{"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/label-smoothing/papers/131","list_of":"/method/label-smoothing","method":"Label Smoothing","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":131,"pages_in_order":144,"rows_per_page":100,"rows":[13001,13100],"of":14327,"counts":{"archive_papers_tagged":14327,"with_a_code_link":6651,"where_syntology_ran_a_sample":2259,"not_listed_spam_title":0,"listed":14327,"listed_where_code_ran":2259,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1920,"every_run_a_failure_of_syntologys_instrument":339,"listed_with_a_run_with_no_instrument_failure":1920,"listed_every_run_a_failure_of_syntologys_instrument":339,"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/label-smoothing","prev":"/method/label-smoothing/papers/130","next":"/method/label-smoothing/papers/132","papers":[{"paper":"/paper/rethinking-attention-with-performers","slug":"rethinking-attention-with-performers","title":"Rethinking Attention with Performers","date":"2020-09-30","arxiv_id":"2009.14794","n_code_links":7,"syntology":{"ran":11,"of":16,"n_ran_checked":7,"n_instrument":4,"unverified":5,"pointer_only":6,"phrase":"11 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","official":{"repos":["google-research/google-research"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":"/paper/a-simple-but-tough-to-beat-data-augmentation","slug":"a-simple-but-tough-to-beat-data-augmentation","title":"A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation","date":"2020-09-29","arxiv_id":"2009.13818","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dinghanshen/Cutoff"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"attention-that-does-not-explain-away","title":"Attention that does not Explain Away","date":"2020-09-29","arxiv_id":"2009.14308","n_code_links":0,"syntology":null},{"paper":null,"slug":"gender-prediction-using-limited-twitter-data","title":"Gender prediction using limited Twitter Data","date":"2020-09-29","arxiv_id":"2010.02005","n_code_links":0,"syntology":null},{"paper":"/paper/sequence-to-sequence-learning-for-indonesian","slug":"sequence-to-sequence-learning-for-indonesian","title":"Sequence-to-Sequence Learning for Indonesian Automatic Question Generator","date":"2020-09-29","arxiv_id":"2009.13889","n_code_links":1,"syntology":null},{"paper":"/paper/deep-transformers-with-latent-depth","slug":"deep-transformers-with-latent-depth","title":"Deep Transformers with Latent Depth","date":"2020-09-28","arxiv_id":"2009.13102","n_code_links":1,"syntology":null},{"paper":"/paper/detecting-soccer-balls-with-reduced-neural","slug":"detecting-soccer-balls-with-reduced-neural","title":"Detecting soccer balls with reduced neural networks: a comparison of multiple architectures under constrained hardware scenarios","date":"2020-09-28","arxiv_id":"2009.13684","n_code_links":1,"syntology":null},{"paper":"/paper/vivo-surpassing-human-performance-in-novel","slug":"vivo-surpassing-human-performance-in-novel","title":"VIVO: Visual Vocabulary Pre-Training for Novel Object Captioning","date":"2020-09-28","arxiv_id":"2009.13682","n_code_links":0,"syntology":null},{"paper":"/paper/a-little-goes-a-long-way-improving-toxic","slug":"a-little-goes-a-long-way-improving-toxic","title":"A little goes a long way: Improving toxic language classification despite data scarcity","date":"2020-09-25","arxiv_id":"2009.12344","n_code_links":1,"syntology":null},{"paper":null,"slug":"hamming-ocr-a-locality-sensitive-hashing","title":"Hamming OCR: A Locality Sensitive Hashing Neural Network for Scene Text Recognition","date":"2020-09-23","arxiv_id":"2009.10874","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-pass-transformer-for-machine","title":"Multi-Pass Transformer for Machine Translation","date":"2020-09-23","arxiv_id":"2009.11382","n_code_links":0,"syntology":null},{"paper":"/paper/seq2edits-sequence-transduction-using-span","slug":"seq2edits-sequence-transduction-using-span","title":"Seq2Edits: Sequence Transduction Using Span-level Edit Operations","date":"2020-09-23","arxiv_id":"2009.11136","n_code_links":1,"syntology":null},{"paper":"/paper/alleviating-the-inequality-of-attention-heads","slug":"alleviating-the-inequality-of-attention-heads","title":"Alleviating the Inequality of Attention Heads for Neural Machine Translation","date":"2020-09-21","arxiv_id":"2009.09672","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-acoustic-events-using-convolutional","title":"Detecting Sound Events Using Convolutional