semantic Segmentation","date":"2021-05-12","arxiv_id":"2105.05633","n_code_links":8,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["rstrudel/segmenter"],"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/swin-unet-unet-like-pure-transformer-for","slug":"swin-unet-unet-like-pure-transformer-for","title":"Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation","date":"2021-05-12","arxiv_id":"2105.05537","n_code_links":7,"syntology":{"ran":17,"of":18,"n_ran_checked":14,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["HuCaoFighting/Swin-Unet"],"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/waste-detection-in-pomerania-non-profit","slug":"waste-detection-in-pomerania-non-profit","title":"Waste detection in Pomerania: non-profit project for detecting waste in environment","date":"2021-05-12","arxiv_id":"2105.06808","n_code_links":1,"syntology":null},{"paper":"/paper/bert-is-to-nlp-what-alexnet-is-to-cv-can-pre","slug":"bert-is-to-nlp-what-alexnet-is-to-cv-can-pre","title":"BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?","date":"2021-05-11","arxiv_id":"2105.04949","n_code_links":1,"syntology":null},{"paper":"/paper/el-attention-memory-efficient-lossless","slug":"el-attention-memory-efficient-lossless","title":"EL-Attention: Memory Efficient Lossless Attention for Generation","date":"2021-05-11","arxiv_id":"2105.04779","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":4,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/fastseq"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"learning-robust-latent-representations-for","title":"Learning Robust Latent Representations for Controllable Speech Synthesis","date":"2021-05-10","arxiv_id":"2105.04458","n_code_links":0,"syntology":null},{"paper":"/paper/matching-visual-features-to-hierarchical","slug":"matching-visual-features-to-hierarchical","title":"Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning","date":"2021-05-10","arxiv_id":"2105.04143","n_code_links":1,"syntology":null},{"paper":"/paper/musemorphose-full-song-and-fine-grained-music","slug":"musemorphose-full-song-and-fine-grained-music","title":"MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAE","date":"2021-05-10","arxiv_id":"2105.04090","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["YatingMusic/MuseMorphose"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"recent-advances-in-deep-learning-based","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","date":"2021-05-10","arxiv_id":"2105.04387","n_code_links":0,"syntology":null},{"paper":null,"slug":"relationtrack-relation-aware-multiple-object","title":"RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation","date":"2021-05-10","arxiv_id":"2105.04322","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-guided-curriculum-learning-for-neural","title":"Self-Guided Curriculum Learning for Neural Machine Translation","date":"2021-05-10","arxiv_id":"2105.04475","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-learning-with-swin","slug":"self-supervised-learning-with-swin","title":"Self-Supervised Learning with Swin Transformers","date":"2021-05-10","arxiv_id":"2105.04553","n_code_links":6,"syntology":null},{"paper":"/paper/fnet-mixing-tokens-with-fourier-transforms","slug":"fnet-mixing-tokens-with-fourier-transforms","title":"FNet: Mixing Tokens with Fourier Transforms","date":"2021-05-09","arxiv_id":"2105.03824","n_code_links":12,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"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) · 0 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":"/paper/trtr-visual-tracking-with-transformer","slug":"trtr-visual-tracking-with-transformer","title":"TrTr: Visual Tracking with Transformer","date":"2021-05-09","arxiv_id":"2105.03817","n_code_links":1,"syntology":null},{"paper":null,"slug":"which-transformer-architecture-fits-my-data-a","title":"Which transformer architecture fits my data? A vocabulary bottleneck in self-attention","date":"2021-05-09","arxiv_id":"2105.03928","n_code_links":0,"syntology":null},{"paper":"/paper/e-vil-a-dataset-and-benchmark-for-natural","slug":"e-vil-a-dataset-and-benchmark-for-natural","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","date":"2021-05-08","arxiv_id":"2105.03761","n_code_links":2,"syntology":{"ran":7,"of":15,"n_ran_checked":6,"n_instrument":1,"unverified":8,"pointer_only":15,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","official":{"repos":["maximek3/e-ViL"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/falling-through-the-gaps-neural-architectures","slug":"falling-through-the-gaps-neural-architectures","title":"Falling Through the Gaps: Neural Architectures as Models of Morphological Rule Learning","date":"2021-05-08","arxiv_id":"2105.03710","n_code_links":1,"syntology":null},{"paper":"/paper/are-pre-trained-convolutions-better-than-pre","slug":"are-pre-trained-convolutions-better-than-pre","title":"Are Pre-trained Convolutions Better than Pre-trained