{"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/237","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":237,"pages_in_order":275,"rows_per_page":100,"rows":[23601,23700],"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/236","next":"/method/dropout/papers/238","papers":[{"paper":"/paper/sentimental-liar-extended-corpus-and-deep","slug":"sentimental-liar-extended-corpus-and-deep","title":"Sentimental LIAR: Extended Corpus and Deep Learning Models for Fake Claim Classification","date":"2020-09-01","arxiv_id":"2009.01047","n_code_links":2,"syntology":null},{"paper":"/paper/a-bidirectional-tree-tagging-scheme-for","slug":"a-bidirectional-tree-tagging-scheme-for","title":"A Bidirectional Tree Tagging Scheme for Joint Medical Relation Extraction","date":"2020-08-31","arxiv_id":"2008.13339","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/soccogcom-at-semeval-2020-task-11","slug":"soccogcom-at-semeval-2020-task-11","title":"SocCogCom at SemEval-2020 Task 11: Characterizing and Detecting Propaganda using Sentence-Level Emotional Salience Features","date":"2020-08-29","arxiv_id":"2008.13012","n_code_links":1,"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":"knowledge-efficient-deep-learning-for-natural","title":"Knowledge Efficient Deep Learning for Natural Language Processing","date":"2020-08-28","arxiv_id":"2008.12878","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-the-objectives-of-extractive","slug":"rethinking-the-objectives-of-extractive","title":"Rethinking the Objectives of Extractive Question Answering","date":"2020-08-28","arxiv_id":"2008.12804","n_code_links":1,"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":["KNOT-FIT-BUT/JointSpanExtraction"],"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":"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/a-fast-and-robust-bert-based-dialogue-state","slug":"a-fast-and-robust-bert-based-dialogue-state","title":"A Fast and Robust BERT-based Dialogue State Tracker for Schema-Guided Dialogue Dataset","date":"2020-08-27","arxiv_id":"2008.12335","n_code_links":1,"syntology":null},{"paper":"/paper/a-free-web-service-for-fast-covid-19","slug":"a-free-web-service-for-fast-covid-19","title":"A free web service for fast COVID-19 classification of chest X-Ray images","date":"2020-08-27","arxiv_id":"2009.01657","n_code_links":1,"syntology":null},{"paper":null,"slug":"ambert-a-pre-trained-language-model-with","title":"AMBERT: A Pre-trained Language Model with Multi-Grained Tokenization","date":"2020-08-27","arxiv_id":"2008.11869","n_code_links":0,"syntology":null},{"paper":null,"slug":"dave-deriving-automatically-verilog-from","title":"DAVE: Deriving Automatically Verilog from English","date":"2020-08-27","arxiv_id":"2009.01026","n_code_links":0,"syntology":null},{"paper":"/paper/entity-and-evidence-guided-relation","slug":"entity-and-evidence-guided-relation","title":"Entity and Evidence Guided Relation Extraction for DocRED","date":"2020-08-27","arxiv_id":"2008.12283","n_code_links":0,"syntology":null},{"paper":"/paper/greek-bert-the-greeks-visiting-sesame-street","slug":"greek-bert-the-greeks-visiting-sesame-street","title":"GREEK-BERT: The Greeks visiting Sesame Street","date":"2020-08-27","arxiv_id":"2008.12014","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":["nlpaueb/greek-bert"],"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/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":"multigbs-a-multi-layer-graph-approach-to","title":"MultiGBS: A multi-layer graph approach to biomedical summarization","date":"2020-08-27","arxiv_id":"2008.11908","n_code_links":0,"syntology":null},{"paper":"/paper/query-focused-multi-document-summarisation-of","slug":"query-focused-multi-document-summarisation-of","title":"Query Focused Multi-document Summarisation of Biomedical Texts","date":"2020-08-27","arxiv_id":"2008.11986","n_code_links":1,"syntology":null},{"paper":"/paper/query-focused-multi-document-summarisation-of-1","slug":"query-focused-multi-document-summarisation-of-1","title":"Query Focused Multi-document Summarisation of Biomedical Texts: Macquarie Universiy and the Australian National University at