{"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/dropout/papers/231","list_of":"/method/dropout","method":"Dropout","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":231,"pages_in_order":275,"rows_per_page":100,"rows":[23001,23100],"of":27472,"counts":{"archive_papers_tagged":27472,"with_a_code_link":12129,"where_syntology_ran_a_sample":3620,"not_listed_spam_title":0,"listed":27472,"listed_where_code_ran":3620,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3044,"every_run_a_failure_of_syntologys_instrument":576,"listed_with_a_run_with_no_instrument_failure":3044,"listed_every_run_a_failure_of_syntologys_instrument":576,"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/dropout","prev":"/method/dropout/papers/230","next":"/method/dropout/papers/232","papers":[{"paper":"/paper/sound-natural-content-rephrasing-in-dialog","slug":"sound-natural-content-rephrasing-in-dialog","title":"Sound Natural: Content Rephrasing in Dialog Systems","date":"2020-11-03","arxiv_id":"2011.01993","n_code_links":1,"syntology":null},{"paper":"/paper/stylemelgan-an-efficient-high-fidelity","slug":"stylemelgan-an-efficient-high-fidelity","title":"StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalization","date":"2020-11-03","arxiv_id":"2011.01557","n_code_links":2,"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":null}},{"paper":"/paper/tabular-transformers-for-modeling","slug":"tabular-transformers-for-modeling","title":"Tabular Transformers for Modeling Multivariate Time Series","date":"2020-11-03","arxiv_id":"2011.01843","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["IBM/TabFormer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"uncertainty-estimation-in-medical-image-1","title":"Uncertainty Estimation in Medical Image Localization: Towards Robust Anterior Thalamus Targeting for Deep Brain Stimulation","date":"2020-11-03","arxiv_id":"2011.02067","n_code_links":0,"syntology":null},{"paper":"/paper/xed-a-multilingual-dataset-for-sentiment","slug":"xed-a-multilingual-dataset-for-sentiment","title":"XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detection","date":"2020-11-03","arxiv_id":"2011.01612","n_code_links":1,"syntology":null},{"paper":"/paper/a-closer-look-at-linguistic-knowledge-in","slug":"a-closer-look-at-linguistic-knowledge-in","title":"A Closer Look at Linguistic Knowledge in Masked Language Models: The Case of Relative Clauses in American English","date":"2020-11-02","arxiv_id":"2011.00960","n_code_links":1,"syntology":null},{"paper":"/paper/abnirml-analyzing-the-behavior-of-neural-ir","slug":"abnirml-analyzing-the-behavior-of-neural-ir","title":"ABNIRML: Analyzing the Behavior of Neural IR Models","date":"2020-11-02","arxiv_id":"2011.00696","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":1,"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":{"repos":["allenai/abnirml"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"abstracting-influence-paths-for-explaining-1","title":"Influence Patterns for Explaining Information Flow in BERT","date":"2020-11-02","arxiv_id":"2011.00740","n_code_links":0,"syntology":null},{"paper":"/paper/dual-decoder-transformer-for-joint-automatic","slug":"dual-decoder-transformer-for-joint-automatic","title":"Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation","date":"2020-11-02","arxiv_id":"2011.00747","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-far-does-bert-look-at-distance-based","title":"How Far Does BERT Look At:Distance-based Clustering and Analysis of BERT$'$s Attention","date":"2020-11-02","arxiv_id":"2011.00943","n_code_links":0,"syntology":null},{"paper":"/paper/introducing-various-semantic-models-for","slug":"introducing-various-semantic-models-for","title":"Introducing various Semantic Models for Amharic: Experimentation and Evaluation with multiple Tasks and Datasets","date":"2020-11-02","arxiv_id":"2011.01154","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-sentence-embeddings-from-pre-trained","slug":"on-the-sentence-embeddings-from-pre-trained","title":"On the Sentence Embeddings from Pre-trained Language Models","date":"2020-11-02","arxiv_id":"2011.05864","n_code_links":3,"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: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bohanli/BERT-flow"],"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":"/paper/point-transformer","slug":"point-transformer","title":"Point