{"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/311","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":311,"pages_in_order":375,"rows_per_page":100,"rows":[31001,31100],"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/310","next":"/method/softmax/papers/312","papers":[{"paper":null,"slug":"neural-network-architectures-to-classify","title":"Neural Network architectures to classify emotions in Indian Classical Music","date":"2021-02-01","arxiv_id":"2102.00616","n_code_links":0,"syntology":null},{"paper":null,"slug":"polyphone-disambiguition-in-mandarin-chinese","title":"Polyphone Disambiguation in Mandarin Chinese with Semi-Supervised Learning","date":"2021-02-01","arxiv_id":"2102.00621","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-federated-learning-for-fine-tuning-of","title":"Scaling Federated Learning for Fine-tuning of Large Language Models","date":"2021-02-01","arxiv_id":"2102.00875","n_code_links":0,"syntology":null},{"paper":"/paper/sj-aj-dravidianlangtech-eacl2021-task","slug":"sj-aj-dravidianlangtech-eacl2021-task","title":"SJ_AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification","date":"2021-02-01","arxiv_id":"2102.01051","n_code_links":1,"syntology":null},{"paper":"/paper/text-to-hashtag-generation-using-seq2seq","slug":"text-to-hashtag-generation-using-seq2seq","title":"Text-to-hashtag Generation using Seq2seq Learning","date":"2021-02-01","arxiv_id":"2102.00904","n_code_links":1,"syntology":null},{"paper":"/paper/classification-of-fracture-and-normal","slug":"classification-of-fracture-and-normal","title":"Classification of Shoulder X-Ray Images with Deep Learning Ensemble Models","date":"2021-01-31","arxiv_id":"2102.00515","n_code_links":0,"syntology":null},{"paper":"/paper/computational-performance-predictions-for","slug":"computational-performance-predictions-for","title":"A Runtime-Based Computational Performance Predictor for Deep Neural Network Training","date":"2021-01-31","arxiv_id":"2102.00527","n_code_links":1,"syntology":null},{"paper":"/paper/re-reproducing-learning-to-deceive-with","slug":"re-reproducing-learning-to-deceive-with","title":"[Re] Reproducing Learning to Deceive With Attention-Based Explanations","date":"2021-01-31","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/short-text-clustering-with-transformers","slug":"short-text-clustering-with-transformers","title":"Short Text Clustering with Transformers","date":"2021-01-31","arxiv_id":"2102.00541","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarially-learning-disentangled-speech","title":"Adversarially learning disentangled speech representations for robust multi-factor voice conversion","date":"2021-01-30","arxiv_id":"2102.00184","n_code_links":0,"syntology":null},{"paper":null,"slug":"empathbert-a-bert-based-framework-for","title":"EmpathBERT: A BERT-based Framework for Demographic-aware Empathy Prediction","date":"2021-01-30","arxiv_id":"2102.00272","n_code_links":0,"syntology":null},{"paper":null,"slug":"icodenet-a-hierarchical-neural-network","title":"ICodeNet -- A Hierarchical Neural Network Approach for Source Code Author Identification","date":"2021-01-30","arxiv_id":"2102.00230","n_code_links":0,"syntology":null},{"paper":"/paper/learning-from-how-human-correct","slug":"learning-from-how-human-correct","title":"Learning From Human Correction","date":"2021-01-30","arxiv_id":"2102.00225","n_code_links":1,"syntology":null},{"paper":null,"slug":"shuftext-a-simple-black-box-approach-to","title":"ShufText: A Simple Black Box Approach to Evaluate the Fragility of Text Classification Models","date":"2021-01-30","arxiv_id":"2102.00238","n_code_links":0,"syntology":null},{"paper":null,"slug":"speech-recognition-by-simply-fine-tuning-bert","title":"Speech Recognition by Simply Fine-tuning BERT","date":"2021-01-30","arxiv_id":"2102.00291","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-characteristic-equation-of-the","title":"The characteristic equation of the exceptional Jordan algebra: its eigenvalues, and their possible connection with the mass ratios of quarks and leptons","date":"2021-01-30","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-bert-based-models-for-plant","slug":"fine-tuning-bert-based-models-for-plant","title":"Fine-tuning BERT-based models for Plant Health Bulletin Classification","date":"2021-01-29","arxiv_id":"2102.00838","n_code_links":1,"syntology":null},{"paper":null,"slug":"n-grams-bayesian-differential-privacy","title":"N-grams Bayesian Differential Privacy","date":"2021-01-29","arxiv_id":"2101.12736","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthesizing-monolingual-data-for-neural","title":"Synthesizing