BioASQ8b","date":"2020-08-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multitask-deep-learning-approach-for-user","title":"A Multitask Deep Learning Approach for User Depression Detection on Sina Weibo","date":"2020-08-26","arxiv_id":"2008.11708","n_code_links":0,"syntology":null},{"paper":null,"slug":"apmsqueeze-a-communication-efficient-adam","title":"APMSqueeze: A Communication Efficient Adam-Preconditioned Momentum SGD Algorithm","date":"2020-08-26","arxiv_id":"2008.11343","n_code_links":0,"syntology":null},{"paper":null,"slug":"discrete-word-embedding-for-logical-natural","title":"Discrete Word Embedding for Logical Natural Language Understanding","date":"2020-08-26","arxiv_id":"2008.11649","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-and-word-sense-disambiguation","slug":"language-models-and-word-sense-disambiguation","title":"Analysis and Evaluation of Language Models for Word Sense Disambiguation","date":"2020-08-26","arxiv_id":"2008.11608","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncertainty-aware-surrogate-model-for","title":"Surrogate Model For Field Optimization Using Beta-VAE Based Regression","date":"2020-08-26","arxiv_id":"2008.11433","n_code_links":0,"syntology":null},{"paper":null,"slug":"conceptualized-representation-learning-for","title":"Conceptualized Representation Learning for Chinese Biomedical Text Mining","date":"2020-08-25","arxiv_id":"2008.10813","n_code_links":0,"syntology":null},{"paper":"/paper/etc-nlg-end-to-end-topic-conditioned-natural","slug":"etc-nlg-end-to-end-topic-conditioned-natural","title":"ETC-NLG: End-to-end Topic-Conditioned Natural Language Generation","date":"2020-08-25","arxiv_id":"2008.10875","n_code_links":1,"syntology":null},{"paper":"/paper/fastsal-a-computationally-efficient-network","slug":"fastsal-a-computationally-efficient-network","title":"FastSal: a Computationally Efficient Network for Visual Saliency Prediction","date":"2020-08-25","arxiv_id":"2008.11151","n_code_links":1,"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":["feiyanhu/FastSal"],"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":"page-a-simple-and-optimal-probabilistic","title":"PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization","date":"2020-08-25","arxiv_id":"2008.10898","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamics-of-feed-forward-induced-interference","title":"Dynamics of feed forward induced interference training","date":"2020-08-24","arxiv_id":"2008.11111","n_code_links":0,"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/knowledge-empowered-representation-learning","slug":"knowledge-empowered-representation-learning","title":"Knowledge-Empowered Representation Learning for Chinese Medical Reading Comprehension: Task, Model and Resources","date":"2020-08-24","arxiv_id":"2008.10327","n_code_links":1,"syntology":null},{"paper":null,"slug":"prediction-of-icd-codes-with-clinical-bert","title":"Prediction of ICD Codes with Clinical BERT Embeddings and Text Augmentation with Label Balancing using MIMIC-III","date":"2020-08-24","arxiv_id":"2008.10492","n_code_links":0,"syntology":null},{"paper":null,"slug":"syrapropa-at-semeval-2020-task-11-bert-based","title":"syrapropa at SemEval-2020 Task 11: BERT-based Models Design For Propagandistic Technique and Span Detection","date":"2020-08-24","arxiv_id":"2008.10163","n_code_links":0,"syntology":null},{"paper":null,"slug":"two-stages-approach-for-tweet-engagement","title":"Two Stages Approach for Tweet Engagement Prediction","date":"2020-08-24","arxiv_id":"2008.10419","n_code_links":0,"syntology":null},{"paper":"/paper/ynu-hpcc-at-semeval-2020-task-11-lstm-network","slug":"ynu-hpcc-at-semeval-2020-task-11-lstm-network","title":"YNU-HPCC at SemEval-2020 Task 11: LSTM Network for Detection of Propaganda Techniques in News Articles","date":"2020-08-24","arxiv_id":"2008.10166","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 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) · 0 unverified","official":{"repos":["daojiaxu/semeval_11"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"variational-inference-based-dropout-in","title":"Variational Inference-Based Dropout in Recurrent Neural Networks for Slot