Transformers?","date":"2021-05-07","arxiv_id":"2105.03322","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-weight-factorization-for","title":"Efficient Weight factorization for Multilingual Speech Recognition","date":"2021-05-07","arxiv_id":"2105.03010","n_code_links":0,"syntology":null},{"paper":"/paper/motr-end-to-end-multiple-object-tracking-with","slug":"motr-end-to-end-multiple-object-tracking-with","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","date":"2021-05-07","arxiv_id":"2105.03247","n_code_links":2,"syntology":null},{"paper":"/paper/on-the-fly-controlled-text-generation-with","slug":"on-the-fly-controlled-text-generation-with","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","date":"2021-05-07","arxiv_id":"2105.03023","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":3,"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) · 2 unverified","official":{"repos":["alisawuffles/DExperts"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/speechmoe-scaling-to-large-acoustic-models","slug":"speechmoe-scaling-to-large-acoustic-models","title":"SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts","date":"2021-05-07","arxiv_id":"2105.03036","n_code_links":1,"syntology":null},{"paper":"/paper/adapting-monolingual-models-data-can-be","slug":"adapting-monolingual-models-data-can-be","title":"Adapting Monolingual Models: Data can be Scarce when Language Similarity is High","date":"2021-05-06","arxiv_id":"2105.02855","n_code_links":1,"syntology":null},{"paper":null,"slug":"aligning-subtitles-in-sign-language-videos","title":"Aligning Subtitles in Sign Language Videos","date":"2021-05-06","arxiv_id":"2105.02877","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-logistical-difficulties-and-findings","slug":"on-the-logistical-difficulties-and-findings","title":"On the logistical difficulties and findings of Jopara Sentiment Analysis","date":"2021-05-06","arxiv_id":"2105.02947","n_code_links":1,"syntology":null},{"paper":"/paper/attention-for-image-registration-air-an","slug":"attention-for-image-registration-air-an","title":"Attention for Image Registration (AiR): an unsupervised Transformer approach","date":"2021-05-05","arxiv_id":"2105.02282","n_code_links":1,"syntology":null},{"paper":null,"slug":"sequential-encryption-of-sparse-neural","title":"Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression","date":"2021-05-05","arxiv_id":"2105.01869","n_code_links":0,"syntology":null},{"paper":null,"slug":"visual-composite-set-detection-using-part-and","title":"Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries","date":"2021-05-05","arxiv_id":"2105.02170","n_code_links":0,"syntology":null},{"paper":"/paper/mlp-mixer-an-all-mlp-architecture-for-vision","slug":"mlp-mixer-an-all-mlp-architecture-for-vision","title":"MLP-Mixer: An all-MLP Architecture for Vision","date":"2021-05-04","arxiv_id":"2105.01601","n_code_links":49,"syntology":{"ran":114,"of":134,"n_ran_checked":105,"n_instrument":9,"unverified":20,"pointer_only":40,"phrase":"114 ran (of which 77 constructed an object rather than computing a result; 105 with no instrument failure: 2 honoured, 0 violated, 103 with no contract checked; 9 where Syntology's instrument failed) · 20 unverified","official":{"repos":["google-research/vision_transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","unlocated"]}}},{"paper":null,"slug":"moving-towards-centers-re-ranking-with","title":"Moving Towards Centers: Re-ranking with Attention and Memory for Re-identification","date":"2021-05-04","arxiv_id":"2105.01447","n_code_links":0,"syntology":null},{"paper":"/paper/retrieving-complex-tables-with-multi-granular","slug":"retrieving-complex-tables-with-multi-granular","title":"Retrieving Complex Tables with Multi-Granular Graph Representation Learning","date":"2021-05-04","arxiv_id":"2105.01736","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":["FeiWang96/GTR"],"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/istr-end-to-end-instance-segmentation-with","slug":"istr-end-to-end-instance-segmentation-with","title":"ISTR: End-to-End Instance Segmentation with Transformers","date":"2021-05-03","arxiv_id":"2105.00637","n_code_links":1,"syntology":null},{"paper":null,"slug":"one-model-to-rule-them-all-towards-zero-shot","title":"One Model to Rule them All: Towards Zero-Shot Learning for Databases","date":"2021-05-03","arxiv_id":"2105.00642","n_code_links":0,"syntology":null},{"paper":"/paper/unreasonable-effectiveness-of-rule-based","slug":"unreasonable-effectiveness-of-rule-based","title":"Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks","date":"2021-05-03","arxiv_id":"2105.01192","n_code_links":0,"syntology":null},{"paper":"/paper/anatomy-guided-parallel-bottleneck","slug":"anatomy-guided-parallel-bottleneck","title":"AGMB-Transformer: Anatomy-Guided Multi-Branch Transformer Network for Automated Evaluation of Root Canal Therapy","date":"2021-05-02","arxiv_id":"2105.00381","n_code_links":1,"syntology":null},{"paper":"/paper/audio-transformers-transformer-architectures","slug":"audio-transformers-transformer-architectures","title":"Audio