Transformer","date":"2020-11-02","arxiv_id":"2011.00931","n_code_links":2,"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":["engelnico/point-transformer"],"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":["listed","official"]}}},{"paper":null,"slug":"qmul-sds-at-sardistance2020-leveraging","title":"QMUL-SDS @ SardiStance: Leveraging Network Interactions to Boost Performance on Stance Detection using Knowledge Graphs","date":"2020-11-02","arxiv_id":"2011.01181","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-semantics-based-approach-to-disclosure","title":"A Semantics-based Approach to Disclosure Classification in User-Generated Online Content","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-structure-enhanced-graph-convolutional","title":"A structure-enhanced graph convolutional network for sentiment analysis","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"active-learning-approaches-to-enhancing","title":"Active Learning Approaches to Enhancing Neural Machine Translation","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/approximation-of-response-knowledge-retrieval","slug":"approximation-of-response-knowledge-retrieval","title":"Approximation of Response Knowledge Retrieval in Knowledge-grounded Dialogue Generation","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/chime-cross-passage-hierarchical-memory","slug":"chime-cross-passage-hierarchical-memory","title":"CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering","date":"2020-11-01","arxiv_id":"2011.00519","n_code_links":1,"syntology":null},{"paper":"/paper/conceptbert-concept-aware-representation-for","slug":"conceptbert-concept-aware-representation-for","title":"ConceptBert: Concept-Aware Representation for Visual Question Answering","date":"2020-11-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"context-analysis-for-pre-trained-masked","title":"Context Analysis for Pre-trained Masked Language Models","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/coot-cooperative-hierarchical-transformer-for","slug":"coot-cooperative-hierarchical-transformer-for","title":"COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning","date":"2020-11-01","arxiv_id":"2011.00597","n_code_links":1,"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":{"repos":["gingsi/coot-videotext"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cross-lingual-training-of-neural-models-for","title":"Cross-Lingual Training of Neural Models for Document Ranking","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/decoding-language-spatial-relations-to-2d","slug":"decoding-language-spatial-relations-to-2d","title":"Decoding Language Spatial Relations to 2D Spatial Arrangements","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/deep-diacritization-efficient-hierarchical","slug":"deep-diacritization-efficient-hierarchical","title":"Deep Diacritization: Efficient Hierarchical Recurrence for Improved Arabic Diacritization","date":"2020-11-01","arxiv_id":"2011.00538","n_code_links":1,"syntology":null},{"paper":null,"slug":"dynamically-throttleable-neural-networks-tnn","title":"Dynamically Throttleable Neural Networks (TNN)","date":"2020-11-01","arxiv_id":"2011.02836","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-generalization-in-natural-language","slug":"enhancing-generalization-in-natural-language","title":"Enhancing Generalization in Natural Language Inference by Syntax","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"exbert-extending-pre-trained-models-with","title":"exBERT: Extending Pre-trained Models with Domain-specific Vocabulary Under Constrained Training Resources","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"factorized-transformer-for-multi-domain","title":"Factorized Transformer for Multi-Domain Neural Machine Translation","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hate-speech-and-offensive-language-detection","title":"Hate-Speech and Offensive Language Detection in Roman Urdu","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"huji-ku-at-mrp-2020-two-transition-based-1","title":"HUJI-KU at MRP 2020: Two Transition-based Neural