Macaron Net With Pseudo Strong Labels","date":"2020-09-21","arxiv_id":"2009.09632","n_code_links":0,"syntology":null},{"paper":"/paper/empathetic-dialogue-generation-via-knowledge","slug":"empathetic-dialogue-generation-via-knowledge","title":"Knowledge Bridging for Empathetic Dialogue Generation","date":"2020-09-21","arxiv_id":"2009.09708","n_code_links":1,"syntology":null},{"paper":"/paper/conditionally-adaptive-multi-task-learning","slug":"conditionally-adaptive-multi-task-learning","title":"Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data","date":"2020-09-19","arxiv_id":"2009.09139","n_code_links":1,"syntology":null},{"paper":"/paper/towards-computational-linguistics-in","slug":"towards-computational-linguistics-in","title":"Towards Computational Linguistics in Minangkabau Language: Studies on Sentiment Analysis and Machine Translation","date":"2020-09-19","arxiv_id":"2009.09309","n_code_links":1,"syntology":null},{"paper":null,"slug":"hardware-accelerator-for-multi-head-attention","title":"Hardware Accelerator for Multi-Head Attention and Position-Wise Feed-Forward in the Transformer","date":"2020-09-18","arxiv_id":"2009.08605","n_code_links":0,"syntology":null},{"paper":"/paper/distilled-one-shot-federated-learning","slug":"distilled-one-shot-federated-learning","title":"Distilled One-Shot Federated Learning","date":"2020-09-17","arxiv_id":"2009.07999","n_code_links":1,"syntology":null},{"paper":"/paper/graphcodebert-pre-training-code","slug":"graphcodebert-pre-training-code","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","date":"2020-09-17","arxiv_id":"2009.08366","n_code_links":1,"syntology":null},{"paper":null,"slug":"label-smoothing-and-adversarial-robustness","title":"Label Smoothing and Adversarial Robustness","date":"2020-09-17","arxiv_id":"2009.08233","n_code_links":0,"syntology":null},{"paper":"/paper/multi-2oie-multilingual-open-information","slug":"multi-2oie-multilingual-open-information","title":"Multi$^2$OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT","date":"2020-09-17","arxiv_id":"2009.08128","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":2,"n_instrument":4,"unverified":1,"pointer_only":0,"phrase":"6 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; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["youngbin-ro/Multi2OIE"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-fully-8-bit-integer-inference-for-the","title":"Towards Fully 8-bit Integer Inference for the Transformer Model","date":"2020-09-17","arxiv_id":"2009.08034","n_code_links":0,"syntology":null},{"paper":"/paper/automated-source-code-generation-and-auto","slug":"automated-source-code-generation-and-auto","title":"Automated Source Code Generation and Auto-completion Using Deep Learning: Comparing and Discussing Current Language-Model-Related Approaches","date":"2020-09-16","arxiv_id":"2009.07740","n_code_links":1,"syntology":null},{"paper":"/paper/cogtree-cognition-tree-loss-for-unbiased","slug":"cogtree-cognition-tree-loss-for-unbiased","title":"CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation","date":"2020-09-16","arxiv_id":"2009.07526","n_code_links":1,"syntology":null},{"paper":null,"slug":"document-level-neural-machine-translation-1","title":"Document-level Neural Machine Translation with Document Embeddings","date":"2020-09-16","arxiv_id":"2009.08775","n_code_links":0,"syntology":null},{"paper":null,"slug":"extremely-low-bit-transformer-quantization","title":"Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation","date":"2020-09-16","arxiv_id":"2009.07453","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-to-sequence-neural-machine-translation","title":"Graph-to-Sequence Neural Machine Translation","date":"2020-09-16","arxiv_id":"2009.07489","n_code_links":0,"syntology":null},{"paper":null,"slug":"nabu-multilingual-graph-based-neural-rdf","title":"NABU $\\mathrm{-}$ Multilingual Graph-based Neural RDF Verbalizer","date":"2020-09-16","arxiv_id":"2009.07728","n_code_links":0,"syntology":null},{"paper":"/paper/rcnn-for-region-of-interest-detection-in","slug":"rcnn-for-region-of-interest-detection-in","title":"RCNN for Region of Interest Detection in Whole Slide Images","date":"2020-09-16","arxiv_id":"2009.07532","n_code_links":1,"syntology":null},{"paper":null,"slug":"retrofitting-structure-aware-transformer","title":"Retrofitting Structure-aware Transformer Language Model for End