Filling in Spoken Language Understanding","date":"2020-08-23","arxiv_id":"2009.01003","n_code_links":0,"syntology":null},{"paper":null,"slug":"applications-of-bert-based-sequence-tagging","title":"Applications of BERT Based Sequence Tagging Models on Chinese Medical Text Attributes Extraction","date":"2020-08-22","arxiv_id":"2008.09740","n_code_links":0,"syntology":null},{"paper":"/paper/cyberwalle-at-semeval-2020-task-11-an","slug":"cyberwalle-at-semeval-2020-task-11-an","title":"CyberWallE at SemEval-2020 Task 11: An Analysis of Feature Engineering for Ensemble Models for Propaganda Detection","date":"2020-08-22","arxiv_id":"2008.09859","n_code_links":1,"syntology":null},{"paper":"/paper/duth-at-semeval-2020-task-11-bert-with-entity","slug":"duth-at-semeval-2020-task-11-bert-with-entity","title":"DUTH at SemEval-2020 Task 11: BERT with Entity Mapping for Propaganda Classification","date":"2020-08-22","arxiv_id":"2008.09894","n_code_links":1,"syntology":null},{"paper":"/paper/fat-albert-finding-answers-in-large-texts","slug":"fat-albert-finding-answers-in-large-texts","title":"FAT ALBERT: Finding Answers in Large Texts using Semantic Similarity Attention Layer based on BERT","date":"2020-08-22","arxiv_id":"2009.01004","n_code_links":1,"syntology":null},{"paper":"/paper/hinglishnlp-fine-tuned-language-models-for","slug":"hinglishnlp-fine-tuned-language-models-for","title":"HinglishNLP: Fine-tuned Language Models for Hinglish Sentiment Detection","date":"2020-08-22","arxiv_id":"2008.09820","n_code_links":2,"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/abstractive-summarization-of-spoken","slug":"abstractive-summarization-of-spoken","title":"Abstractive Summarization of Spoken andWritten Instructions with BERT","date":"2020-08-21","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"adapting-event-extractors-to-medical-data","title":"Adapting Event Extractors to Medical Data: Bridging the Covariate Shift","date":"2020-08-21","arxiv_id":"2008.09266","n_code_links":0,"syntology":null},{"paper":"/paper/an-improved-person-re-identification-method","slug":"an-improved-person-re-identification-method","title":"An Improved Person Re-identification Method by light-weight convolutional neural network","date":"2020-08-21","arxiv_id":"2008.09448","n_code_links":1,"syntology":null},{"paper":"/paper/neural-machine-translation-without-embeddings","slug":"neural-machine-translation-without-embeddings","title":"Neural Machine Translation without Embeddings","date":"2020-08-21","arxiv_id":"2008.09396","n_code_links":2,"syntology":null},{"paper":null,"slug":"an-experimental-study-of-deep-neural-network","title":"An Experimental Study of Deep Neural Network Models for Vietnamese Multiple-Choice Reading Comprehension","date":"2020-08-20","arxiv_id":"2008.08810","n_code_links":0,"syntology":null},{"paper":"/paper/lite-training-strategies-for-portuguese","slug":"lite-training-strategies-for-portuguese","title":"Lite Training Strategies for Portuguese-English and English-Portuguese Translation","date":"2020-08-20","arxiv_id":"2008.08769","n_code_links":1,"syntology":null},{"paper":"/paper/mmea-entity-alignment-for-multi-modal","slug":"mmea-entity-alignment-for-multi-modal","title":"MMEA: Entity Alignment for Multi-Modal Knowledge Graphs","date":"2020-08-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/parade-passage-representation-aggregation-for","slug":"parade-passage-representation-aggregation-for","title":"PARADE: Passage Representation Aggregation for Document Reranking","date":"2020-08-20","arxiv_id":"2008.09093","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":{"repos":["canjiali/PARADE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":"/paper/ptt5-pretraining-and-validating-the-t5-model","slug":"ptt5-pretraining-and-validating-the-t5-model","title":"PTT5: Pretraining and validating the T5 model on Brazilian Portuguese data","date":"2020-08-20","arxiv_id":"2008.09144","n_code_links":3,"syntology":null},{"paper":"/paper/uncertainty-estimation-in-medical-image","slug":"uncertainty-estimation-in-medical-image","title":"Uncertainty Estimation in Medical Image Denoising with Bayesian Deep Image