{"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/179","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":179,"pages_in_order":190,"rows_per_page":100,"rows":[17801,17900],"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/178","next":"/method/bpe/papers/180","papers":[{"paper":null,"slug":"end-to-end-deep-metamodeling-to-calibrate-and","title":"End-to-end deep metamodeling to calibrate and optimize energy loads","date":"2020-06-19","arxiv_id":"2006.12390","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-objective-scores-of-speech","title":"Boosting Objective Scores of a Speech Enhancement Model by MetricGAN Post-processing","date":"2020-06-18","arxiv_id":"2006.10296","n_code_links":0,"syntology":null},{"paper":"/paper/deep-learning-enabled-semantic-communication","slug":"deep-learning-enabled-semantic-communication","title":"Deep Learning Enabled Semantic Communication Systems","date":"2020-06-18","arxiv_id":"2006.10685","n_code_links":1,"syntology":null},{"paper":"/paper/i-bert-inductive-generalization-of","slug":"i-bert-inductive-generalization-of","title":"I-BERT: Inductive Generalization of Transformer to Arbitrary Context Lengths","date":"2020-06-18","arxiv_id":"2006.10220","n_code_links":1,"syntology":null},{"paper":"/paper/multi-branch-attentive-transformer","slug":"multi-branch-attentive-transformer","title":"Multi-branch Attentive Transformer","date":"2020-06-18","arxiv_id":"2006.10270","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"seal-segment-wise-extractive-abstractive-long","title":"SEAL: Segment-wise Extractive-Abstractive Long-form Text Summarization","date":"2020-06-18","arxiv_id":"2006.10213","n_code_links":0,"syntology":null},{"paper":"/paper/senwave-monitoring-the-global-sentiments","slug":"senwave-monitoring-the-global-sentiments","title":"SenWave: Monitoring the Global Sentiments under the COVID-19 Pandemic","date":"2020-06-18","arxiv_id":"2006.10842","n_code_links":2,"syntology":null},{"paper":"/paper/sparse-gpu-kernels-for-deep-learning","slug":"sparse-gpu-kernels-for-deep-learning","title":"Sparse GPU Kernels for Deep Learning","date":"2020-06-18","arxiv_id":"2006.10901","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatically-ranked-russian-paraphrase","title":"Automatically Ranked Russian Paraphrase Corpus for Text Generation","date":"2020-06-17","arxiv_id":"2006.09719","n_code_links":0,"syntology":null},{"paper":null,"slug":"intelligent-protection-classification-of","title":"Intelligent Protection & Classification of Transients in Two-Core Symmetric Phase Angle Regulating Transformers","date":"2020-06-17","arxiv_id":"2006.09865","n_code_links":0,"syntology":null},{"paper":"/paper/learning-visual-commonsense-for-robust-scene","slug":"learning-visual-commonsense-for-robust-scene","title":"Learning Visual Commonsense for Robust Scene Graph Generation","date":"2020-06-17","arxiv_id":"2006.09623","n_code_links":2,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/cross-lingual-retrieval-for-iterative-self","slug":"cross-lingual-retrieval-for-iterative-self","title":"Cross-lingual Retrieval for Iterative Self-Supervised Training","date":"2020-06-16","arxiv_id":"2006.09526","n_code_links":1,"syntology":null},{"paper":"/paper/memory-efficient-pipeline-parallel-dnn","slug":"memory-efficient-pipeline-parallel-dnn","title":"Memory-Efficient Pipeline-Parallel DNN Training","date":"2020-06-16","arxiv_id":"2006.09503","n_code_links":1,"syntology":{"ran":2,"of":10,"n_ran_checked":2,"n_instrument":0,"unverified":8,"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) · 8 unverified","official":null}},{"paper":"/paper/modeling-graph-structure-via-relative","slug":"modeling-graph-structure-via-relative","title":"Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs","date":"2020-06-16","arxiv_id":"2006.09242","n_code_links":0,"syntology":null},{"paper":null,"slug":"cooking-is-all-about-people-comment","title":"Cooking Is All About People: Comment Classification On Cookery Channels Using BERT and Classification Models (Malayalam-English Mix-Code)","date":"2020-06-15","arxiv_id":"2007.04249","n_code_links":0,"syntology":null},{"paper":null,"slug":"differentiable-neural-architecture","title":"Differentiable Neural Architecture Transformation for Reproducible Architecture Improvement","date":"2020-06-15","arxiv_id":"2006.08231","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploration-of-end-to-end-asr-for-openstt","title":"Exploration of End-to-End ASR for OpenSTT -- Russian Open Speech-to-Text