{"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/softmax/papers/324","list_of":"/method/softmax","method":"Softmax","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":324,"pages_in_order":375,"rows_per_page":100,"rows":[32301,32400],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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/softmax","prev":"/method/softmax/papers/323","next":"/method/softmax/papers/325","papers":[{"paper":null,"slug":"on-the-interplay-between-fine-tuning-and","title":"On the Interplay Between Fine-tuning and Sentence-level Probing for Linguistic Knowledge in Pre-trained Transformers","date":"2020-10-06","arxiv_id":"2010.02616","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-sub-layer-functionalities-of","title":"On the Sub-Layer Functionalities of Transformer Decoder","date":"2020-10-06","arxiv_id":"2010.02648","n_code_links":0,"syntology":null},{"paper":null,"slug":"parallax-motion-effect-generation-through","title":"Parallax Motion Effect Generation Through Instance Segmentation And Depth Estimation","date":"2020-10-06","arxiv_id":"2010.02680","n_code_links":0,"syntology":null},{"paper":"/paper/poison-attacks-against-text-datasets-with","slug":"poison-attacks-against-text-datasets-with","title":"Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder","date":"2020-10-06","arxiv_id":"2010.02684","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 1 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) · 0 unverified","official":{"repos":["alvinchangw/CARA_EMNLP2020"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/pretrained-language-model-embryology-the","slug":"pretrained-language-model-embryology-the","title":"Pretrained Language Model Embryology: The Birth of ALBERT","date":"2020-10-06","arxiv_id":"2010.02480","n_code_links":1,"syntology":null},{"paper":null,"slug":"resource-enhanced-neural-model-for-event","title":"Resource-Enhanced Neural Model for Event Argument Extraction","date":"2020-10-06","arxiv_id":"2010.03022","n_code_links":0,"syntology":null},{"paper":"/paper/scene-graph-modification-based-on-natural","slug":"scene-graph-modification-based-on-natural","title":"Scene Graph Modification Based on Natural Language Commands","date":"2020-10-06","arxiv_id":"2010.02591","n_code_links":1,"syntology":null},{"paper":"/paper/the-multilingual-amazon-reviews-corpus","slug":"the-multilingual-amazon-reviews-corpus","title":"The Multilingual Amazon Reviews Corpus","date":"2020-10-06","arxiv_id":"2010.02573","n_code_links":1,"syntology":null},{"paper":null,"slug":"vector-vector-matrix-architecture-a-novel","title":"Vector-Vector-Matrix Architecture: A Novel Hardware-Aware Framework for Low-Latency Inference in NLP Applications","date":"2020-10-06","arxiv_id":"2010.08412","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-automotive-radar-data-acquisition-1","slug":"adaptive-automotive-radar-data-acquisition-1","title":"Automotive Radar Data Acquisition using Object Detection","date":"2020-10-05","arxiv_id":"2010.02367","n_code_links":1,"syntology":null},{"paper":"/paper/d3net-densely-connected-multidilated-densenet","slug":"d3net-densely-connected-multidilated-densenet","title":"D3Net: Densely connected multidilated DenseNet for music source separation","date":"2020-10-05","arxiv_id":"2010.01733","n_code_links":1,"syntology":null},{"paper":"/paper/dct-snn-using-dct-to-distribute-spatial-1","slug":"dct-snn-using-dct-to-distribute-spatial-1","title":"DCT-SNN: Using DCT to Distribute Spatial Information over Time for Learning Low-Latency Spiking Neural Networks","date":"2020-10-05","arxiv_id":"2010.01795","n_code_links":1,"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":["SayeedChowdhury/dct-snn"],"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":"deep-reinforcement-learning-for-electric-1","title":"Deep Reinforcement Learning for Electric Vehicle Routing Problem with Time Windows","date":"2020-10-05","arxiv_id":"2010.02068","n_code_links":0,"syntology":null},{"paper":"/paper/genaug-data-augmentation-for-finetuning-text","slug":"genaug-data-augmentation-for-finetuning-text","title":"GenAug: Data