{"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/169","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":169,"pages_in_order":190,"rows_per_page":100,"rows":[16801,16900],"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/168","next":"/method/bpe/papers/170","papers":[{"paper":"/paper/hierarchical-transformer-networks-for","slug":"hierarchical-transformer-networks-for","title":"Three-level Hierarchical Transformer Networks for Long-sequence and Multiple Clinical Documents Classification","date":"2021-04-17","arxiv_id":"2104.08444","n_code_links":1,"syntology":null},{"paper":"/paper/higher-order-recurrent-space-time-transformer","slug":"higher-order-recurrent-space-time-transformer","title":"Higher Order Recurrent Space-Time Transformer for Video Action Prediction","date":"2021-04-17","arxiv_id":"2104.08665","n_code_links":1,"syntology":null},{"paper":"/paper/visual-transformer-pruning","slug":"visual-transformer-pruning","title":"Vision Transformer Pruning","date":"2021-04-17","arxiv_id":"2104.08500","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":null}},{"paper":"/paper/zero-shot-slot-filling-with-dpr-and-rag","slug":"zero-shot-slot-filling-with-dpr-and-rag","title":"Zero-shot Slot Filling with DPR and RAG","date":"2021-04-17","arxiv_id":"2104.08610","n_code_links":2,"syntology":null},{"paper":"/paper/an-adversarially-learned-turing-test-for","slug":"an-adversarially-learned-turing-test-for","title":"An Adversarially-Learned Turing Test for Dialog Generation Models","date":"2021-04-16","arxiv_id":"2104.08231","n_code_links":1,"syntology":null},{"paper":null,"slug":"comparison-of-grammatical-error-correction","title":"Comparison of Grammatical Error Correction Using Back-Translation Models","date":"2021-04-16","arxiv_id":"2104.07848","n_code_links":0,"syntology":null},{"paper":"/paper/editing-factual-knowledge-in-language-models","slug":"editing-factual-knowledge-in-language-models","title":"Editing Factual Knowledge in Language Models","date":"2021-04-16","arxiv_id":"2104.08164","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nicola-decao/KnowledgeEditor"],"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":"/paper/is-your-language-model-ready-for-dense","slug":"is-your-language-model-ready-for-dense","title":"Condenser: a Pre-training Architecture for Dense Retrieval","date":"2021-04-16","arxiv_id":"2104.08253","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 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["luyug/Condenser"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/serial-or-parallel-plug-able-adapter-for","slug":"serial-or-parallel-plug-able-adapter-for","title":"Counter-Interference Adapter for Multilingual Machine Translation","date":"2021-04-16","arxiv_id":"2104.08154","n_code_links":1,"syntology":null},{"paper":"/paper/surface-form-competition-why-the-highest","slug":"surface-form-competition-why-the-highest","title":"Surface Form Competition: Why the Highest Probability Answer Isn't Always Right","date":"2021-04-16","arxiv_id":"2104.08315","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":0,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["peterwestuw/surface-form-competition"],"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/text2app-a-framework-for-creating-android","slug":"text2app-a-framework-for-creating-android","title":"Text2App: A Framework for Creating Android Apps from Text Descriptions","date":"2021-04-16","arxiv_id":"2104.08301","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-survey-of-recent-abstract-summarization","title":"A Survey of Recent Abstract Summarization Techniques","date":"2021-04-15","arxiv_id":"2105.00824","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-sparse-transformer-for-multilingual","title":"Adaptive Sparse Transformer for Multilingual Translation","date":"2021-04-15","arxiv_id":"2104.07358","n_code_links":0,"syntology":null},{"paper":"/paper/cross-domain-speech-recognition-with","slug":"cross-domain-speech-recognition-with","title":"Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching","date":"2021-04-15","arxiv_id":"2104.07491","n_code_links":1,"syntology":null},{"paper":null,"slug":"demystify-optimization-challenges-in","title":"Robust Optimization for Multilingual Translation with Imbalanced