Dataset","date":"2020-06-15","arxiv_id":"2006.08274","n_code_links":0,"syntology":null},{"paper":"/paper/fine-grained-human-evaluation-of-transformer","slug":"fine-grained-human-evaluation-of-transformer","title":"Fine-grained Human Evaluation of Transformer and Recurrent Approaches to Neural Machine Translation for English-to-Chinese","date":"2020-06-15","arxiv_id":"2006.08297","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-image-summarization-textual-summary","title":"Multi-Image Summarization: Textual Summary from a Set of Cohesive Images","date":"2020-06-15","arxiv_id":"2006.08686","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-multi-property-extraction-and-beyond","title":"On the Multi-Property Extraction and Beyond","date":"2020-06-15","arxiv_id":"2006.08281","n_code_links":0,"syntology":null},{"paper":null,"slug":"guided-transformer-leveraging-multiple","title":"Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search","date":"2020-06-13","arxiv_id":"2006.07548","n_code_links":0,"syntology":null},{"paper":"/paper/modelling-high-level-mathematical-reasoning","slug":"modelling-high-level-mathematical-reasoning","title":"IsarStep: a Benchmark for High-level Mathematical Reasoning","date":"2020-06-13","arxiv_id":"2006.09265","n_code_links":2,"syntology":{"ran":2,"of":8,"n_ran_checked":2,"n_instrument":0,"unverified":6,"pointer_only":0,"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) · 6 unverified","official":null}},{"paper":null,"slug":"temporal-fusion-network-for-temporal-action","title":"Temporal Fusion Network for Temporal Action Localization:Submission to ActivityNet Challenge 2020 (Task E)","date":"2020-06-13","arxiv_id":"2006.07520","n_code_links":0,"syntology":null},{"paper":null,"slug":"transferring-monolingual-model-to-low","title":"Transferring Monolingual Model to Low-Resource Language: The Case of Tigrinya","date":"2020-06-13","arxiv_id":"2006.07698","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-natural-language-processing","title":"Comparing Natural Language Processing Techniques for Alzheimer's Dementia Prediction in Spontaneous Speech","date":"2020-06-12","arxiv_id":"2006.07358","n_code_links":0,"syntology":null},{"paper":"/paper/unmasking-the-inductive-biases-of","slug":"unmasking-the-inductive-biases-of","title":"Benchmarking Unsupervised Object Representations for Video Sequences","date":"2020-06-12","arxiv_id":"2006.07034","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"7 ran (of which 0 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) · 1 unverified","official":{"repos":["ecker-lab/object-centric-representation-benchmark"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/dance-revolution-long-sequence-dance","slug":"dance-revolution-long-sequence-dance","title":"Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning","date":"2020-06-11","arxiv_id":"2006.06119","n_code_links":0,"syntology":null},{"paper":"/paper/fastpitch-parallel-text-to-speech-with-pitch","slug":"fastpitch-parallel-text-to-speech-with-pitch","title":"FastPitch: Parallel Text-to-speech with Pitch Prediction","date":"2020-06-11","arxiv_id":"2006.06873","n_code_links":6,"syntology":{"ran":8,"of":9,"n_ran_checked":7,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["NVIDIA/DeepLearningExamples"],"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","named_in_paper"]}}},{"paper":null,"slug":"implicit-kernel-attention","title":"Implicit Kernel Attention","date":"2020-06-11","arxiv_id":"2006.06147","n_code_links":0,"syntology":null},{"paper":"/paper/traffic-transformer-capturing-the-continuity","slug":"traffic-transformer-capturing-the-continuity","title":"Traffic transformer: Capturing the continuity and periodicity of time series for traffic forecasting","date":"2020-06-11","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"extrapolation-for-large-batch-training-in","title":"Extrapolation for Large-batch Training in Deep Learning","date":"2020-06-10","arxiv_id":"2006.05720","n_code_links":0,"syntology":null},{"paper":"/paper/few-shot-generative-conversational-query","slug":"few-shot-generative-conversational-query","title":"Few-Shot Generative Conversational Query Rewriting","date":"2020-06-09","arxiv_id":"2006.05009","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["thunlp/ConversationQueryRewriter"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"graph-aware-transformer-is-attention-all","title":"Graph-Aware Transformer: Is Attention All Graphs Need?","date":"2020-06-09","arxiv_id":"2006.05213","n_code_links":0,"syntology":null},{"paper":null,"slug":"hausamt-v1-0-towards-english-hausa-neural","title":"HausaMT v1.0: Towards English-Hausa Neural Machine