{"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/163","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":163,"pages_in_order":190,"rows_per_page":100,"rows":[16201,16300],"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/162","next":"/method/bpe/papers/164","papers":[{"paper":null,"slug":"mvsr-nat-multi-view-subset-regularization-for","title":"MvSR-NAT: Multi-view Subset Regularization for Non-Autoregressive Machine Translation","date":"2021-08-19","arxiv_id":"2108.08447","n_code_links":0,"syntology":null},{"paper":"/paper/sentence-t5-scalable-sentence-encoders-from","slug":"sentence-t5-scalable-sentence-encoders-from","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","date":"2021-08-19","arxiv_id":"2108.08877","n_code_links":2,"syntology":null},{"paper":"/paper/video-relation-detection-via-tracklet-based","slug":"video-relation-detection-via-tracklet-based","title":"Video Relation Detection via Tracklet based Visual Transformer","date":"2021-08-19","arxiv_id":"2108.08669","n_code_links":1,"syntology":null},{"paper":"/paper/table-caption-generation-in-scholarly","slug":"table-caption-generation-in-scholarly","title":"Table Caption Generation in Scholarly Documents Leveraging Pre-trained Language Models","date":"2021-08-18","arxiv_id":"2108.08111","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-predicting-the-future-applying","slug":"transformers-predicting-the-future-applying","title":"Transformers predicting the future. Applying attention in next-frame and time series forecasting","date":"2021-08-18","arxiv_id":"2108.08224","n_code_links":1,"syntology":null},{"paper":null,"slug":"two-streams-and-two-resolution-spectrograms","title":"A Multi-level Acoustic Feature Extraction Framework for Transformer Based End-to-End Speech Recognition","date":"2021-08-18","arxiv_id":"2108.07980","n_code_links":0,"syntology":null},{"paper":null,"slug":"enct5-fine-tuning-t5-encoder-for","title":"EncT5: Fine-tuning T5 Encoder for Discriminative Tasks","date":"2021-08-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learning-c-to-x86-translation-an-experiment","slug":"learning-c-to-x86-translation-an-experiment","title":"Learning C to x86 Translation: An Experiment in Neural Compilation","date":"2021-08-17","arxiv_id":"2108.07639","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":["jordiae/neural-compilers"],"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/light-field-image-super-resolution-with","slug":"light-field-image-super-resolution-with","title":"Light Field Image Super-Resolution with Transformers","date":"2021-08-17","arxiv_id":"2108.07597","n_code_links":1,"syntology":null},{"paper":null,"slug":"moi-mixer-improving-mlp-mixer-with-multi","title":"MOI-Mixer: Improving MLP-Mixer with Multi Order Interactions in Sequential Recommendation","date":"2021-08-17","arxiv_id":"2108.07505","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantics-aware-attention-improves-neural-1","title":"Semantics-aware Attention Improves Neural Machine Translation","date":"2021-08-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/semi-parametric-bayesian-additive-regression","slug":"semi-parametric-bayesian-additive-regression","title":"Accounting for shared covariates in semi-parametric Bayesian additive regression trees","date":"2021-08-17","arxiv_id":"2108.07636","n_code_links":2,"syntology":null},{"paper":null,"slug":"an-effective-non-autoregressive-model-for","title":"An Effective Non-Autoregressive Model for Spoken Language Understanding","date":"2021-08-16","arxiv_id":"2108.07005","n_code_links":0,"syntology":null},{"paper":"/paper/misleading-the-covid-19-vaccination-discourse","slug":"misleading-the-covid-19-vaccination-discourse","title":"Misleading the Covid-19 vaccination discourse on Twitter: An exploratory study of infodemic around the pandemic","date":"2021-08-16","arxiv_id":"2108.10735","n_code_links":1,"syntology":null},{"paper":"/paper/no-reference-image-quality-assessment-via-1","slug":"no-reference-image-quality-assessment-via-1","title":"No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency","date":"2021-08-16","arxiv_id":"2108.06858","n_code_links":1,"syntology":null},{"paper":"/paper/scene-designer-a-unified-model-for-scene","slug":"scene-designer-a-unified-model-for-scene","title":"Scene