Transformers","date":"2021-05-01","arxiv_id":"2105.00335","n_code_links":0,"syntology":null},{"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/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":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/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":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/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":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":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":"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":"/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/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/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/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":"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/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/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":"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":"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":"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":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/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":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":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/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":"/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":"/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},{"paper":null,"slug":"demystifying-the-better-performance-of","title":"A Simple and Effective Positional Encoding for Transformers","date":"2021-04-18","arxiv_id":"2104.08698","n_code_links":0,"syntology":null},{"paper":"/paper/fantastically-ordered-prompts-and-where-to","slug":"fantastically-ordered-prompts-and-where-to","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","date":"2021-04-18","arxiv_id":"2104.08786","n_code_links":2,"syntology":{"ran":3,"of":10,"n_ran_checked":0,"n_instrument":3,"unverified":7,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","official":null}},{"paper":"/paper/fednlp-a-research-platform-for-federated","slug":"fednlp-a-research-platform-for-federated","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","date":"2021-04-18","arxiv_id":"2104.08815","n_code_links":1,"syntology":null},{"paper":"/paper/gpt3mix-leveraging-large-scale-language","slug":"gpt3mix-leveraging-large-scale-language","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","date":"2021-04-18","arxiv_id":"2104.08826","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["naver-ai/hypermix"],"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/mt6-multilingual-pretrained-text-to-text","slug":"mt6-multilingual-pretrained-text-to-text","title":"MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs","date":"2021-04-18","arxiv_id":"2104.08692","n_code_links":2,"syntology":null},{"paper":"/paper/natural-instructions-benchmarking","slug":"natural-instructions-benchmarking","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","date":"2021-04-18","arxiv_id":"2104.08773","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":1,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/natural-instructions","allenai/natural-instructions-v1"],"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","unlocated"]}}},{"paper":"/paper/on-the-strengths-of-cross-attention-in","slug":"on-the-strengths-of-cross-attention-in","title":"Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation","date":"2021-04-18","arxiv_id":"2104.08771","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":7,"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) · 3 unverified","official":{"repos":["mgheini/xattn-transfer-for-mt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-power-of-scale-for-parameter-efficient","slug":"the-power-of-scale-for-parameter-efficient","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","date":"2021-04-18","arxiv_id":"2104.08691","n_code_links":12,"syntology":{"ran":13,"of":15,"n_ran_checked":13,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["google-research/prompt-tuning"],"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/when-does-pretraining-help-assessing-self","slug":"when-does-pretraining-help-assessing-self","title":"When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset","date":"2021-04-18","arxiv_id":"2104.08671","n_code_links":2,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["reglab/casehold"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/decrypting-cryptic-crosswords-semantically","slug":"decrypting-cryptic-crosswords-semantically","title":"Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP","date":"2021-04-17","arxiv_id":"2104.08620","n_code_links":2,"syntology":null}],"record_sha256":"baa21f6dba660e20a1a82fe12e63915904b2d88fdc0b8c4a84834626e042a05e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}