Translation","date":"2020-06-09","arxiv_id":"2006.05014","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-paraphrase-generation-using-pre","title":"Unsupervised Paraphrase Generation using Pre-trained Language Models","date":"2020-06-09","arxiv_id":"2006.05477","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-count-words-in-fluent-speech","slug":"learning-to-count-words-in-fluent-speech","title":"Learning to Count Words in Fluent Speech enables Online Speech Recognition","date":"2020-06-08","arxiv_id":"2006.04928","n_code_links":1,"syntology":null},{"paper":"/paper/linformer-self-attention-with-linear","slug":"linformer-self-attention-with-linear","title":"Linformer: Self-Attention with Linear Complexity","date":"2020-06-08","arxiv_id":"2006.04768","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["facebookresearch/fairseq"],"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":null,"slug":"modeling-discourse-structure-for-document","title":"Modeling Discourse Structure for Document-level Neural Machine Translation","date":"2020-06-08","arxiv_id":"2006.04721","n_code_links":0,"syntology":null},{"paper":"/paper/multispeech-multi-speaker-text-to-speech-with","slug":"multispeech-multi-speaker-text-to-speech-with","title":"MultiSpeech: Multi-Speaker Text to Speech with Transformer","date":"2020-06-08","arxiv_id":"2006.04664","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"o-n-connections-are-expressive-enough","title":"$O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers","date":"2020-06-08","arxiv_id":"2006.04862","n_code_links":0,"syntology":null},{"paper":"/paper/wat-zei-je-detecting-out-of-distribution","slug":"wat-zei-je-detecting-out-of-distribution","title":"Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers","date":"2020-06-08","arxiv_id":"2006.08344","n_code_links":1,"syntology":null},{"paper":"/paper/learning-texture-transformer-network-for-1","slug":"learning-texture-transformer-network-for-1","title":"Learning Texture Transformer Network for Image Super-Resolution","date":"2020-06-07","arxiv_id":"2006.04139","n_code_links":2,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["researchmm/TTSR"],"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":null,"slug":"challenges-and-thrills-of-legal-arguments","title":"Challenges and Thrills of Legal Arguments","date":"2020-06-06","arxiv_id":"2006.03773","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-overview-of-neural-network-compression","title":"An Overview of Neural Network Compression","date":"2020-06-05","arxiv_id":"2006.03669","n_code_links":0,"syntology":null},{"paper":"/paper/deberta-decoding-enhanced-bert-with","slug":"deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","n_code_links":14,"syntology":{"ran":4,"of":13,"n_ran_checked":3,"n_instrument":1,"unverified":9,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","official":{"repos":["microsoft/DeBERTa"],"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","named_in_paper","unlocated"]}}},{"paper":"/paper/funnel-transformer-filtering-out-sequential","slug":"funnel-transformer-filtering-out-sequential","title":"Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing","date":"2020-06-05","arxiv_id":"2006.03236","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["laiguokun/Funnel-Transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/gmat-global-memory-augmentation-for","slug":"gmat-global-memory-augmentation-for","title":"GMAT: Global Memory Augmentation for Transformers","date":"2020-06-05","arxiv_id":"2006.03274","n_code_links":1,"syntology":null},{"paper":"/paper/masked-language-modeling-for-proteins-via","slug":"masked-language-modeling-for-proteins-via","title":"Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers","date":"2020-06-05","arxiv_id":"2006.03555","n_code_links":1,"syntology":null},{"paper":"/paper/visual-transformers-token-based-image","slug":"visual-transformers-token-based-image","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","date":"2020-06-05","arxiv_id":"2006.03677","n_code_links":8,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":null}},{"paper":null,"slug":"end-to-end-speech-translation-with-knowledge-1","title":"End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020","date":"2020-06-04","arxiv_id":"2006.02965","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-text-summarization-of-covid-19","slug":"automatic-text-summarization-of-covid-19","title":"Automatic Text Summarization of COVID-19 Medical Research Articles using BERT and