Parsers","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/integrating-task-specific-information-into","slug":"integrating-task-specific-information-into","title":"Integrating Task Specific Information into Pretrained Language Models for Low Resource Fine Tuning","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"investigation-of-bert-model-on-biomedical","title":"Investigation of BERT Model on Biomedical Relation Extraction Based on Revised Fine-tuning Mechanism","date":"2020-11-01","arxiv_id":"2011.00398","n_code_links":0,"syntology":null},{"paper":"/paper/kermit-complementing-transformer","slug":"kermit-complementing-transformer","title":"KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-ground-medical-text-in-a-3d-human","slug":"learning-to-ground-medical-text-in-a-3d-human","title":"Learning to ground medical text in a 3D human atlas","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/limit-bert-linguistics-informed-multi-task","slug":"limit-bert-linguistics-informed-multi-task","title":"LIMIT-BERT : Linguistics Informed Multi-Task BERT","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"making-information-seeking-easier-an-improved","title":"Making Information Seeking Easier: An Improved Pipeline for Conversational Search","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"making-ml-models-fairer-through-explanations","title":"Making ML models fairer through explanations: the case of LimeOut","date":"2020-11-01","arxiv_id":"2011.00603","n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-intra-and-inter-modality-incongruity","title":"Modeling Intra and Inter-modality Incongruity for Multi-Modal Sarcasm Detection","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multi-2oie-multilingual-open-information-1","slug":"multi-2oie-multilingual-open-information-1","title":"Multi\\^2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/optimizing-word-segmentation-for-downstream","slug":"optimizing-word-segmentation-for-downstream","title":"Optimizing Word Segmentation for Downstream Task","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-responses-to-psychological","title":"Predicting Responses to Psychological Questionnaires from Participants' Social Media Posts and Question Text Embeddings","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/representation-learning-for-type-driven","slug":"representation-learning-for-type-driven","title":"Representation Learning for Type-Driven Composition","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"smrt-chatbots-improving-non-task-oriented","title":"SMRT Chatbots: Improving Non-Task-Oriented Dialog with Simulated Multiple Reference Training","date":"2020-11-01","arxiv_id":"2011.00547","n_code_links":0,"syntology":null},{"paper":"/paper/social-chemistry-101-learning-to-reason-about","slug":"social-chemistry-101-learning-to-reason-about","title":"Social Chemistry 101: Learning to Reason about Social and Moral Norms","date":"2020-11-01","arxiv_id":"2011.00620","n_code_links":2,"syntology":null},{"paper":null,"slug":"the-amazing-world-of-neural-language","title":"The Amazing World of Neural Language Generation","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/the-relx-dataset-and-matching-the-1","slug":"the-relx-dataset-and-matching-the-1","title":"The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/towards-zero-shot-conditional-summarization","slug":"towards-zero-shot-conditional-summarization","title":"Towards Zero-Shot Conditional Summarization with Adaptive Multi-Task Fine-Tuning","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-multi-aspect-modeling-for","title":"Transformer-based Multi-Aspect Modeling for Multi-Aspect Multi-Sentiment Analysis","date":"2020-11-01","arxiv_id":"2011.00476","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-monte-carlo-dropout-and-bootstrap","title":"A comparison of Monte Carlo dropout and bootstrap aggregation on the performance and uncertainty estimation in radiation therapy dose prediction with deep learning neural