Augmentation for Finetuning Text Generators","date":"2020-10-05","arxiv_id":"2010.01794","n_code_links":2,"syntology":null},{"paper":null,"slug":"how-effective-is-task-agnostic-data","title":"How Effective is Task-Agnostic Data Augmentation for Pretrained Transformers?","date":"2020-10-05","arxiv_id":"2010.01764","n_code_links":0,"syntology":null},{"paper":"/paper/improving-amr-parsing-with-sequence-to","slug":"improving-amr-parsing-with-sequence-to","title":"Improving AMR Parsing with Sequence-to-Sequence Pre-training","date":"2020-10-05","arxiv_id":"2010.01771","n_code_links":1,"syntology":null},{"paper":"/paper/infobert-improving-robustness-of-language-1","slug":"infobert-improving-robustness-of-language-1","title":"InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective","date":"2020-10-05","arxiv_id":"2010.02329","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["AI-secure/InfoBERT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"linguistic-profiling-of-a-neural-language","title":"Linguistic Profiling of a Neural Language Model","date":"2020-10-05","arxiv_id":"2010.01869","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixup-transfomer-dynamic-data-augmentation","title":"Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks","date":"2020-10-05","arxiv_id":"2010.02394","n_code_links":0,"syntology":null},{"paper":null,"slug":"pair-planning-and-iterative-refinement-in-pre","title":"PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation","date":"2020-10-05","arxiv_id":"2010.02301","n_code_links":0,"syntology":null},{"paper":"/paper/pareto-probing-trading-off-accuracy-for","slug":"pareto-probing-trading-off-accuracy-for","title":"Pareto Probing: Trading Off Accuracy for Complexity","date":"2020-10-05","arxiv_id":"2010.02180","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 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":["rycolab/pareto-probing"],"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/pmi-masking-principled-masking-of-correlated-1","slug":"pmi-masking-principled-masking-of-correlated-1","title":"PMI-Masking: Principled masking of correlated spans","date":"2020-10-05","arxiv_id":"2010.01825","n_code_links":1,"syntology":null},{"paper":"/paper/pruning-redundant-mappings-in-transformer","slug":"pruning-redundant-mappings-in-transformer","title":"Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior","date":"2020-10-05","arxiv_id":"2010.01791","n_code_links":1,"syntology":null},{"paper":null,"slug":"pum-at-semeval-2020-task-12-aggregation-of","title":"PUM at SemEval-2020 Task 12: Aggregation of Transformer-based models' features for offensive language recognition","date":"2020-10-05","arxiv_id":"2010.01897","n_code_links":0,"syntology":null},{"paper":"/paper/self-training-improves-pre-training-for","slug":"self-training-improves-pre-training-for","title":"Self-training Improves Pre-training for Natural Language Understanding","date":"2020-10-05","arxiv_id":"2010.02194","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-based-neural-text-generation-with","slug":"transformer-based-neural-text-generation-with","title":"Transformer-Based Neural Text Generation with Syntactic Guidance","date":"2020-10-05","arxiv_id":"2010.01737","n_code_links":1,"syntology":null},{"paper":"/paper/unsupervised-reference-free-summary-quality","slug":"unsupervised-reference-free-summary-quality","title":"Unsupervised Reference-Free Summary Quality Evaluation via Contrastive Learning","date":"2020-10-05","arxiv_id":"2010.01781","n_code_links":1,"syntology":null},{"paper":"/paper/x-srl-a-parallel-cross-lingual-semantic-role","slug":"x-srl-a-parallel-cross-lingual-semantic-role","title":"X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset","date":"2020-10-05","arxiv_id":"2010.01998","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-new-mask-r-cnn-based-method-for-improved","title":"A New Mask R-CNN Based Method for Improved Landslide Detection","date":"2020-10-04","arxiv_id":"2010.01499","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-on-large-scale-multi-label","slug":"an-empirical-study-on-large-scale-multi-label","title":"An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels","date":"2020-10-04","arxiv_id":"2010.01653","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"7 