GPT-2","date":"2020-06-03","arxiv_id":"2006.01997","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-predictive-power-of-neural-language","slug":"on-the-predictive-power-of-neural-language","title":"On the Predictive Power of Neural Language Models for Human Real-Time Comprehension Behavior","date":"2020-06-02","arxiv_id":"2006.01912","n_code_links":1,"syntology":null},{"paper":"/paper/subjective-question-answering-deciphering-the","slug":"subjective-question-answering-deciphering-the","title":"Subjective Question Answering: Deciphering the inner workings of Transformers in the realm of subjectivity","date":"2020-06-02","arxiv_id":"2006.08342","n_code_links":1,"syntology":null},{"paper":"/paper/adahessian-an-adaptive-second-order-optimizer","slug":"adahessian-an-adaptive-second-order-optimizer","title":"ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning","date":"2020-06-01","arxiv_id":"2006.00719","n_code_links":4,"syntology":{"ran":5,"of":11,"n_ran_checked":4,"n_instrument":1,"unverified":6,"pointer_only":1,"phrase":"5 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; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["amirgholami/adahessian"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"approche-de-g-en-eration-de-r-eponse-a-base","title":"Approche de g\\'en\\'eration de r\\'eponse \\`a base de transformers (Transformer based approach for answer generation)","date":"2020-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/context-based-transformer-models-for-answer","slug":"context-based-transformer-models-for-answer","title":"Context-based Transformer Models for Answer Sentence Selection","date":"2020-06-01","arxiv_id":"2006.01285","n_code_links":1,"syntology":null},{"paper":"/paper/emergence-of-separable-manifolds-in-deep","slug":"emergence-of-separable-manifolds-in-deep","title":"Emergence of Separable Manifolds in Deep Language Representations","date":"2020-06-01","arxiv_id":"2006.01095","n_code_links":1,"syntology":null},{"paper":null,"slug":"few-shot-learning-of-part-specific","title":"Few-Shot Learning of Part-Specific Probability Space for 3D Shape Segmentation","date":"2020-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/image-search-with-text-feedback-by","slug":"image-search-with-text-feedback-by","title":"Image Search With Text Feedback by Visiolinguistic Attention Learning","date":"2020-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-architecture-search-with-reinforce-and","title":"Hyperparameter optimization with REINFORCE and Transformers","date":"2020-06-01","arxiv_id":"2006.00939","n_code_links":0,"syntology":null},{"paper":"/paper/online-versus-offline-nmt-quality-an-in-depth","slug":"online-versus-offline-nmt-quality-an-in-depth","title":"Online Versus Offline NMT Quality: An In-depth Analysis on English-German and German-English","date":"2020-06-01","arxiv_id":"2006.00814","n_code_links":1,"syntology":null},{"paper":null,"slug":"rdcface-radial-distortion-correction-for-face","title":"RDCFace: Radial Distortion Correction for Face Recognition","date":"2020-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-sparse-view-backprojection-via","title":"Unsupervised Sparse-view Backprojection via Convolutional and Spatial Transformer Networks","date":"2020-06-01","arxiv_id":"2006.01658","n_code_links":0,"syntology":null},{"paper":null,"slug":"bpgc-at-semeval-2020-task-11-propaganda","title":"BPGC at SemEval-2020 Task 11: Propaganda Detection in News Articles with Multi-Granularity Knowledge Sharing and Linguistic Features based Ensemble Learning","date":"2020-05-31","arxiv_id":"2006.00593","n_code_links":0,"syntology":null},{"paper":null,"slug":"cnrl-at-semeval-2020-task-5-modelling-causal","title":"CNRL at SemEval-2020 Task 5: Modelling Causal Reasoning in Language with Multi-Head Self-Attention Weights based Counterfactual Detection","date":"2020-05-31","arxiv_id":"2006.00609","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-lexical-substitution","title":"A Comparative Study of Lexical Substitution Approaches based on Neural Language Models","date":"2020-05-29","arxiv_id":"2006.00031","n_code_links":0,"syntology":null},{"paper":null,"slug":"first-neural-conjecturing-datasets-and","title":"First Neural Conjecturing Datasets and Experiments","date":"2020-05-29","arxiv_id":"2005.14664","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-pretrained-language-models-for","title":"Using Large Pretrained Language Models for Answering User Queries from Product Specifications","date":"2020-05-29","arxiv_id":"2005.14613","n_code_links":0,"syntology":null},{"paper":"/paper/empirical-evaluation-of-pretraining","slug":"empirical-evaluation-of-pretraining","title":"Empirical