networks","date":"2020-11-01","arxiv_id":"2011.00388","n_code_links":0,"syntology":null},{"paper":"/paper/visually-grounded-planning-without-vision-1","slug":"visually-grounded-planning-without-vision-1","title":"Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions","date":"2020-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/free-the-plural-unrestricted-split-antecedent","slug":"free-the-plural-unrestricted-split-antecedent","title":"Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution","date":"2020-10-31","arxiv_id":"2011.00245","n_code_links":1,"syntology":null},{"paper":null,"slug":"methods-for-pruning-deep-neural-networks","title":"Methods for Pruning Deep Neural Networks","date":"2020-10-31","arxiv_id":"2011.00241","n_code_links":0,"syntology":null},{"paper":"/paper/neural-coreference-resolution-for-arabic","slug":"neural-coreference-resolution-for-arabic","title":"Neural Coreference Resolution for Arabic","date":"2020-10-31","arxiv_id":"2011.00286","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-pre-trained-bert-for-aspect","slug":"understanding-pre-trained-bert-for-aspect","title":"Understanding Pre-trained BERT for Aspect-based Sentiment Analysis","date":"2020-10-31","arxiv_id":"2011.00169","n_code_links":2,"syntology":null},{"paper":null,"slug":"83-imagenet-accuracy-in-one-hour","title":"Training EfficientNets at Supercomputer Scale: 83% ImageNet Top-1 Accuracy in One Hour","date":"2020-10-30","arxiv_id":"2011.00071","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-sui-generis-qa-approach-using-roberta-for","title":"A Sui Generis QA Approach using RoBERTa for Adverse Drug Event Identification","date":"2020-10-30","arxiv_id":"2011.00057","n_code_links":0,"syntology":null},{"paper":"/paper/generating-radiology-reports-via-memory","slug":"generating-radiology-reports-via-memory","title":"Generating Radiology Reports via Memory-driven Transformer","date":"2020-10-30","arxiv_id":"2010.16056","n_code_links":2,"syntology":{"ran":26,"of":31,"n_ran_checked":20,"n_instrument":6,"unverified":5,"pointer_only":25,"phrase":"26 ran (of which 13 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 3 violated, 14 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","official":{"repos":["zhjohnchan/R2Gen"],"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":["found_in_text","listed","official"]}}},{"paper":null,"slug":"improving-dialogue-breakdown-detection-with","title":"Improving Dialogue Breakdown Detection with Semi-Supervised Learning","date":"2020-10-30","arxiv_id":"2011.00136","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-labeling-using-a-deep-contextualized","slug":"semantic-labeling-using-a-deep-contextualized","title":"Semantic Labeling Using a Deep Contextualized Language Model","date":"2020-10-30","arxiv_id":"2010.16037","n_code_links":1,"syntology":null},{"paper":null,"slug":"slm-learning-a-discourse-language","title":"SLM: Learning a Discourse Language Representation with Sentence Unshuffling","date":"2020-10-30","arxiv_id":"2010.16249","n_code_links":0,"syntology":null},{"paper":"/paper/target-word-masking-for-location-metonymy","slug":"target-word-masking-for-location-metonymy","title":"Target Word Masking for Location Metonymy Resolution","date":"2020-10-30","arxiv_id":"2010.16097","n_code_links":1,"syntology":null},{"paper":null,"slug":"topic-preserving-synthetic-news-generation-an","title":"Topic-Preserving Synthetic News Generation: An Adversarial Deep Reinforcement Learning Approach","date":"2020-10-30","arxiv_id":"2010.16324","n_code_links":0,"syntology":null},{"paper":"/paper/veco-variable-encoder-decoder-pre-training-1","slug":"veco-variable-encoder-decoder-pre-training-1","title":"VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation","date":"2020-10-30","arxiv_id":"2010.16046","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-s-in-a-loss-function-for-image","title":"Why Do Better Loss Functions Lead to Less Transferable Features?","date":"2020-10-30","arxiv_id":"2010.16402","n_code_links":0,"syntology":null},{"paper":"/paper/combining-self-training-and-self-supervised","slug":"combining-self-training-and-self-supervised","title":"Combining Self-Training and Self-Supervised Learning for Unsupervised Disfluency Detection","date":"2020-10-29","arxiv_id":"2010.15360","n_code_links":1,"syntology":null},{"paper":null,"slug":"contextual-bert-conditioning-the-language","title":"Contextual BERT: Conditioning the Language Model Using a Global