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["iliaschalkidis/lmtc-eurlex57k"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/inquisitive-question-generation-for-high","slug":"inquisitive-question-generation-for-high","title":"Inquisitive Question Generation for High Level Text Comprehension","date":"2020-10-04","arxiv_id":"2010.01657","n_code_links":1,"syntology":null},{"paper":"/paper/metadetect-uncertainty-quantification-and","slug":"metadetect-uncertainty-quantification-and","title":"MetaDetect: Uncertainty Quantification and Prediction Quality Estimates for Object Detection","date":"2020-10-04","arxiv_id":"2010.01695","n_code_links":1,"syntology":null},{"paper":"/paper/on-losses-for-modern-language-models","slug":"on-losses-for-modern-language-models","title":"On Losses for Modern Language Models","date":"2020-10-04","arxiv_id":"2010.01694","n_code_links":1,"syntology":null},{"paper":"/paper/tell-me-how-to-ask-again-question-data","slug":"tell-me-how-to-ask-again-question-data","title":"Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space","date":"2020-10-04","arxiv_id":"2010.01475","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-training-of-cnn-ensembles-for","title":"End-to-End Training of CNN Ensembles for Person Re-Identification","date":"2020-10-03","arxiv_id":"2010.01342","n_code_links":0,"syntology":null},{"paper":"/paper/mining-knowledge-for-natural-language","slug":"mining-knowledge-for-natural-language","title":"Mining Knowledge for Natural Language Inference from Wikipedia Categories","date":"2020-10-03","arxiv_id":"2010.01239","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ZeweiChu/WikiNLI"],"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":["official"]}}},{"paper":"/paper/nonconvex-regularization-for-network-slimming","slug":"nonconvex-regularization-for-network-slimming","title":"Improving Network Slimming with Nonconvex Regularization","date":"2020-10-03","arxiv_id":"2010.01242","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["kbui1993/NonconvexNetworkSlimming"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"personality-trait-detection-using-bagged-svm","title":"Personality Trait Detection Using Bagged SVM over BERT Word Embedding Ensembles","date":"2020-10-03","arxiv_id":"2010.01309","n_code_links":0,"syntology":null},{"paper":"/paper/autoregressive-entity-retrieval","slug":"autoregressive-entity-retrieval","title":"Autoregressive Entity Retrieval","date":"2020-10-02","arxiv_id":"2010.00904","n_code_links":2,"syntology":null},{"paper":null,"slug":"background-adaptive-faster-r-cnn-for-semi","title":"Background Adaptive Faster R-CNN for Semi-Supervised Convolutional Object Detection of Threats in X-Ray Images","date":"2020-10-02","arxiv_id":"2010.01202","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-chemical-1d-knowledge-using","title":"Beyond Chemical 1D knowledge using Transformers","date":"2020-10-02","arxiv_id":"2010.01027","n_code_links":0,"syntology":null},{"paper":"/paper/cost-effective-selection-of-pretraining-data","slug":"cost-effective-selection-of-pretraining-data","title":"Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media","date":"2020-10-02","arxiv_id":"2010.01150","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-transfer-approaches-to-improve-seq-to","title":"Data Transfer Approaches to Improve Seq-to-Seq Retrosynthesis","date":"2020-10-02","arxiv_id":"2010.00792","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-tail-zero-and-few-shot-learning-via","title":"Data-Efficient Pretraining via Contrastive Self-Supervision","date":"2020-10-02","arxiv_id":"2010.01061","n_code_links":0,"syntology":null},{"paper":"/paper/luke-deep-contextualized-entity","slug":"luke-deep-contextualized-entity","title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","date":"2020-10-02","arxiv_id":"2010.01057","n_code_links":9,"syntology":{"ran":3,"of":10,"n_ran_checked":3,"n_instrument":0,"unverified":7,"pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 