Designer: a Unified Model for Scene Search and Synthesis from Sketch","date":"2021-08-16","arxiv_id":"2108.07353","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-generalization-ability-of","title":"Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning","date":"2021-08-15","arxiv_id":"2108.06743","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-temporal-coherence-for-more-general","slug":"exploring-temporal-coherence-for-more-general","title":"Exploring Temporal Coherence for More General Video Face Forgery Detection","date":"2021-08-15","arxiv_id":"2108.06693","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 4 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) · 0 unverified","official":null}},{"paper":null,"slug":"sapphire-approaches-for-enhanced-concept-to","title":"SAPPHIRE: Approaches for Enhanced Concept-to-Text Generation","date":"2021-08-15","arxiv_id":"2108.06643","n_code_links":0,"syntology":null},{"paper":"/paper/sotr-segmenting-objects-with-transformers","slug":"sotr-segmenting-objects-with-transformers","title":"SOTR: Segmenting Objects with Transformers","date":"2021-08-15","arxiv_id":"2108.06747","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":6,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["easton-cau/SOTR"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/heterogeneous-temporal-graph-transformer-an","slug":"heterogeneous-temporal-graph-transformer-an","title":"heterogeneous temporal graph transformer: an intelligent system for evolving android malware detection","date":"2021-08-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/conditional-detr-for-fast-training","slug":"conditional-detr-for-fast-training","title":"Conditional DETR for Fast Training Convergence","date":"2021-08-13","arxiv_id":"2108.06152","n_code_links":4,"syntology":{"ran":6,"of":9,"n_ran_checked":4,"n_instrument":2,"unverified":3,"pointer_only":4,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["atten4vis/conditionaldetr"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/curriculum-learning-a-regularization-method","slug":"curriculum-learning-a-regularization-method","title":"The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models","date":"2021-08-13","arxiv_id":"2108.06084","n_code_links":1,"syntology":null},{"paper":"/paper/point-voxel-transformer-an-efficient-approach","slug":"point-voxel-transformer-an-efficient-approach","title":"PVT: Point-Voxel Transformer for Point Cloud Learning","date":"2021-08-13","arxiv_id":"2108.06076","n_code_links":2,"syntology":null},{"paper":"/paper/ammus-a-survey-of-transformer-based","slug":"ammus-a-survey-of-transformer-based","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","date":"2021-08-12","arxiv_id":"2108.05542","n_code_links":1,"syntology":null},{"paper":"/paper/how-optimal-is-greedy-decoding-for-extractive","slug":"how-optimal-is-greedy-decoding-for-extractive","title":"How Optimal is Greedy Decoding for Extractive Question Answering?","date":"2021-08-12","arxiv_id":"2108.05857","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ocastel/exact-extract"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/mobile-former-bridging-mobilenet-and","slug":"mobile-former-bridging-mobilenet-and","title":"Mobile-Former: Bridging MobileNet and Transformer","date":"2021-08-12","arxiv_id":"2108.05895","n_code_links":4,"syntology":null},{"paper":"/paper/musiq-multi-scale-image-quality-transformer","slug":"musiq-multi-scale-image-quality-transformer","title":"MUSIQ: Multi-scale Image Quality Transformer","date":"2021-08-12","arxiv_id":"2108.05997","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 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/patrickstar-parallel-training-of-pre-trained","slug":"patrickstar-parallel-training-of-pre-trained","title":"PatrickStar: Parallel Training of Pre-trained Models via Chunk-based Memory Management","date":"2021-08-12","arxiv_id":"2108.05818","n_code_links":1,"syntology":null},{"paper":"/paper/tvt-transferable-vision-transformer-for","slug":"tvt-transferable-vision-transformer-for","title":"TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation","date":"2021-08-12","arxiv_id":"2108.05988","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"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":["uta-smile/TVT"],"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":"abstractive-sentence-summarization-with-1","title":"ICAF: Iterative Contrastive Alignment Framework for Multimodal Abstractive Summarization","date":"2021-08-11","arxiv_id":"2108.05123","n_code_links":0,"syntology":null},{"paper":null,"slug":"convnets-vs-transformers-whose-visual","title":"ConvNets vs. Transformers: Whose Visual Representations are More Transferable?","date":"2021-08-11","arxiv_id":"2108.05305","n_code_links":0,"syntology":null},{"paper":"/paper/perturbing-inputs-for-fragile-interpretations","slug":"perturbing-inputs-for-fragile-interpretations","title":"Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing","date":"2021-08-11","arxiv_id":"2108.04990","n_code_links":1,"syntology":null},{"paper":"/paper/variable-length-music-score-infilling-via","slug":"variable-length-music-score-infilling-via","title":"Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding","date":"2021-08-11","arxiv_id":"2108.05064","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaptive-multi-resolution-attention-with","title":"Adaptive Multi-Resolution Attention with Linear Complexity","date":"2021-08-10","arxiv_id":"2108.04962","n_code_links":0,"syntology":null},{"paper":"/paper/adarnn-adaptive-learning-and-forecasting-of","slug":"adarnn-adaptive-learning-and-forecasting-of","title":"AdaRNN: Adaptive Learning and Forecasting of Time Series","date":"2021-08-10","arxiv_id":"2108.04443","n_code_links":2,"syntology":null},{"paper":"/paper/differentiable-subset-pruning-of-transformer","slug":"differentiable-subset-pruning-of-transformer","title":"Differentiable Subset Pruning of Transformer Heads","date":"2021-08-10","arxiv_id":"2108.04657","n_code_links":2,"syntology":null},{"paper":"/paper/end-to-end-user-behavior-retrieval-in-click","slug":"end-to-end-user-behavior-retrieval-in-click","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","date":"2021-08-10","arxiv_id":"2108.04468","n_code_links":1,"syntology":null},{"paper":null,"slug":"ft-tdr-frequency-guided-transformer-and-top","title":"FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpainting","date":"2021-08-10","arxiv_id":"2108.04424","n_code_links":0,"syntology":null},{"paper":"/paper/do-images-really-do-the-talking-analysing-the","slug":"do-images-really-do-the-talking-analysing-the","title":"Do Images really do the Talking? Analysing the significance of Images in Tamil Troll meme classification","date":"2021-08-09","arxiv_id":"2108.03886","n_code_links":1,"syntology":null},{"paper":null,"slug":"intent5-search-result-diversification-using","title":"IntenT5: Search Result Diversification using Causal Language Models","date":"2021-08-09","arxiv_id":"2108.04026","n_code_links":0,"syntology":null},{"paper":"/paper/making-transformers-solve-compositional-tasks","slug":"making-transformers-solve-compositional-tasks","title":"Making Transformers Solve Compositional Tasks","date":"2021-08-09","arxiv_id":"2108.04378","n_code_links":1,"syntology":null},{"paper":"/paper/paint-transformer-feed-forward-neural","slug":"paint-transformer-feed-forward-neural","title":"Paint Transformer: Feed Forward Neural Painting with Stroke Prediction","date":"2021-08-09","arxiv_id":"2108.03798","n_code_links":2,"syntology":null},{"paper":"/paper/raftmlp-do-mlp-based-models-dream-of-winning","slug":"raftmlp-do-mlp-based-models-dream-of-winning","title":"RaftMLP: How Much Can Be Done Without Attention and with Less Spatial Locality?","date":"2021-08-09","arxiv_id":"2108.04384","n_code_links":2,"syntology":null},{"paper":null,"slug":"the-hw-tsc-s-offline-speech-translation","title":"The HW-TSC's Offline Speech Translation Systems for IWSLT 2021 Evaluation","date":"2021-08-09","arxiv_id":"2108.03845","n_code_links":0,"syntology":null},{"paper":"/paper/edge-augmented-graph-transformers-global-self","slug":"edge-augmented-graph-transformers-global-self","title":"Global Self-Attention as a Replacement for Graph