State","date":"2020-10-29","arxiv_id":"2010.15778","n_code_links":0,"syntology":null},{"paper":"/paper/cream-of-the-crop-distilling-prioritized","slug":"cream-of-the-crop-distilling-prioritized","title":"Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search","date":"2020-10-29","arxiv_id":"2010.15821","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["microsoft/cream"],"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":"devicetts-a-small-footprint-fast-stable","title":"DeviceTTS: A Small-Footprint, Fast, Stable Network for On-Device Text-to-Speech","date":"2020-10-29","arxiv_id":"2010.15311","n_code_links":0,"syntology":null},{"paper":null,"slug":"memory-attentive-fusion-external-language","title":"Memory Attentive Fusion: External Language Model Integration for Transformer-based Sequence-to-Sequence Model","date":"2020-10-29","arxiv_id":"2010.15437","n_code_links":0,"syntology":null},{"paper":null,"slug":"tilde-at-wmt-2020-news-task-systems","title":"Tilde at WMT 2020: News Task Systems","date":"2020-10-29","arxiv_id":"2010.15423","n_code_links":0,"syntology":null},{"paper":null,"slug":"bayesian-methods-for-semi-supervised-text","title":"Bayesian Methods for Semi-supervised Text Annotation","date":"2020-10-28","arxiv_id":"2010.14872","n_code_links":0,"syntology":null},{"paper":"/paper/desmog-detecting-stance-in-media-on-global","slug":"desmog-detecting-stance-in-media-on-global","title":"Detecting Stance in Media on Global Warming","date":"2020-10-28","arxiv_id":"2010.15149","n_code_links":1,"syntology":null},{"paper":null,"slug":"fusion-models-for-improved-visual-captioning","title":"Fusion Models for Improved Visual Captioning","date":"2020-10-28","arxiv_id":"2010.15251","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-unknot","title":"Learning to Unknot","date":"2020-10-28","arxiv_id":"2010.16263","n_code_links":0,"syntology":null},{"paper":"/paper/model-rubik-s-cube-twisting-resolution-depth","slug":"model-rubik-s-cube-twisting-resolution-depth","title":"Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets","date":"2020-10-28","arxiv_id":"2010.14819","n_code_links":9,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["huawei-noah/CV-backbones","huawei-noah/ghostnet"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"the-volctrans-machine-translation-system-for","title":"The Volctrans Machine Translation System for WMT20","date":"2020-10-28","arxiv_id":"2010.14806","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-clarifying-question-selection-system-from","title":"A Clarifying Question Selection System from NTES_ALONG in Convai3 Challenge","date":"2020-10-27","arxiv_id":"2010.14202","n_code_links":0,"syntology":null},{"paper":"/paper/fast-interleaved-bidirectional-sequence","slug":"fast-interleaved-bidirectional-sequence","title":"Fast Interleaved Bidirectional Sequence Generation","date":"2020-10-27","arxiv_id":"2010.14481","n_code_links":1,"syntology":null},{"paper":"/paper/fragmentvc-any-to-any-voice-conversion-by-end","slug":"fragmentvc-any-to-any-voice-conversion-by-end","title":"FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention","date":"2020-10-27","arxiv_id":"2010.14150","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yistLin/FragmentVC"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"know-where-to-drop-your-weights-towards","title":"Know Where To Drop Your Weights: Towards Faster Uncertainty Estimation","date":"2020-10-27","arxiv_id":"2010.14019","n_code_links":0,"syntology":null},{"paper":"/paper/mmft-bert-multimodal-fusion-transformer-with","slug":"mmft-bert-multimodal-fusion-transformer-with","title":"MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering","date":"2020-10-27","arxiv_id":"2010.14095","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-emotion-recognition-with","slug":"multimodal-emotion-recognition-with","title":"Multimodal Emotion Recognition with Transformer-Based Self Supervised Feature Fusion","date":"2020-10-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"parallel-waveform-synthesis-based-on","title":"Parallel waveform synthesis based on generative adversarial networks with voicing-aware conditional discriminators","date":"2020-10-27","arxiv_id":"2010.14151","n_code_links":0,"syntology":null},{"paper":null,"slug":"to-bert-or-not-to-bert-comparing-task","title":"To BERT or Not to BERT: Comparing Task-specific and Task-agnostic Semi-Supervised Approaches for Sequence