7 unverified","official":{"repos":["studio-ousia/luke"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/multicqa-zero-shot-transfer-of-self","slug":"multicqa-zero-shot-transfer-of-self","title":"MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale","date":"2020-10-02","arxiv_id":"2010.00980","n_code_links":1,"syntology":null},{"paper":null,"slug":"polyphonic-piano-transcription-using","title":"Polyphonic Piano Transcription Using Autoregressive Multi-State Note Model","date":"2020-10-02","arxiv_id":"2010.01104","n_code_links":0,"syntology":null},{"paper":"/paper/stil-simultaneous-slot-filling-translation","slug":"stil-simultaneous-slot-filling-translation","title":"STIL -- Simultaneous Slot Filling, Translation, Intent Classification, and Language Identification: Initial Results using mBART on MultiATIS++","date":"2020-10-02","arxiv_id":"2010.00760","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-compare-aggregate-transformer-for","title":"A Compare Aggregate Transformer for Understanding Document-grounded Dialogue","date":"2020-10-01","arxiv_id":"2010.00190","n_code_links":0,"syntology":null},{"paper":"/paper/a-technical-question-answering-system-with","slug":"a-technical-question-answering-system-with","title":"A Technical Question Answering System with Transfer Learning","date":"2020-10-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-the-text-analysis-of-privacy","title":"Beyond The Text: Analysis of Privacy Statements through Syntactic and Semantic Role Labeling","date":"2020-10-01","arxiv_id":"2010.00678","n_code_links":0,"syntology":null},{"paper":"/paper/colake-contextualized-language-and-knowledge","slug":"colake-contextualized-language-and-knowledge","title":"CoLAKE: Contextualized Language and Knowledge Embedding","date":"2020-10-01","arxiv_id":"2010.00309","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["txsun1997/CoLAKE"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"detecting-white-supremacist-hate-speech-using","title":"Detecting White Supremacist Hate Speech using Domain Specific Word Embedding with Deep Learning and BERT","date":"2020-10-01","arxiv_id":"2010.00357","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-multilingual-bert-for-estonian","title":"Evaluating Multilingual BERT for Estonian","date":"2020-10-01","arxiv_id":"2010.00454","n_code_links":0,"syntology":null},{"paper":null,"slug":"examining-the-rhetorical-capacities-of-neural","title":"Examining the rhetorical capacities of neural language models","date":"2020-10-01","arxiv_id":"2010.00153","n_code_links":0,"syntology":null},{"paper":null,"slug":"lane-change-for-system-driven-vehicles-using","title":"Lane Change For System-Driven Vehicles Using Dynamic Information","date":"2020-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/phonemer-at-wnut-2020-task-2-sequence","slug":"phonemer-at-wnut-2020-task-2-sequence","title":"Phonemer at WNUT-2020 Task 2: Sequence Classification Using COVID Twitter BERT and Bagging Ensemble Technique based on Plurality Voting","date":"2020-10-01","arxiv_id":"2010.00294","n_code_links":1,"syntology":null},{"paper":"/paper/refvos-a-closer-look-at-referring-expressions","slug":"refvos-a-closer-look-at-referring-expressions","title":"RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation","date":"2020-10-01","arxiv_id":"2010.00263","n_code_links":2,"syntology":null},{"paper":null,"slug":"rrf102-meeting-the-trec-covid-challenge-with","title":"RRF102: Meeting the TREC-COVID Challenge with a 100+ Runs Ensemble","date":"2020-10-01","arxiv_id":"2010.00200","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-state-of-the-art-natural-1","slug":"transformers-state-of-the-art-natural-1","title":"Transformers: State-of-the-Art Natural Language Processing","date":"2020-10-01","arxiv_id":null,"n_code_links":3,"syntology":null},{"paper":"/paper/understanding-tables-with-intermediate-pre","slug":"understanding-tables-with-intermediate-pre","title":"Understanding tables with intermediate pre-training","date":"2020-10-01","arxiv_id":"2010.00571","n_code_links":1,"syntology":null},{"paper":null,"slug":"wechat-neural-machine-translation-systems-for","title":"WeChat