Convolution","date":"2021-08-07","arxiv_id":"2108.03348","n_code_links":3,"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":["shamim-hussain/egt","shamim-hussain/egt_pytorch","shamim-hussain/egt_triangular"],"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/hetemotionnet-two-stream-heterogeneous-graph","slug":"hetemotionnet-two-stream-heterogeneous-graph","title":"HetEmotionNet: Two-Stream Heterogeneous Graph Recurrent Neural Network for Multi-modal Emotion Recognition","date":"2021-08-07","arxiv_id":"2108.03354","n_code_links":2,"syntology":null},{"paper":"/paper/rethinking-of-alphastar","slug":"rethinking-of-alphastar","title":"Rethinking of AlphaStar","date":"2021-08-07","arxiv_id":"2108.03452","n_code_links":2,"syntology":null},{"paper":null,"slug":"vision-transformers-for-femur-fracture","title":"Vision Transformer for femur fracture classification","date":"2021-08-07","arxiv_id":"2108.03414","n_code_links":0,"syntology":null},{"paper":null,"slug":"offensive-language-and-hate-speech-detection-1","title":"Offensive Language and Hate Speech Detection with Deep Learning and Transfer Learning","date":"2021-08-06","arxiv_id":"2108.03305","n_code_links":0,"syntology":null},{"paper":"/paper/simpler-is-better-few-shot-semantic","slug":"simpler-is-better-few-shot-semantic","title":"Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer","date":"2021-08-06","arxiv_id":"2108.03032","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 1 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":["zhiheLu/CWT-for-FSS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-right-to-talk-an-audio-visual-transformer","slug":"the-right-to-talk-an-audio-visual-transformer","title":"The Right to Talk: An Audio-Visual Transformer Approach","date":"2021-08-06","arxiv_id":"2108.03256","n_code_links":1,"syntology":null},{"paper":"/paper/fast-convergence-of-detr-with-spatially-1","slug":"fast-convergence-of-detr-with-spatially-1","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","date":"2021-08-05","arxiv_id":"2108.02404","n_code_links":1,"syntology":null},{"paper":"/paper/finetuning-pretrained-transformers-into","slug":"finetuning-pretrained-transformers-into","title":"Finetuning Pretrained Transformers into Variational Autoencoders","date":"2021-08-05","arxiv_id":"2108.02446","n_code_links":1,"syntology":null},{"paper":null,"slug":"rockgpt-reconstructing-three-dimensional","title":"RockGPT: Reconstructing three-dimensional digital rocks from single two-dimensional slice from the perspective of video generation","date":"2021-08-05","arxiv_id":"2108.03132","n_code_links":0,"syntology":null},{"paper":null,"slug":"transrefer3d-entity-and-relation-aware","title":"TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding","date":"2021-08-05","arxiv_id":"2108.02388","n_code_links":0,"syntology":null},{"paper":null,"slug":"wechat-neural-machine-translation-systems-for-1","title":"WeChat Neural Machine Translation Systems for WMT21","date":"2021-08-05","arxiv_id":"2108.02401","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-latency-for-online-video","title":"Optimizing Latency for Online Video CaptioningUsing Audio-Visual Transformers","date":"2021-08-04","arxiv_id":"2108.02147","n_code_links":0,"syntology":null},{"paper":null,"slug":"random-offset-block-embedding-array-robe-for","title":"Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000$\\times$ Compression and 3.1$\\times$ Faster Inference","date":"2021-08-04","arxiv_id":"2108.02191","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-dynamic-head-importance-computation","title":"A Dynamic Head Importance Computation Mechanism for Neural Machine Translation","date":"2021-08-03","arxiv_id":"2108.01377","n_code_links":0,"syntology":null},{"paper":"/paper/a-study-of-multilingual-end-to-end-speech","slug":"a-study-of-multilingual-end-to-end-speech","title":"A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and English","date":"2021-08-03","arxiv_id":"2108.01280","n_code_links":1,"syntology":null},{"paper":"/paper/q-pain-a-question-answering-dataset-to","slug":"q-pain-a-question-answering-dataset-to","title":"Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Management","date":"2021-08-03","arxiv_id":"2108.01764","n_code_links":0,"syntology":null},{"paper":"/paper/vision-transformer-with-progressive-sampling","slug":"vision-transformer-with-progressive-sampling","title":"Vision Transformer with Progressive