Evaluation of Pretraining Strategies for Supervised Entity Linking","date":"2020-05-28","arxiv_id":"2005.14253","n_code_links":0,"syntology":null},{"paper":"/paper/hat-hardware-aware-transformers-for-efficient","slug":"hat-hardware-aware-transformers-for-efficient","title":"HAT: Hardware-Aware Transformers for Efficient Natural Language Processing","date":"2020-05-28","arxiv_id":"2005.14187","n_code_links":4,"syntology":null},{"paper":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","n_code_links":67,"syntology":{"ran":45,"of":65,"n_ran_checked":40,"n_instrument":5,"unverified":20,"pointer_only":7,"phrase":"45 ran (of which 0 constructed an object rather than computing a result; 40 with no instrument failure: 2 honoured, 1 violated, 37 with no contract checked; 5 where Syntology's instrument failed) · 20 unverified","official":{"repos":["openai/gpt-3"],"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":"variational-neural-machine-translation-with","title":"Variational Neural Machine Translation with Normalizing Flows","date":"2020-05-28","arxiv_id":"2005.13978","n_code_links":0,"syntology":null},{"paper":"/paper/general-purpose-user-embeddings-based-on","slug":"general-purpose-user-embeddings-based-on","title":"General-Purpose User Embeddings based on Mobile App Usage","date":"2020-05-27","arxiv_id":"2005.13303","n_code_links":1,"syntology":null},{"paper":"/paper/pai-conv-permutable-anisotropic-convolutional","slug":"pai-conv-permutable-anisotropic-convolutional","title":"Permutation Matters: Anisotropic Convolutional Layer for Learning on Point Clouds","date":"2020-05-27","arxiv_id":"2005.13135","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-object-detection-with-transformers","slug":"end-to-end-object-detection-with-transformers","title":"End-to-End Object Detection with Transformers","date":"2020-05-26","arxiv_id":"2005.12872","n_code_links":37,"syntology":{"ran":70,"of":92,"n_ran_checked":62,"n_instrument":8,"unverified":22,"pointer_only":19,"phrase":"70 ran (of which 45 constructed an object rather than computing a result; 62 with no instrument failure: 2 honoured, 1 violated, 59 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified","official":{"repos":["facebookresearch/detr"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/gector-grammatical-error-correction-tag-not","slug":"gector-grammatical-error-correction-tag-not","title":"GECToR -- Grammatical Error Correction: Tag, Not Rewrite","date":"2020-05-26","arxiv_id":"2005.12592","n_code_links":3,"syntology":{"ran":10,"of":12,"n_ran_checked":9,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["grammarly/gector"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"guiding-symbolic-natural-language-grammar","title":"Guiding Symbolic Natural Language Grammar Induction via Transformer-Based Sequence Probabilities","date":"2020-05-26","arxiv_id":"2005.12533","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-models-for-automatic","title":"Deep Learning Models for Automatic Summarization","date":"2020-05-25","arxiv_id":"2005.11988","n_code_links":0,"syntology":null},{"paper":"/paper/the-unreasonable-volatility-of-neural-machine","slug":"the-unreasonable-volatility-of-neural-machine","title":"The Unreasonable Volatility of Neural Machine Translation Models","date":"2020-05-25","arxiv_id":"2005.12398","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-nli-for-factual-correctness-in","title":"Adversarial NLI for Factual Correctness in Text Summarisation Models","date":"2020-05-24","arxiv_id":"2005.11739","n_code_links":0,"syntology":null},{"paper":"/paper/stronger-baselines-for-grammatical-error","slug":"stronger-baselines-for-grammatical-error","title":"Stronger Baselines for Grammatical Error Correction Using Pretrained Encoder-Decoder Model","date":"2020-05-24","arxiv_id":"2005.11849","n_code_links":2,"syntology":null},{"paper":null,"slug":"devising-malware-characterstics-using","title":"Devising Malware Characterstics using Transformers","date":"2020-05-23","arxiv_id":"2005.12978","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-generative-approach-to-titling-and","title":"A Generative Approach to Titling and Clustering Wikipedia Sections","date":"2020-05-22","arxiv_id":"2005.11216","n_code_links":0,"syntology":null},{"paper":null,"slug":"character-level-transformer-based-neural","title":"Character-level Transformer-based Neural Machine