Tasks","date":"2020-09-16","arxiv_id":"2009.07408","n_code_links":0,"syntology":null},{"paper":"/paper/attention-aware-inference-for-neural","slug":"attention-aware-inference-for-neural","title":"Global-aware Beam Search for Neural Abstractive Summarization","date":"2020-09-15","arxiv_id":"2009.06891","n_code_links":2,"syntology":null},{"paper":null,"slug":"event-presence-prediction-helps-trigger","title":"Event Presence Prediction Helps Trigger Detection Across Languages","date":"2020-09-15","arxiv_id":"2009.07188","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-label-smoothing","title":"Adaptive Label Smoothing","date":"2020-09-14","arxiv_id":"2009.06432","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-transformers-a-survey","title":"Efficient Transformers: A Survey","date":"2020-09-14","arxiv_id":"2009.06732","n_code_links":0,"syntology":null},{"paper":null,"slug":"boostingbert-integrating-multi-class-boosting","title":"BoostingBERT:Integrating Multi-Class Boosting into BERT for NLP Tasks","date":"2020-09-13","arxiv_id":"2009.05959","n_code_links":0,"syntology":null},{"paper":"/paper/yolobile-real-time-object-detection-on-mobile","slug":"yolobile-real-time-object-detection-on-mobile","title":"YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design","date":"2020-09-12","arxiv_id":"2009.05697","n_code_links":3,"syntology":null},{"paper":null,"slug":"extending-label-smoothing-regularization-with","title":"Extending Label Smoothing Regularization with Self-Knowledge Distillation","date":"2020-09-11","arxiv_id":"2009.05226","n_code_links":0,"syntology":null},{"paper":"/paper/gtea-representation-learning-for-temporal","slug":"gtea-representation-learning-for-temporal","title":"GTEA: Inductive Representation Learning on Temporal Interaction Graphs via Temporal Edge Aggregation","date":"2020-09-11","arxiv_id":"2009.05266","n_code_links":2,"syntology":null},{"paper":null,"slug":"learning-universal-representations-from-word","title":"Learning Universal Representations from Word to Sentence","date":"2020-09-10","arxiv_id":"2009.04656","n_code_links":0,"syntology":null},{"paper":"/paper/rank-over-class-the-untapped-potential-of","slug":"rank-over-class-the-untapped-potential-of","title":"Rank over Class: The Untapped Potential of Ranking in Natural Language Processing","date":"2020-09-10","arxiv_id":"2009.05160","n_code_links":1,"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":["atapour/rank-over-class"],"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/sparsifying-transformer-models-with","slug":"sparsifying-transformer-models-with","title":"Sparsifying Transformer Models with Trainable Representation Pooling","date":"2020-09-10","arxiv_id":"2009.05169","n_code_links":1,"syntology":null},{"paper":"/paper/pay-attention-when-required","slug":"pay-attention-when-required","title":"Pay Attention when Required","date":"2020-09-09","arxiv_id":"2009.04534","n_code_links":2,"syntology":null},{"paper":"/paper/masked-label-prediction-unified-massage","slug":"masked-label-prediction-unified-massage","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","date":"2020-09-08","arxiv_id":"2009.03509","n_code_links":3,"syntology":{"ran":7,"of":7,"n_ran_checked":6,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"7 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["PaddlePaddle/PGL"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"tanhsoft-a-family-of-activation-functions","title":"TanhSoft -- a family of activation functions combining Tanh and Softplus","date":"2020-09-08","arxiv_id":"2009.03863","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-watermarking-transformer-towards","slug":"adversarial-watermarking-transformer-towards","title":"Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding","date":"2020-09-07","arxiv_id":"2009.03015","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":null}},{"paper":null,"slug":"robust-conversational-ai-with-grounded-text","title":"Robust Conversational AI with Grounded Text Generation","date":"2020-09-07","arxiv_id":"2009.03457","n_code_links":0,"syntology":null},{"paper":"/paper/transmodality-an-end2end-fusion-method-with","slug":"transmodality-an-end2end-fusion-method-with","title":"TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis","date":"2020-09-07","arxiv_id":"2009.02902","n_code_links":0,"syntology":null},{"paper":null,"slug":"class-interference-regularization","title":"Class Interference Regularization","date":"2020-09-04","arxiv_id":"2009.02396","n_code_links":0,"syntology":null},{"paper":null,"slug":"voice-conversion-by-cascading-automatic","title":"Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody Transfer","date":"2020-09-03","arxiv_id":"2009.01475","n_code_links":0,"syntology":null},{"paper":"/paper/liftformer-3d-human-pose-estimation-using","slug":"liftformer-3d-human-pose-estimation-using","title":"LiftFormer: 3D Human Pose Estimation using attention models","date":"2020-09-01","arxiv_id":"2009.00348","n_code_links":0,"syntology":null},{"paper":null,"slug":"parallel-rescoring-with-transformer-for","title":"Parallel Rescoring with Transformer for Streaming On-Device Speech Recognition","date":"2020-08-30","arxiv_id":"2008.13093","n_code_links":0,"syntology":null},{"paper":"/paper/hitter-hierarchical-transformers-for","slug":"hitter-hierarchical-transformers-for","title":"HittER: Hierarchical Transformers for Knowledge Graph Embeddings","date":"2020-08-28","arxiv_id":"2008.12813","n_code_links":3,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":null}},{"paper":null,"slug":"tatl-at-w-nut-2020-task-2-a-transformer-based","title":"TATL at W-NUT 2020 Task 2: A Transformer-based Baseline System for Identification of Informative COVID-19 English Tweets","date":"2020-08-28","arxiv_id":"2008.12854","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-conditioned-transformer-for-automatic","title":"Text-Conditioned Transformer for Automatic Pronunciation Error Detection","date":"2020-08-28","arxiv_id":"2008.12424","n_code_links":0,"syntology":null},{"paper":"/paper/improvement-of-a-dedicated-model-for-open","slug":"improvement-of-a-dedicated-model-for-open","title":"Improvement of a dedicated model for open domain persona-aware dialogue generation","date":"2020-08-27","arxiv_id":"2008.11970","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-dialogue-transformer","title":"End to End Dialogue Transformer","date":"2020-08-24","arxiv_id":"2008.10392","n_code_links":0,"syntology":null},{"paper":"/paper/identity-aware-multi-sentence-video","slug":"identity-aware-multi-sentence-video","title":"Identity-Aware Multi-Sentence Video Description","date":"2020-08-22","arxiv_id":"2008.09791","n_code_links":1,"syntology":null},{"paper":"/paper/are-neural-open-domain-dialog-systems-robust","slug":"are-neural-open-domain-dialog-systems-robust","title":"Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study","date":"2020-08-18","arxiv_id":"2008.07683","n_code_links":1,"syntology":null},{"paper":"/paper/glancing-transformer-for-non-autoregressive","slug":"glancing-transformer-for-non-autoregressive","title":"Glancing Transformer for Non-Autoregressive Neural Machine Translation","date":"2020-08-18","arxiv_id":"2008.07905","n_code_links":2,"syntology":null},{"paper":"/paper/very-deep-transformers-for-neural-machine","slug":"very-deep-transformers-for-neural-machine","title":"Very Deep Transformers for Neural Machine Translation","date":"2020-08-18","arxiv_id":"2008.07772","n_code_links":4,"syntology":{"ran":8,"of":9,"n_ran_checked":3,"n_instrument":5,"unverified":1,"pointer_only":3,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["namisan/exdeep-nmt"],"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/spatial-temporal-transformer-network-for","slug":"spatial-temporal-transformer-network-for","title":"Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks","date":"2020-08-17","arxiv_id":"2008.07404","n_code_links":1,"syntology":null},{"paper":null,"slug":"dcr-net-a-deep-co-interactive-relation","title":"DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification","date":"2020-08-16","arxiv_id":"2008.06914","n_code_links":0,"syntology":null},{"paper":null,"slug":"topicbert-a-transformer-transfer-learning","title":"TopicBERT: A Transformer transfer learning based memory-graph approach for multimodal streaming social media topic detection","date":"2020-08-16","arxiv_id":"2008.06877","n_code_links":0,"syntology":null},{"paper":null,"slug":"finding-fast-transformers-one-shot-neural","title":"Finding Fast Transformers: One-Shot Neural Architecture Search by Component Composition","date":"2020-08-15","arxiv_id":"2008.06808","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hybrid-bert-and-lightgbm-based-model-for","title":"A Hybrid BERT and LightGBM based Model for Predicting Emotion GIF Categories on Twitter","date":"2020-08-14","arxiv_id":"2008.06176","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptable-multi-domain-language-model-for","title":"Adaptable Multi-Domain Language Model for Transformer