Sampling","date":"2021-08-03","arxiv_id":"2108.01684","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"6 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yuexy/PS-ViT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/congested-crowd-instance-localization-with","slug":"congested-crowd-instance-localization-with","title":"Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer","date":"2021-08-02","arxiv_id":"2108.00584","n_code_links":1,"syntology":null},{"paper":"/paper/constrained-graphic-layout-generation-via","slug":"constrained-graphic-layout-generation-via","title":"Constrained Graphic Layout Generation via Latent Optimization","date":"2021-08-02","arxiv_id":"2108.00871","n_code_links":1,"syntology":null},{"paper":null,"slug":"musical-speech-a-transformer-based","title":"Musical Speech: A Transformer-based Composition Tool","date":"2021-08-02","arxiv_id":"2108.01043","n_code_links":0,"syntology":null},{"paper":"/paper/representation-learning-for-neural-population","slug":"representation-learning-for-neural-population","title":"Representation learning for neural population activity with Neural Data Transformers","date":"2021-08-02","arxiv_id":"2108.01210","n_code_links":1,"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, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["snel-repo/neural-data-transformers"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"self-supervised-answer-retrieval-on-clinical","title":"Self-supervised Answer Retrieval on Clinical Notes","date":"2021-08-02","arxiv_id":"2108.00775","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-bidirectional-transformer-based-alignment","title":"A Bidirectional Transformer Based Alignment Model for Unsupervised Word Alignment","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/are-pretrained-convolutions-better-than","slug":"are-pretrained-convolutions-better-than","title":"Are Pretrained Convolutions Better than Pretrained Transformers?","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/bertac-enhancing-transformer-based-language","slug":"bertac-enhancing-transformer-based-language","title":"BERTAC: Enhancing Transformer-based Language Models with Adversarially Pretrained Convolutional Neural Networks","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"best-of-both-worlds-making-high-accuracy-non","title":"Best of Both Worlds: Making High Accuracy Non-incremental Transformer-based Disfluency Detection Incremental","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/beyond-sentence-level-end-to-end-speech","slug":"beyond-sentence-level-end-to-end-speech","title":"Beyond Sentence-Level End-to-End Speech Translation: Context Helps","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/ctfn-hierarchical-learning-for-multimodal","slug":"ctfn-hierarchical-learning-for-multimodal","title":"CTFN: Hierarchical Learning for Multimodal Sentiment Analysis Using Coupled-Translation Fusion Network","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-differential-amplifier-for-extractive","title":"Deep Differential Amplifier for Extractive Summarization","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/ecco-an-open-source-library-for-the","slug":"ecco-an-open-source-library-for-the","title":"Ecco: An Open Source Library for the Explainability of Transformer Language Models","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/employing-argumentation-knowledge-graphs-for","slug":"employing-argumentation-knowledge-graphs-for","title":"Employing Argumentation Knowledge Graphs for Neural Argument Generation","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/explanations-for-commonsenseqa-new-dataset","slug":"explanations-for-commonsenseqa-new-dataset","title":"Explanations for CommonsenseQA: New Dataset and Models","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-listwise-evidence-reasoning-with-t5","title":"Exploring Listwise Evidence Reasoning with T5 for Fact Verification","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-and-accurate-neural-machine-translation","title":"Fast and Accurate Neural Machine Translation with Translation Memory","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"kuileixi-a-chinese-open-ended-text-adventure","title":"KuiLeiXi: a Chinese