Translation","date":"2020-05-22","arxiv_id":"2005.11239","n_code_links":0,"syntology":null},{"paper":"/paper/low-latency-sequence-to-sequence-speech","slug":"low-latency-sequence-to-sequence-speech","title":"Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection","date":"2020-05-22","arxiv_id":"2005.11185","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dannigt/NMTGMinor.lowLatency"],"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":["official"]}}},{"paper":"/paper/retrieval-augmented-generation-for-knowledge","slug":"retrieval-augmented-generation-for-knowledge","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","date":"2020-05-22","arxiv_id":"2005.11401","n_code_links":18,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"transformer-based-context-aware-sarcasm","title":"Transformer-based Context-aware Sarcasm Detection in Conversation Threads from Social Media","date":"2020-05-22","arxiv_id":"2005.11424","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-text-data-using-hybrid-transformer","title":"Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning","date":"2020-05-21","arxiv_id":"2005.10407","n_code_links":0,"syntology":null},{"paper":null,"slug":"simplified-self-attention-for-transformer","title":"Simplified Self-Attention for Transformer-based End-to-End Speech Recognition","date":"2020-05-21","arxiv_id":"2005.10463","n_code_links":0,"syntology":null},{"paper":"/paper/text-to-text-pre-training-for-data-to-text","slug":"text-to-text-pre-training-for-data-to-text","title":"Text-to-Text Pre-Training for Data-to-Text Tasks","date":"2020-05-21","arxiv_id":"2005.10433","n_code_links":2,"syntology":null},{"paper":"/paper/a-further-study-of-unsupervised-pre-training","slug":"a-further-study-of-unsupervised-pre-training","title":"A Further Study of Unsupervised Pre-training for Transformer Based Speech Recognition","date":"2020-05-20","arxiv_id":"2005.09862","n_code_links":1,"syntology":null},{"paper":"/paper/applying-the-transformer-to-character-level","slug":"applying-the-transformer-to-character-level","title":"Applying the Transformer to Character-level Transduction","date":"2020-05-20","arxiv_id":"2005.10213","n_code_links":3,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"4 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["shijie-wu/neural-transducer"],"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/creative-artificial-intelligence-algorithms","slug":"creative-artificial-intelligence-algorithms","title":"Artificial Intelligence versus Maya Angelou: Experimental evidence that people cannot differentiate AI-generated from human-written poetry","date":"2020-05-20","arxiv_id":"2005.09980","n_code_links":1,"syntology":null},{"paper":null,"slug":"relative-positional-encoding-for-speech","title":"Relative Positional Encoding for Speech Recognition and Direct Translation","date":"2020-05-20","arxiv_id":"2005.09940","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-performance-estimation-in-neural","slug":"rethinking-performance-estimation-in-neural","title":"Rethinking Performance Estimation in Neural Architecture Search","date":"2020-05-20","arxiv_id":"2005.09917","n_code_links":1,"syntology":null},{"paper":"/paper/comparing-transformers-and-rnns-on-predicting","slug":"comparing-transformers-and-rnns-on-predicting","title":"Human Sentence Processing: Recurrence or Attention?","date":"2020-05-19","arxiv_id":"2005.09471","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-transformers-for-large-scale-speech","title":"Exploring Transformers for Large-Scale Speech Recognition","date":"2020-05-19","arxiv_id":"2005.09684","n_code_links":0,"syntology":null},{"paper":"/paper/investigations-on-phoneme-based-end-to-end","slug":"investigations-on-phoneme-based-end-to-end","title":"A systematic comparison of grapheme-based vs. phoneme-based label units for encoder-decoder-attention models","date":"2020-05-19","arxiv_id":"2005.09336","n_code_links":1,"syntology":null},{"paper":"/paper/should-we-hard-code-the-recurrence-concept-or","slug":"should-we-hard-code-the-recurrence-concept-or","title":"Should we hard-code the recurrence concept or learn it instead ? Exploring the Transformer architecture for Audio-Visual Speech Recognition","date":"2020-05-19","arxiv_id":"2005.09297","n_code_links":1,"syntology":null},{"paper":"/paper/sketch-bert-learning-sketch-bidirectional","slug":"sketch-bert-learning-sketch-bidirectional","title":"Sketch-BERT: Learning Sketch Bidirectional Encoder Representation from Transformers by Self-supervised Learning of Sketch Gestalt","date":"2020-05-19","arxiv_id":"2005.09159","n_code_links":1,"syntology":null}],"record_sha256":"b06895223ca378deb04f91eb215ceb0e3b6097e98d76a9b8112d0e65358f7ef9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}