Data","date":"2021-04-15","arxiv_id":"2104.07639","n_code_links":0,"syntology":null},{"paper":"/paper/explagraphs-an-explanation-graph-generation","slug":"explagraphs-an-explanation-graph-generation","title":"ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning","date":"2021-04-15","arxiv_id":"2104.07644","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["swarnaHub/ExplaGraphs"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/nt5-training-t5-to-perform-numerical","slug":"nt5-training-t5-to-perform-numerical","title":"NT5?! Training T5 to Perform Numerical Reasoning","date":"2021-04-15","arxiv_id":"2104.07307","n_code_links":1,"syntology":null},{"paper":"/paper/points-as-queries-weakly-semi-supervised","slug":"points-as-queries-weakly-semi-supervised","title":"Points as Queries: Weakly Semi-supervised Object Detection by Points","date":"2021-04-15","arxiv_id":"2104.07434","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":null}},{"paper":"/paper/rethinking-text-line-recognition-models","slug":"rethinking-text-line-recognition-models","title":"Rethinking Text Line Recognition Models","date":"2021-04-15","arxiv_id":"2104.07787","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-video-object-segmentation-by","slug":"self-supervised-video-object-segmentation-by","title":"Self-supervised Video Object Segmentation by Motion Grouping","date":"2021-04-15","arxiv_id":"2104.07658","n_code_links":0,"syntology":null},{"paper":"/paper/shoulder-implant-x-ray-manufacturer","slug":"shoulder-implant-x-ray-manufacturer","title":"Shoulder Implant X-Ray Manufacturer Classification: Exploring with Vision Transformer","date":"2021-04-15","arxiv_id":"2104.07667","n_code_links":1,"syntology":null},{"paper":"/paper/syntax-aware-graph-to-graph-transformer-for","slug":"syntax-aware-graph-to-graph-transformer-for","title":"Syntax-Aware Graph-to-Graph Transformer for Semantic Role Labelling","date":"2021-04-15","arxiv_id":"2104.07704","n_code_links":0,"syntology":null},{"paper":"/paper/torontocl-at-cmcl-2021-shared-task-roberta","slug":"torontocl-at-cmcl-2021-shared-task-roberta","title":"TorontoCL at CMCL 2021 Shared Task: RoBERTa with Multi-Stage Fine-Tuning for Eye-Tracking Prediction","date":"2021-04-15","arxiv_id":"2104.07244","n_code_links":1,"syntology":null},{"paper":null,"slug":"vision-transformer-using-low-level-chest-x","title":"Vision Transformer using Low-level Chest X-ray Feature Corpus for COVID-19 Diagnosis and Severity Quantification","date":"2021-04-15","arxiv_id":"2104.07235","n_code_links":0,"syntology":null},{"paper":"/paper/an-introduction-of-mini-alphastar","slug":"an-introduction-of-mini-alphastar","title":"An Introduction of mini-AlphaStar","date":"2021-04-14","arxiv_id":"2104.06890","n_code_links":1,"syntology":null},{"paper":"/paper/decoupled-spatial-temporal-transformer-for","slug":"decoupled-spatial-temporal-transformer-for","title":"Decoupled Spatial-Temporal Transformer for Video Inpainting","date":"2021-04-14","arxiv_id":"2104.06637","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-driven-answer-generation-for","title":"Knowledge-driven Answer Generation for Conversational Search","date":"2021-04-14","arxiv_id":"2104.06892","n_code_links":0,"syntology":null},{"paper":"/paper/nareor-the-narrative-reordering-problem","slug":"nareor-the-narrative-reordering-problem","title":"NAREOR: The Narrative Reordering Problem","date":"2021-04-14","arxiv_id":"2104.06669","n_code_links":1,"syntology":null},{"paper":null,"slug":"non-autoregressive-sequence-to-sequence-voice","title":"Non-autoregressive sequence-to-sequence voice conversion","date":"2021-04-14","arxiv_id":"2104.06793","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-attention-with-linear-units","slug":"sparse-attention-with-linear-units","title":"Sparse Attention with Linear Units","date":"2021-04-14","arxiv_id":"2104.07012","n_code_links":3,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 1 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":["bzhangGo/zero"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"paper":"/paper/tweac-transformer-with-extendable-qa-agent","slug":"tweac-transformer-with-extendable-qa-agent","title":"TWEAC: Transformer with Extendable QA Agent Classifiers","date":"2021-04-14","arxiv_id":"2104.07081","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-a-transformer-pass-the-wug-test-tuning","title":"Can a Transformer Pass the Wug Test? Tuning Copying Bias in Neural Morphological Inflection