ASR","date":"2020-08-14","arxiv_id":"2008.06208","n_code_links":0,"syntology":null},{"paper":"/paper/a-community-powered-search-of-machine","slug":"a-community-powered-search-of-machine","title":"A community-powered search of machine learning strategy space to find NMR property prediction models","date":"2020-08-13","arxiv_id":"2008.05994","n_code_links":1,"syntology":null},{"paper":null,"slug":"conv-transformer-transducer-low-latency-low","title":"Conv-Transformer Transducer: Low Latency, Low Frame Rate, Streamable End-to-End Speech Recognition","date":"2020-08-13","arxiv_id":"2008.05750","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-contextual-perception-and","title":"End-to-end Contextual Perception and Prediction with Interaction Transformer","date":"2020-08-13","arxiv_id":"2008.05927","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-scale-transfer-learning-for-low","title":"Large-scale Transfer Learning for Low-resource Spoken Language Understanding","date":"2020-08-13","arxiv_id":"2008.05671","n_code_links":0,"syntology":null},{"paper":"/paper/mmm-exploring-conditional-multi-track-music","slug":"mmm-exploring-conditional-multi-track-music","title":"MMM : Exploring Conditional Multi-Track Music Generation with the Transformer","date":"2020-08-13","arxiv_id":"2008.06048","n_code_links":3,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":null}},{"paper":null,"slug":"compression-of-deep-learning-models-for-text","title":"Compression of Deep Learning Models for Text: A Survey","date":"2020-08-12","arxiv_id":"2008.05221","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-impact-of-knowledge-graph","slug":"evaluating-the-impact-of-knowledge-graph","title":"Evaluating the Impact of Knowledge Graph Context on Entity Disambiguation Models","date":"2020-08-12","arxiv_id":"2008.05190","n_code_links":1,"syntology":null},{"paper":"/paper/fine-grained-visual-textual-alignment-for","slug":"fine-grained-visual-textual-alignment-for","title":"Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders","date":"2020-08-12","arxiv_id":"2008.05231","n_code_links":1,"syntology":{"ran":14,"of":16,"n_ran_checked":13,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["mesnico/TERAN"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"forming-local-intersections-of-projections","title":"Forming Local Intersections of Projections for Classifying and Searching Histopathology Images","date":"2020-08-08","arxiv_id":"2008.03553","n_code_links":0,"syntology":null},{"paper":"/paper/pretraining-techniques-for-sequence-to","slug":"pretraining-techniques-for-sequence-to","title":"Pretraining Techniques for Sequence-to-Sequence Voice Conversion","date":"2020-08-07","arxiv_id":"2008.03088","n_code_links":2,"syntology":null},{"paper":null,"slug":"6veclm-language-modeling-in-vector-space-for","title":"6VecLM: Language Modeling in Vector Space for IPv6 Target Generation","date":"2020-08-05","arxiv_id":"2008.02213","n_code_links":0,"syntology":null},{"paper":"/paper/designing-the-business-conversation-corpus-1","slug":"designing-the-business-conversation-corpus-1","title":"Designing the Business Conversation Corpus","date":"2020-08-05","arxiv_id":"2008.01940","n_code_links":1,"syntology":null},{"paper":null,"slug":"select-extract-and-generate-neural-keyphrase","title":"Select, Extract and Generate: Neural Keyphrase Generation with Layer-wise Coverage Attention","date":"2020-08-04","arxiv_id":"2008.01739","n_code_links":0,"syntology":null},{"paper":"/paper/the-jazz-transformer-on-the-front-line","slug":"the-jazz-transformer-on-the-front-line","title":"The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures","date":"2020-08-04","arxiv_id":"2008.01307","n_code_links":2,"syntology":{"ran":13,"of":14,"n_ran_checked":13,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["slSeanWU/MusDr","slSeanWU/jazz_transformer"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/delight-very-deep-and-light-weight","slug":"delight-very-deep-and-light-weight","title":"DeLighT: Deep and Light-weight Transformer","date":"2020-08-03","arxiv_id":"2008.00623","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["sacmehta/delight"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lt-helsinki-at-semeval-2020-task-12","title":"LT@Helsinki at SemEval-2020 Task 12: Multilingual or language-specific BERT?","date":"2020-08-03","arxiv_id":"2008.00805","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-attention-encoding-and-pooling-for","title":"Self-attention encoding and pooling