Tagging","date":"2020-10-27","arxiv_id":"2010.14042","n_code_links":0,"syntology":null},{"paper":"/paper/unmasking-contextual-stereotypes-measuring","slug":"unmasking-contextual-stereotypes-measuring","title":"Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias","date":"2020-10-27","arxiv_id":"2010.14534","n_code_links":1,"syntology":null},{"paper":"/paper/accelerating-training-of-transformer-based","slug":"accelerating-training-of-transformer-based","title":"Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping","date":"2020-10-26","arxiv_id":"2010.13369","n_code_links":1,"syntology":null},{"paper":"/paper/controlled-molecule-generator-for-optimizing","slug":"controlled-molecule-generator-for-optimizing","title":"Controlled Molecule Generator for Optimizing Multiple Chemical Properties","date":"2020-10-26","arxiv_id":"2010.13908","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["deargen/cmg"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/delta-stn-efficient-bilevel-optimization-for","slug":"delta-stn-efficient-bilevel-optimization-for","title":"Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians","date":"2020-10-26","arxiv_id":"2010.13514","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["pomonam/Self-Tuning-Networks"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/fastformers-highly-efficient-transformer","slug":"fastformers-highly-efficient-transformer","title":"FastFormers: Highly Efficient Transformer Models for Natural Language Understanding","date":"2020-10-26","arxiv_id":"2010.13382","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["microsoft/fastformers"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/fine-grained-information-status-1","slug":"fine-grained-information-status-1","title":"Fine-grained Information Status Classification Using Discourse Context-Aware BERT","date":"2020-10-26","arxiv_id":"2010.14759","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-transformer-networks-with-syntactic-and","title":"Graph Transformer Networks with Syntactic and Semantic Structures for Event Argument Extraction","date":"2020-10-26","arxiv_id":"2010.13391","n_code_links":0,"syntology":null},{"paper":null,"slug":"peak-detection-on-data-independent","title":"Peak Detection On Data Independent Acquisition Mass Spectrometry Data With Semisupervised Convolutional Transformers","date":"2020-10-26","arxiv_id":"2010.13841","n_code_links":0,"syntology":null},{"paper":null,"slug":"restrained-generative-adversarial-network","title":"Restrained Generative Adversarial Network against Overfitting in Numeric Data Augmentation","date":"2020-10-26","arxiv_id":"2010.13549","n_code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-spoken-language-understanding","slug":"semi-supervised-spoken-language-understanding","title":"Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining","date":"2020-10-26","arxiv_id":"2010.13826","n_code_links":1,"syntology":null},{"paper":null,"slug":"theory-oriented-deep-leakage-from-gradients","title":"Exploring the Security Boundary of Data Reconstruction via Neuron Exclusivity Analysis","date":"2020-10-26","arxiv_id":"2010.13356","n_code_links":0,"syntology":null},{"paper":null,"slug":"upb-at-semeval-2020-task-12-multilingual","title":"UPB at SemEval-2020 Task 12: Multilingual Offensive Language Detection on Social Media by Fine-tuning a Variety of BERT-based Models","date":"2020-10-26","arxiv_id":"2010.13609","n_code_links":0,"syntology":null},{"paper":null,"slug":"commonsense-knowledge-adversarial-dataset","title":"Commonsense knowledge adversarial dataset that challenges ELECTRA","date":"2020-10-25","arxiv_id":"2010.13049","n_code_links":0,"syntology":null},{"paper":null,"slug":"contextualized-word-embeddings-encode-aspects","title":"Contextualized Word Embeddings Encode Aspects of Human-Like Word Sense Knowledge","date":"2020-10-25","arxiv_id":"2010.13057","n_code_links":0,"syntology":null},{"paper":null,"slug":"crab-class-representation-attentive-bert-for","title":"CRAB: Class Representation Attentive BERT for Hate Speech Identification in Social Media","date":"2020-10-25","arxiv_id":"2010.13028","n_code_links":0,"syntology":null}],"record_sha256":"0b961c5298033e9c994878ccaa6bd95825be1712bc15b768748b38d6df7653a3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}