Models","date":"2021-04-13","arxiv_id":"2104.06483","n_code_links":0,"syntology":null},{"paper":"/paper/discourse-probing-of-pretrained-language","slug":"discourse-probing-of-pretrained-language","title":"Discourse Probing of Pretrained Language Models","date":"2021-04-13","arxiv_id":"2104.05882","n_code_links":1,"syntology":null},{"paper":"/paper/ms2-multi-document-summarization-of-medical","slug":"ms2-multi-document-summarization-of-medical","title":"MS2: Multi-Document Summarization of Medical Studies","date":"2021-04-13","arxiv_id":"2104.06486","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["allenai/ms2"],"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":["listed","official"]}}},{"paper":"/paper/qa-gnn-reasoning-with-language-models-and","slug":"qa-gnn-reasoning-with-language-models-and","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","date":"2021-04-13","arxiv_id":"2104.06378","n_code_links":6,"syntology":{"ran":8,"of":25,"n_ran_checked":8,"n_instrument":0,"unverified":17,"pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 17 unverified","official":{"repos":["michiyasunaga/qagnn","worksheets.codalab.org/worksheets/0xf215deb05edf44a2ac353c711f52a25f"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":13,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"semantic-maps-and-metrics-for-science","title":"Semantic maps and metrics for science Semantic maps and metrics for science using deep transformer encoders","date":"2021-04-13","arxiv_id":"2104.05928","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-methods-for-recognizing","title":"Transformer-based Methods for Recognizing Ultra Fine-grained Entities (RUFES)","date":"2021-04-13","arxiv_id":"2104.06048","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-transformers-for-bot-detection","slug":"understanding-transformers-for-bot-detection","title":"Understanding Transformers for Bot Detection in Twitter","date":"2021-04-13","arxiv_id":"2104.06182","n_code_links":1,"syntology":null},{"paper":null,"slug":"upb-at-semeval-2021-task-7-adversarial-multi","title":"UPB at SemEval-2021 Task 7: Adversarial Multi-Task Learning for Detecting and Rating Humor and Offense","date":"2021-04-13","arxiv_id":"2104.06063","n_code_links":0,"syntology":null},{"paper":"/paper/vit-v-net-vision-transformer-for-unsupervised","slug":"vit-v-net-vision-transformer-for-unsupervised","title":"ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration","date":"2021-04-13","arxiv_id":"2104.06468","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":6,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["junyuchen245/ViT-V-Net_for_3D_Image_Registration_Pytorch"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/cloth-interactive-transformer-for-virtual-try","slug":"cloth-interactive-transformer-for-virtual-try","title":"Cloth Interactive Transformer for Virtual Try-On","date":"2021-04-12","arxiv_id":"2104.05519","n_code_links":1,"syntology":null},{"paper":null,"slug":"family-of-origin-and-family-of-choice","title":"Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Machine Translation","date":"2021-04-12","arxiv_id":"2104.05848","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-dynamic-and-hierarchical-traffic","title":"Learning dynamic and hierarchical traffic spatiotemporal features with Transformer","date":"2021-04-12","arxiv_id":"2104.05163","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-synthesize-data-for-semantic","slug":"learning-to-synthesize-data-for-semantic","title":"Learning to Synthesize Data for Semantic Parsing","date":"2021-04-12","arxiv_id":"2104.05827","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-language-models-predict-human","slug":"multilingual-language-models-predict-human","title":"Multilingual Language Models Predict Human Reading Behavior","date":"2021-04-12","arxiv_id":"2104.05433","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-representation-learning-for-scientific","title":"On Representation Learning for Scientific News Articles Using Heterogeneous Knowledge Graphs","date":"2021-04-12","arxiv_id":"2104.05866","n_code_links":0,"syntology":null},{"paper":"/paper/paragraph-level-simplification-of-medical","slug":"paragraph-level-simplification-of-medical","title":"Paragraph-level Simplification of Medical Texts","date":"2021-04-12","arxiv_id":"2104.05767","n_code_links":1,"syntology":null},{"paper":null,"slug":"updater-extractor-architecture-for-inductive","title":"Updater-Extractor Architecture for Inductive World State