for speaker recognition","date":"2020-08-03","arxiv_id":"2008.01077","n_code_links":0,"syntology":null},{"paper":"/paper/seqdialn-sequential-visual-dialog-networks-in","slug":"seqdialn-sequential-visual-dialog-networks-in","title":"SeqDialN: Sequential Visual Dialog Networks in Joint Visual-Linguistic Representation Space","date":"2020-08-02","arxiv_id":"2008.00397","n_code_links":1,"syntology":null},{"paper":"/paper/the-chess-transformer-mastering-play-using","slug":"the-chess-transformer-mastering-play-using","title":"The Chess Transformer: Mastering Play using Generative Language Models","date":"2020-08-02","arxiv_id":"2008.04057","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":null}},{"paper":null,"slug":"object-detection-and-tracking-algorithms-for","title":"Object Detection and Tracking Algorithms for Vehicle Counting: A Comparative Analysis","date":"2020-07-31","arxiv_id":"2007.16198","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-multi-view-spatiotemporal-virtual-graph","title":"Deep Multi-View Spatiotemporal Virtual Graph Neural Network for Significant Citywide Ride-hailing Demand Prediction","date":"2020-07-30","arxiv_id":"2007.15189","n_code_links":0,"syntology":null},{"paper":"/paper/interpretable-contextual-team-aware-item","slug":"interpretable-contextual-team-aware-item","title":"Interpretable Contextual Team-aware Item Recommendation: Application in Multiplayer Online Battle Arena Games","date":"2020-07-30","arxiv_id":"2007.15236","n_code_links":1,"syntology":null},{"paper":null,"slug":"tensorcoder-dimension-wise-attention-via","title":"TensorCoder: Dimension-Wise Attention via Tensor Representation for Natural Language Modeling","date":"2020-07-28","arxiv_id":"2008.01547","n_code_links":0,"syntology":null},{"paper":null,"slug":"to-bert-or-not-to-bert-comparing-speech-and","title":"To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer's Disease Detection","date":"2020-07-26","arxiv_id":"2008.01551","n_code_links":0,"syntology":null},{"paper":"/paper/fissa-at-semeval-2020-task-9-fine-tuned-for","slug":"fissa-at-semeval-2020-task-9-fine-tuned-for","title":"FiSSA at SemEval-2020 Task 9: Fine-tuned For Feelings","date":"2020-07-24","arxiv_id":"2007.12544","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-swedish-english-fasttext-embeddings","slug":"exploring-swedish-english-fasttext-embeddings","title":"Exploring Swedish & English fastText Embeddings for NER with the Transformer","date":"2020-07-23","arxiv_id":"2007.16007","n_code_links":1,"syntology":null},{"paper":"/paper/pp-yolo-an-effective-and-efficient","slug":"pp-yolo-an-effective-and-efficient","title":"PP-YOLO: An Effective and Efficient Implementation of Object Detector","date":"2020-07-23","arxiv_id":"2007.12099","n_code_links":5,"syntology":null},{"paper":null,"slug":"analogical-reasoning-for-visually-grounded","title":"Analogical Reasoning for Visually Grounded Language Acquisition","date":"2020-07-22","arxiv_id":"2007.11668","n_code_links":0,"syntology":null},{"paper":"/paper/crosstransformers-spatially-aware-few-shot","slug":"crosstransformers-spatially-aware-few-shot","title":"CrossTransformers: spatially-aware few-shot transfer","date":"2020-07-22","arxiv_id":"2007.11498","n_code_links":6,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google-research/meta-dataset"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","listed"]}}},{"paper":"/paper/neural-machine-translation-with-error","slug":"neural-machine-translation-with-error","title":"Neural Machine Translation with Error Correction","date":"2020-07-21","arxiv_id":"2007.10681","n_code_links":1,"syntology":null},{"paper":null,"slug":"sliceout-training-transformers-and-cnns","title":"Improving compute efficacy frontiers with SliceOut","date":"2020-07-21","arxiv_id":"2007.10909","n_code_links":0,"syntology":null},{"paper":"/paper/unified-multisensory-perception-weakly","slug":"unified-multisensory-perception-weakly","title":"Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing","date":"2020-07-21","arxiv_id":"2007.10558","n_code_links":2,"syntology":null},{"paper":"/paper/conformer-kernel-with-query-term-independence","slug":"conformer-kernel-with-query-term-independence","title":"Conformer-Kernel with Query Term Independence for Document Retrieval","date":"2020-07-20","arxiv_id":"2007.10434","n_code_links":1,"syntology":null}],"record_sha256":"bbb0544b0463103f1ca1e31ebe650fc2cca380485433675cc85a41e358d52b7c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}