Neural Machine Translation Systems for WMT20","date":"2020-10-01","arxiv_id":"2010.00247","n_code_links":0,"syntology":null},{"paper":"/paper/a-tale-of-two-linkings-dynamically-gating","slug":"a-tale-of-two-linkings-dynamically-gating","title":"A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing","date":"2020-09-30","arxiv_id":"2009.14809","n_code_links":1,"syntology":null},{"paper":"/paper/a-vietnamese-dataset-for-evaluating-machine","slug":"a-vietnamese-dataset-for-evaluating-machine","title":"A Vietnamese Dataset for Evaluating Machine Reading Comprehension","date":"2020-09-30","arxiv_id":"2009.14725","n_code_links":0,"syntology":null},{"paper":null,"slug":"auber-automated-bert-regularization","title":"AUBER: Automated BERT Regularization","date":"2020-09-30","arxiv_id":"2009.14409","n_code_links":0,"syntology":null},{"paper":"/paper/bert-for-monolingual-and-cross-lingual","slug":"bert-for-monolingual-and-cross-lingual","title":"BERT for Monolingual and Cross-Lingual Reverse Dictionary","date":"2020-09-30","arxiv_id":"2009.14790","n_code_links":1,"syntology":null},{"paper":"/paper/is-ai-model-interpretable-to-combat-with","slug":"is-ai-model-interpretable-to-combat-with","title":"Interpretable Machine Learning for COVID-19: An Empirical Study on Severity Prediction Task","date":"2020-09-30","arxiv_id":"2010.02006","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-hard-retrieval-cross-attention-for","title":"Learning Hard Retrieval Decoder Attention for Transformers","date":"2020-09-30","arxiv_id":"2009.14658","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-systematic-generalization-in-neural","slug":"measuring-systematic-generalization-in-neural","title":"Measuring Systematic Generalization in Neural Proof Generation with Transformers","date":"2020-09-30","arxiv_id":"2009.14786","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["NicolasAG/SGinPG"],"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":"mqtransformer-multi-horizon-forecasts-with","title":"MQTransformer: Multi-Horizon Forecasts with Context Dependent and Feedback-Aware Attention","date":"2020-09-30","arxiv_id":"2009.14799","n_code_links":0,"syntology":null},{"paper":null,"slug":"pea-kd-parameter-efficient-and-accurate","title":"Pea-KD: Parameter-efficient and Accurate Knowledge Distillation on BERT","date":"2020-09-30","arxiv_id":"2009.14822","n_code_links":0,"syntology":null},{"paper":null,"slug":"perceptual-modelling-of-unconstrained-road","title":"Perceptual Modelling of Unconstrained Road Traffic Scenarios with Deep Learning","date":"2020-09-30","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"perceptual-modelling-of-unconstrained-road-2","title":"Perceptual Modelling of Unconstrained Road Traffic Scenarios with Deep Learning","date":"2020-09-30","arxiv_id":null,"n_code_links":0,"syntology":null},{"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-driven-body-pose-encoding-for-human","title":"Attention-Driven Body Pose Encoding for Human Activity Recognition","date":"2020-09-29","arxiv_id":"2009.14326","n_code_links":0,"syntology":null},{"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":"/paper/contrastive-distillation-on-intermediate","slug":"contrastive-distillation-on-intermediate","title":"Contrastive Distillation on Intermediate Representations for Language Model Compression","date":"2020-09-29","arxiv_id":"2009.14167","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["intersun/CoDIR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cross-lingual-alignment-methods-for","title":"Cross-lingual Alignment Methods for Multilingual BERT: A Comparative Study","date":"2020-09-29","arxiv_id":"2009.14304","n_code_links":0,"syntology":null},{"paper":null,"slug":"ensembles-of-convolutional-neural-networks","title":"Ensembles of Convolutional Neural Networks models for pediatric pneumonia diagnosis","date":"2020-09-29","arxiv_id":"2010.02007","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-twitter-to-traffic-predictor-next-day","title":"From Twitter to Traffic Predictor: Next-Day