Prior","date":"2020-08-20","arxiv_id":"2008.08837","n_code_links":1,"syntology":null},{"paper":"/paper/top2vec-distributed-representations-of-topics","slug":"top2vec-distributed-representations-of-topics","title":"Top2Vec: Distributed Representations of Topics","date":"2020-08-19","arxiv_id":"2008.09470","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ddangelov/Top2Vec"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"uob-at-semeval-2020-task-12-boosting-bert","title":"UoB at SemEval-2020 Task 12: Boosting BERT with Corpus Level Information","date":"2020-08-19","arxiv_id":"2008.08547","n_code_links":0,"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":null,"slug":"discovering-multi-hardware-mobile-models-via","title":"Discovering Multi-Hardware Mobile Models via Architecture Search","date":"2020-08-18","arxiv_id":"2008.08178","n_code_links":0,"syntology":null},{"paper":null,"slug":"estimation-of-causal-effects-of-multiple","title":"Estimation of causal effects of multiple treatments in healthcare database studies with rare outcomes","date":"2020-08-18","arxiv_id":"2008.07687","n_code_links":0,"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":null,"slug":"ranking-clarification-questions-via-natural","title":"Ranking Clarification Questions via Natural Language Inference","date":"2020-08-18","arxiv_id":"2008.07688","n_code_links":0,"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":null,"slug":"generative-models-are-unsupervised-predictors","title":"Generative Models are Unsupervised Predictors of Page Quality: A Colossal-Scale Study","date":"2020-08-17","arxiv_id":"2008.13533","n_code_links":0,"syntology":null},{"paper":null,"slug":"narrative-interpolation-for-generating-and","title":"Narrative Interpolation for Generating and Understanding Stories","date":"2020-08-17","arxiv_id":"2008.07466","n_code_links":0,"syntology":null},{"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":"stock-index-prediction-with-multi-task","title":"Stock Index Prediction with Multi-task Learning and Word Polarity Over Time","date":"2020-08-17","arxiv_id":"2008.07605","n_code_links":0,"syntology":null},{"paper":null,"slug":"adding-recurrence-to-pretrained-transformers","title":"Adding Recurrence to Pretrained Transformers for Improved Efficiency and Context Size","date":"2020-08-16","arxiv_id":"2008.07027","n_code_links":0,"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":"/paper/devlbert-learning-deconfounded-visio","slug":"devlbert-learning-deconfounded-visio","title":"DeVLBert: Learning Deconfounded Visio-Linguistic Representations","date":"2020-08-16","arxiv_id":"2008.06884","n_code_links":1,"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":"/paper/jointly-fine-tuning-bert-like-self-supervised","slug":"jointly-fine-tuning-bert-like-self-supervised","title":"Jointly Fine-Tuning \"BERT-like\" Self Supervised Models to Improve Multimodal Speech Emotion Recognition","date":"2020-08-15","arxiv_id":"2008.06682","n_code_links":1,"syntology":null},{"paper":"/paper/jointly-fine-tuning-bert-like-self-supervised-1","slug":"jointly-fine-tuning-bert-like-self-supervised-1","title":"Jointly Fine-Tuning “BERT-like” Self Supervised Models to Improve Multimodal Speech Emotion Recognition","date":"2020-08-15","arxiv_id":null,"n_code_links":1,"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":null,"slug":"hate-speech-detection-and-racial-bias","title":"Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model","date":"2020-08-14","arxiv_id":"2008.06460","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-as-few-shot-learner-for-task","title":"Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems","date":"2020-08-14","arxiv_id":"2008.06239","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":"/paper/andes-at-semeval-2020-task-12-a-jointly","slug":"andes-at-semeval-2020-task-12-a-jointly","title":"ANDES at SemEval-2020 Task 12: A jointly-trained BERT multilingual model for offensive language detection","date":"2020-08-13","arxiv_id":"2008.06408","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":"/paper/enhancing-speech-intelligibility-in-text-to","slug":"enhancing-speech-intelligibility-in-text-to","title":"Enhancing Speech