Representations","date":"2021-04-12","arxiv_id":"2104.05500","n_code_links":0,"syntology":null},{"paper":"/paper/unidrop-a-simple-yet-effective-technique-to","slug":"unidrop-a-simple-yet-effective-technique-to","title":"UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost","date":"2021-04-11","arxiv_id":"2104.04946","n_code_links":0,"syntology":null},{"paper":"/paper/meta-tuning-language-models-to-answer-prompts","slug":"meta-tuning-language-models-to-answer-prompts","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","date":"2021-04-10","arxiv_id":"2104.04670","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-transformer-networks-for-time-series","title":"Deep Transformer Networks for Time Series Classification: The NPP Safety Case","date":"2021-04-09","arxiv_id":"2104.05448","n_code_links":0,"syntology":null},{"paper":null,"slug":"ki-bert-infusing-knowledge-context-for-better","title":"KI-BERT: Infusing Knowledge Context for Better Language and Domain Understanding","date":"2021-04-09","arxiv_id":"2104.08145","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-aware-graph-enhanced-gpt-2-for","slug":"knowledge-aware-graph-enhanced-gpt-2-for","title":"Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking","date":"2021-04-09","arxiv_id":"2104.04466","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformers-the-end-of-history-for-nlp","title":"Transformers: \"The End of History\" for NLP?","date":"2021-04-09","arxiv_id":"2105.00813","n_code_links":0,"syntology":null},{"paper":null,"slug":"layer-reduction-accelerating-conformer-based","title":"Layer Reduction: Accelerating Conformer-Based Self-Supervised Model via Layer Consistency","date":"2021-04-08","arxiv_id":"2105.00812","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-simple-neural-probabilistic","slug":"revisiting-simple-neural-probabilistic","title":"Revisiting Simple Neural Probabilistic Language Models","date":"2021-04-08","arxiv_id":"2104.03474","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":["SimengSun/revisit-nplm"],"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":"facial-attribute-transformers-for-precise-and","title":"Facial Attribute Transformers for Precise and Robust Makeup Transfer","date":"2021-04-07","arxiv_id":"2104.02894","n_code_links":0,"syntology":null},{"paper":null,"slug":"interpreting-a-pre-trained-model-is-a-key-for","title":"Interpreting A Pre-trained Model Is A Key For Model Architecture Optimization: A Case Study On Wav2Vec 2.0","date":"2021-04-07","arxiv_id":"2104.02851","n_code_links":0,"syntology":null},{"paper":null,"slug":"li-net-large-pose-identity-preserving-face","title":"LI-Net: Large-Pose Identity-Preserving Face Reenactment Network","date":"2021-04-07","arxiv_id":"2104.02850","n_code_links":0,"syntology":null},{"paper":"/paper/seeing-out-of-the-box-end-to-end-pre-training","slug":"seeing-out-of-the-box-end-to-end-pre-training","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","date":"2021-04-07","arxiv_id":"2104.03135","n_code_links":3,"syntology":null},{"paper":null,"slug":"attention-head-masking-for-inference-time","title":"Attention Head Masking for Inference Time Content Selection in Abstractive Summarization","date":"2021-04-06","arxiv_id":"2104.02205","n_code_links":0,"syntology":null},{"paper":"/paper/codetrans-towards-cracking-the-language-of","slug":"codetrans-towards-cracking-the-language-of","title":"CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing","date":"2021-04-06","arxiv_id":"2104.02443","n_code_links":1,"syntology":null},{"paper":"/paper/fourier-image-transformer","slug":"fourier-image-transformer","title":"Fourier Image Transformer","date":"2021-04-06","arxiv_id":"2104.02555","n_code_links":1,"syntology":null},{"paper":"/paper/lt-lm-a-novel-non-autoregressive-language","slug":"lt-lm-a-novel-non-autoregressive-language","title":"LT-LM: a novel non-autoregressive language model for single-shot lattice rescoring","date":"2021-04-06","arxiv_id":"2104.02526","n_code_links":1,"syntology":null},{"paper":null,"slug":"muslcat-multi-scale-multi-level-convolutional","title":"MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms","date":"2021-04-06","arxiv_id":"2104.02309","n_code_links":0,"syntology":null},{"paper":null,"slug":"ode-transformer-an-ordinary-differential","title":"ODE Transformer: An Ordinary Differential Equation-Inspired Model for Neural Machine