Morning Traffic Prediction Using Social Media Data","date":"2020-09-29","arxiv_id":"2009.13794","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/hint3-raising-the-bar-for-intent-detection-in","slug":"hint3-raising-the-bar-for-intent-detection-in","title":"HINT3: Raising the bar for Intent Detection in the Wild","date":"2020-09-29","arxiv_id":"2009.13833","n_code_links":1,"syntology":null},{"paper":null,"slug":"map-a-matrix-based-prediction-approach-to","title":"MaP: A Matrix-based Prediction Approach to Improve Span Extraction in Machine Reading Comprehension","date":"2020-09-29","arxiv_id":"2009.14348","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-retrieval-for-question-answering-with","title":"Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation","date":"2020-09-29","arxiv_id":"2009.13815","n_code_links":0,"syntology":null},{"paper":"/paper/self-grouping-convolutional-neural-networks","slug":"self-grouping-convolutional-neural-networks","title":"Self-grouping Convolutional Neural Networks","date":"2020-09-29","arxiv_id":"2009.13803","n_code_links":1,"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":null,"slug":"test-positive-at-w-nut-2020-shared-task-3","title":"TEST_POSITIVE at W-NUT 2020 Shared Task-3: Joint Event Multi-task Learning for Slot Filling in Noisy Text","date":"2020-09-29","arxiv_id":"2009.14262","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-design-and-implementation-of-language","title":"The design and implementation of Language Learning Chatbot with XAI using Ontology and Transfer Learning","date":"2020-09-29","arxiv_id":"2009.13984","n_code_links":0,"syntology":null},{"paper":"/paper/tinygan-distilling-biggan-for-conditional","slug":"tinygan-distilling-biggan-for-conditional","title":"TinyGAN: Distilling BigGAN for Conditional Image Generation","date":"2020-09-29","arxiv_id":"2009.13829","n_code_links":1,"syntology":null},{"paper":"/paper/visually-grounded-planning-without-vision","slug":"visually-grounded-planning-without-vision","title":"Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions","date":"2020-09-29","arxiv_id":"2009.14259","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"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":["cognitiveailab/alfred-gpt2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-simple-and-efficient-ensemble-classifier","title":"A Simple and Efficient Ensemble Classifier Combining Multiple Neural Network Models on Social Media Datasets in Vietnamese","date":"2020-09-28","arxiv_id":"2009.13060","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-multi-model-inference-by-merging","title":"Accelerating Multi-Model Inference by Merging DNNs of Different Weights","date":"2020-09-28","arxiv_id":"2009.13062","n_code_links":0,"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/dialoglue-a-natural-language-understanding","slug":"dialoglue-a-natural-language-understanding","title":"DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue","date":"2020-09-28","arxiv_id":"2009.13570","n_code_links":1,"syntology":null},{"paper":null,"slug":"eis-a-family-of-activation-functions","title":"EIS -- a family of activation functions combining Exponential, ISRU, and Softplus","date":"2020-09-28","arxiv_id":"2009.13501","n_code_links":0,"syntology":null},{"paper":null,"slug":"fancy-man-lauches-zippo-at-wnut-2020-shared","title":"Fancy Man Lauches Zippo at WNUT 2020 Shared Task-1: A Bert Case Model for Wet Lab Entity Extraction","date":"2020-09-28","arxiv_id":"2009.12997","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-aware-procedural-text-understanding","title":"Knowledge-Aware Procedural Text Understanding with Multi-Stage Training","date":"2020-09-28","arxiv_id":"2009.13199","n_code_links":0,"syntology":null},{"paper":null,"slug":"pin-a-novel-parallel-interactive-network-for","title":"PIN: A Novel Parallel Interactive Network for Spoken Language Understanding","date":"2020-09-28","arxiv_id":"2009.13431","n_code_links":0,"syntology":null}],"record_sha256":"c4008a176ade23977a413822922761bb40bd7e93d9c8d64f32a15c3955e9e7e5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}