Intelligibility in Text-To-Speech Synthesis using Speaking Style Conversion","date":"2020-08-13","arxiv_id":"2008.05809","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":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/mice-mining-idioms-with-contextual-embeddings","slug":"mice-mining-idioms-with-contextual-embeddings","title":"MICE: Mining Idioms with Contextual Embeddings","date":"2020-08-13","arxiv_id":"2008.05759","n_code_links":1,"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/facial-expression-recognition-under-partial","slug":"facial-expression-recognition-under-partial","title":"Facial Expression Recognition Under Partial Occlusion from Virtual Reality Headsets based on Transfer Learning","date":"2020-08-12","arxiv_id":"2008.05563","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":"leveraging-automated-mixed-low-precision","title":"Leveraging Automated Mixed-Low-Precision Quantization for tiny edge microcontrollers","date":"2020-08-12","arxiv_id":"2008.05124","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-moocs-dropout-using-only-two","title":"Predicting MOOCs Dropout Using Only Two Easily Obtainable Features from the First Week's Activities","date":"2020-08-12","arxiv_id":"2008.05849","n_code_links":0,"syntology":null},{"paper":null,"slug":"variance-reduced-language-pretraining-via-a","title":"Variance-reduced Language Pretraining via a Mask Proposal Network","date":"2020-08-12","arxiv_id":"2008.05333","n_code_links":0,"syntology":null},{"paper":"/paper/decoding-kinetic-features-of-hand-motor","slug":"decoding-kinetic-features-of-hand-motor","title":"Decoding kinetic features of hand motor preparation from single‐trial EEG using convolutional neural networks","date":"2020-08-11","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"modeling-prosodic-phrasing-with-multi-task","title":"Modeling Prosodic Phrasing with Multi-Task Learning in Tacotron-based TTS","date":"2020-08-11","arxiv_id":"2008.05284","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-modal-segmentation-of-3d-brain-scans","title":"Multi-modal segmentation of 3D brain scans using neural networks","date":"2020-08-11","arxiv_id":"2008.04594","n_code_links":0,"syntology":null},{"paper":null,"slug":"pneumoxttention-a-cnn-compensating-for-human","title":"PneumoXttention: A CNN compensating for Human Fallibility when Detecting Pneumonia through CXR images with Attention","date":"2020-08-11","arxiv_id":"2008.04907","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-lexical-a-semantic-retrieval-framework","title":"Beyond Lexical: A Semantic Retrieval Framework for Textual SearchEngine","date":"2020-08-10","arxiv_id":"2008.03917","n_code_links":0,"syntology":null},{"paper":"/paper/do-ideas-have-shape-plato-s-theory-of-forms","slug":"do-ideas-have-shape-plato-s-theory-of-forms","title":"Do ideas have shape? Idea registration as the continuous limit of artificial neural networks","date":"2020-08-10","arxiv_id":"2008.03920","n_code_links":1,"syntology":null},{"paper":null,"slug":"does-bert-solve-commonsense-task-via","title":"On Commonsense Cues in BERT for Solving Commonsense Tasks","date":"2020-08-10","arxiv_id":"2008.03945","n_code_links":0,"syntology":null},{"paper":"/paper/firebert-hardening-bert-based-classifiers","slug":"firebert-hardening-bert-based-classifiers","title":"FireBERT: Hardening BERT-based classifiers against adversarial attack","date":"2020-08-10","arxiv_id":"2008.04203","n_code_links":1,"syntology":null},{"paper":null,"slug":"ganbert-generative-adversarial-networks-with","title":"GANBERT: Generative Adversarial Networks with Bidirectional Encoder Representations from Transformers for MRI to PET synthesis","date":"2020-08-10","arxiv_id":"2008.04393","n_code_links":0,"syntology":null},{"paper":"/paper/informative-dropout-for-robust-representation","slug":"informative-dropout-for-robust-representation","title":"Informative Dropout for Robust Representation Learning: A Shape-bias Perspective","date":"2020-08-10","arxiv_id":"2008.04254","n_code_links":1,"syntology":null}],"record_sha256":"8725b0f88cc01526444a7c3cbf1ba876dc92df4aca2d3ce899d5c59ed191eb3f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}