Translation","date":"2021-04-06","arxiv_id":"2104.02308","n_code_links":0,"syntology":null},{"paper":"/paper/variable-selection-with-missing-data-in-both","slug":"variable-selection-with-missing-data-in-both","title":"Variable selection with missing data in both covariates and outcomes: Imputation and machine learning","date":"2021-04-06","arxiv_id":"2104.02769","n_code_links":1,"syntology":null},{"paper":null,"slug":"variational-transformer-networks-for-layout","title":"Variational Transformer Networks for Layout Generation","date":"2021-04-06","arxiv_id":"2104.02416","n_code_links":0,"syntology":null},{"paper":"/paper/ast-audio-spectrogram-transformer","slug":"ast-audio-spectrogram-transformer","title":"AST: Audio Spectrogram Transformer","date":"2021-04-05","arxiv_id":"2104.01778","n_code_links":5,"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":["YuanGongND/ast"],"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":"exploring-transformers-in-emotion-recognition","title":"Exploring Transformers in Emotion Recognition: a comparison of BERT, DistillBERT, RoBERTa, XLNet and ELECTRA","date":"2021-04-05","arxiv_id":"2104.02041","n_code_links":0,"syntology":null},{"paper":"/paper/iitk-detox-at-semeval-2021-task-5-semi","slug":"iitk-detox-at-semeval-2021-task-5-semi","title":"IITK@Detox at SemEval-2021 Task 5: Semi-Supervised Learning and Dice Loss for Toxic Spans Detection","date":"2021-04-04","arxiv_id":"2104.01566","n_code_links":1,"syntology":null},{"paper":null,"slug":"indt5-a-text-to-text-transformer-for-10","title":"IndT5: A Text-to-Text Transformer for 10 Indigenous Languages","date":"2021-04-04","arxiv_id":"2104.07483","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfornn-capturing-the-sequential","title":"TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling","date":"2021-04-04","arxiv_id":"2104.01572","n_code_links":0,"syntology":null},{"paper":"/paper/deepfake-detection-scheme-based-on-vision","slug":"deepfake-detection-scheme-based-on-vision","title":"Deepfake Detection Scheme Based on Vision Transformer and Distillation","date":"2021-04-03","arxiv_id":"2104.01353","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-detr-improving-end-to-end-object","title":"Efficient DETR: Improving End-to-End Object Detector with Dense Prior","date":"2021-04-03","arxiv_id":"2104.01318","n_code_links":0,"syntology":null},{"paper":null,"slug":"aaformer-auto-aligned-transformer-for-person","title":"AAformer: Auto-Aligned Transformer for Person Re-Identification","date":"2021-04-02","arxiv_id":"2104.00921","n_code_links":0,"syntology":null},{"paper":null,"slug":"effect-of-depth-order-on-iterative-nested","title":"Effect of depth order on iterative nested named entity recognition models","date":"2021-04-02","arxiv_id":"2104.01037","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-based-video-editing-via-multi-modal","title":"M3L: Language-based Video Editing via Multi-Modal Multi-Level Transformers","date":"2021-04-02","arxiv_id":"2104.01122","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-gpt-2-to-create-synthetic-data-to","title":"Using GPT-2 to Create Synthetic Data to Improve the Prediction Performance of NLP Machine Learning Classification Models","date":"2021-04-02","arxiv_id":"2104.10658","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-new-view-of-multi-modal-language-analysis","title":"A New View of Multi-modal Language Analysis: Audio and Video Features as Text ``Styles''","date":"2021-04-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bart-tl-weakly-supervised-topic-label","title":"BART-TL: Weakly-Supervised Topic Label Generation","date":"2021-04-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-graph-transformer-for-implicit-tag","title":"Dynamic Graph Transformer for Implicit Tag Recognition","date":"2021-04-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"enriching-non-autoregressive-transformer-with-1","title":"Enriching Non-Autoregressive Transformer with Syntactic and Semantic Structures for Neural Machine Translation","date":"2021-04-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/from-characters-to-words-the-turning-point-of","slug":"from-characters-to-words-the-turning-point-of","title":"From characters to words: the turning point of BPE merges","date":"2021-04-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"interpret-an-interactive-visualization-tool","title":"InterpreT: An Interactive Visualization Tool for Interpreting