Open-Ended Text Adventure Game","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/lasor-learning-accurate-3d-human-pose-and","slug":"lasor-learning-accurate-3d-human-pose-and","title":"LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering","date":"2021-08-01","arxiv_id":"2108.00351","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"7 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["iGame-Lab/LASOR"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"modeling-task-aware-mimo-cardinality-for","title":"Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/more-than-text-multi-modal-chinese-word","slug":"more-than-text-multi-modal-chinese-word","title":"More than Text: Multi-modal Chinese Word Segmentation","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-head-highly-parallelized-lstm-decoder","title":"Multi-Head Highly Parallelized LSTM Decoder for Neural Machine Translation","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"nmt5-is-parallel-data-still-relevant-for-pre-1","title":"nmT5 - Is parallel data still relevant for pre-training massively multilingual language models?","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"paw-at-semeval-2021-task-2-multilingual-and","title":"PAW at SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation : Exploring Cross Lingual Transfer, Augmentations and Adversarial Training","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"point-disambiguate-and-copy-incorporating","title":"Point, Disambiguate and Copy: Incorporating Bilingual Dictionaries for Neural Machine Translation","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pral-a-tailored-pre-training-model-for-task","title":"PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"stretch-vst-getting-flexible-with-visual","title":"Stretch-VST: Getting Flexible With Visual Stories","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"synchronous-syntactic-attention-for","title":"Synchronous Syntactic Attention for Transformer Neural Machine Translation","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tgea-an-error-annotated-dataset-and-benchmark","title":"TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"to-pos-tag-or-not-to-pos-tag-the-impact-of","title":"To POS Tag or Not to POS Tag: The Impact of POS Tags on Morphological Learning in Low-Resource Settings","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-deep-imitation-learning-for","title":"Transformer-based deep imitation learning for dual-arm robot manipulation","date":"2021-08-01","arxiv_id":"2108.00385","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-map-matching-with-model","title":"Transformer-based Map Matching Model with Limited Ground-Truth Data using Transfer-Learning Approach","date":"2021-08-01","arxiv_id":"2108.00439","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-encoder-gru-t-e-gru-for-chinese","title":"Transformer-Encoder-GRU (T-E-GRU) for Chinese Sentiment Analysis on Chinese Comment Text","date":"2021-08-01","arxiv_id":"2108.00400","n_code_links":0,"syntology":null},{"paper":null,"slug":"unleash-gpt-2-power-for-event-detection","title":"Unleash GPT-2 Power for Event Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/youngsheldon-at-semeval-2021-task-5-fine","slug":"youngsheldon-at-semeval-2021-task-5-fine","title":"YoungSheldon at SemEval-2021 Task 5: Fine-tuning Pre-trained Language Models for Toxic Spans Detection using Token classification Objective","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/dadagp-a-dataset-of-tokenized-guitarpro-songs","slug":"dadagp-a-dataset-of-tokenized-guitarpro-songs","title":"DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models","date":"2021-07-30","arxiv_id":"2107.14653","n_code_links":1,"syntology":null},{"paper":"/paper/dpt-deformable-patch-based-transformer-for","slug":"dpt-deformable-patch-based-transformer-for","title":"DPT: Deformable Patch-based Transformer for Visual Recognition","date":"2021-07-30","arxiv_id":"2107.14467","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":["CASIA-IVA-Lab/DPT"],"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"]}}}],"record_sha256":"8a7079ae8f1717da204a76f6069c32e68e6e03a59e93877790540aec3c981e5c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}