Transformers","date":"2021-04-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/loftr-detector-free-local-feature-matching","slug":"loftr-detector-free-local-feature-matching","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","date":"2021-04-01","arxiv_id":"2104.00680","n_code_links":4,"syntology":{"ran":14,"of":16,"n_ran_checked":11,"n_instrument":3,"unverified":2,"pointer_only":3,"phrase":"14 ran (of which 6 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zju3dv/LoFTR"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/multitarget-tracking-with-transformers","slug":"multitarget-tracking-with-transformers","title":"Next Generation Multitarget Trackers: Random Finite Set Methods vs Transformer-based Deep Learning","date":"2021-04-01","arxiv_id":"2104.00734","n_code_links":1,"syntology":null},{"paper":"/paper/putting-nerf-on-a-diet-semantically","slug":"putting-nerf-on-a-diet-semantically","title":"Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis","date":"2021-04-01","arxiv_id":"2104.00677","n_code_links":2,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ajayjain/DietNeRF"],"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/russian-paraphrasers-paraphrase-with","slug":"russian-paraphrasers-paraphrase-with","title":"Russian Paraphrasers: Paraphrase with Transformers","date":"2021-04-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/spatial-temporal-graph-transformer-for","slug":"spatial-temporal-graph-transformer-for","title":"TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking","date":"2021-04-01","arxiv_id":"2104.00194","n_code_links":0,"syntology":null},{"paper":null,"slug":"through-the-looking-glass-learning-to","title":"Through the Looking Glass: Learning to Attribute Synthetic Text Generated by Language Models","date":"2021-04-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"wakavt-a-sequential-variational-transformer","title":"WakaVT: A Sequential Variational Transformer for Waka Generation","date":"2021-04-01","arxiv_id":"2104.00426","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-neighbourhood-framework-for-resource-lean","title":"A Neighbourhood Framework for Resource-Lean Content Flagging","date":"2021-03-31","arxiv_id":"2103.17055","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-attacks-and-defenses-for-speech","title":"Adversarial Attacks and Defenses for Speech Recognition Systems","date":"2021-03-31","arxiv_id":"2103.17122","n_code_links":0,"syntology":null},{"paper":"/paper/learning-spatio-temporal-transformer-for","slug":"learning-spatio-temporal-transformer-for","title":"Learning Spatio-Temporal Transformer for Visual Tracking","date":"2021-03-31","arxiv_id":"2103.17154","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 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["researchmm/Stark"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"automatic-graph-partitioning-for-very-large","title":"Automatic Graph Partitioning for Very Large-scale Deep Learning","date":"2021-03-30","arxiv_id":"2103.16063","n_code_links":0,"syntology":null},{"paper":null,"slug":"read-and-attend-temporal-localisation-in-sign","title":"Read and Attend: Temporal Localisation in Sign Language Videos","date":"2021-03-30","arxiv_id":"2103.16481","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-spatial-dimensions-of-vision","slug":"rethinking-spatial-dimensions-of-vision","title":"Rethinking Spatial Dimensions of Vision Transformers","date":"2021-03-30","arxiv_id":"2103.16302","n_code_links":12,"syntology":{"ran":10,"of":20,"n_ran_checked":10,"n_instrument":0,"unverified":10,"pointer_only":0,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","official":{"repos":["naver-ai/pit"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"spatiotemporal-transformer-for-video-based","title":"Spatiotemporal Transformer for Video-based Person Re-identification","date":"2021-03-30","arxiv_id":"2103.16469","n_code_links":0,"syntology":null},{"paper":"/paper/2103-15358","slug":"2103-15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","date":"2021-03-29","arxiv_id":"2103.15358","n_code_links":3,"syntology":{"ran":8,"of":10,"n_ran_checked":5,"n_instrument":3,"unverified":2,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/vision-longformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}],"record_sha256":"c890668e688418dce1b6f3b4824ea4dc0781ec20f515919fe5043bf06949e39c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}