Monolingual Data for Neural Machine Translation","date":"2021-01-29","arxiv_id":"2101.12462","n_code_links":0,"syntology":null},{"paper":"/paper/transition-based-graph-decoder-for-neural","slug":"transition-based-graph-decoder-for-neural","title":"Enhancing the Transformer Decoder with Transition-based Syntax","date":"2021-01-29","arxiv_id":"2101.12640","n_code_links":1,"syntology":null},{"paper":"/paper/a-graph-based-relevance-matching-model-for-ad","slug":"a-graph-based-relevance-matching-model-for-ad","title":"A Graph-based Relevance Matching Model for Ad-hoc Retrieval","date":"2021-01-28","arxiv_id":"2101.11873","n_code_links":1,"syntology":null},{"paper":null,"slug":"augmenting-proposals-by-the-detector-itself","title":"Augmenting Proposals by the Detector Itself","date":"2021-01-28","arxiv_id":"2101.11789","n_code_links":0,"syntology":null},{"paper":null,"slug":"bertau-itau-bert-for-digital-customer-service","title":"BERTaú: Itaú BERT for digital customer service","date":"2021-01-28","arxiv_id":"2101.12015","n_code_links":0,"syntology":null},{"paper":null,"slug":"consequence-of-enterprise-resource-planning","title":"Consequence of Enterprise Resource Planning in the Environs of Pedagogical Organization.","date":"2021-01-28","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"consequence-of-enterprise-resource-planning-1","title":"Consequence of Enterprise Resource Planning in the Environs of Pedagogical Organization.","date":"2021-01-28","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lstm-sakt-lstm-encoded-sakt-like-transformer","title":"LSTM-SAKT: LSTM-Encoded SAKT-like Transformer for Knowledge Tracing","date":"2021-01-28","arxiv_id":"2102.00845","n_code_links":0,"syntology":null},{"paper":null,"slug":"s-a-fast-and-deployable-secure-computation","title":"S++: A Fast and Deployable Secure-Computation Framework for Privacy-Preserving Neural Network Training","date":"2021-01-28","arxiv_id":"2101.12078","n_code_links":0,"syntology":null},{"paper":"/paper/tokens-to-token-vit-training-vision","slug":"tokens-to-token-vit-training-vision","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","date":"2021-01-28","arxiv_id":"2101.11986","n_code_links":13,"syntology":{"ran":21,"of":26,"n_ran_checked":21,"n_instrument":0,"unverified":5,"pointer_only":8,"phrase":"21 ran (of which 16 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["yitu-opensource/T2T-ViT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"an-explainable-transformer-based-deep","title":"An explainable Transformer-based deep learning model for the prediction of incident heart failure","date":"2021-01-27","arxiv_id":"2101.11359","n_code_links":0,"syntology":null},{"paper":"/paper/bottleneck-transformers-for-visual","slug":"bottleneck-transformers-for-visual","title":"Bottleneck Transformers for Visual Recognition","date":"2021-01-27","arxiv_id":"2101.11605","n_code_links":13,"syntology":{"ran":26,"of":49,"n_ran_checked":19,"n_instrument":7,"unverified":23,"pointer_only":8,"phrase":"26 ran (of which 9 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 7 where Syntology's instrument failed) · 23 unverified","official":null}},{"paper":"/paper/exploring-multi-task-multi-lingual-learning","slug":"exploring-multi-task-multi-lingual-learning","title":"Exploring multi-task multi-lingual learning of transformer models for hate speech and offensive speech identification in social media","date":"2021-01-27","arxiv_id":"2101.11155","n_code_links":1,"syntology":null},{"paper":null,"slug":"korealbert-pretraining-a-lite-bert-model-for","title":"KoreALBERT: Pretraining a Lite BERT Model for Korean Language Understanding","date":"2021-01-27","arxiv_id":"2101.11363","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-evolution-of-syntactic-information","title":"On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations","date":"2021-01-27","arxiv_id":"2101.11492","n_code_links":0,"syntology":null},{"paper":null,"slug":"spatial-channel-transformer-network-for","title":"Spatial-Channel Transformer Network for Trajectory Prediction on the Traffic Scenes","date":"2021-01-27","arxiv_id":"2101.11472","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-zero-shot-cross-lingual-transfer-in","title":"Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP Tasks","date":"2021-01-26","arxiv_id":"2101.10649","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-can-reflect-syntactic-structure-if","title":"Attention Can Reflect Syntactic Structure (If You Let It)","date":"2021-01-26","arxiv_id":"2101.10927","n_code_links":0,"syntology":null},{"paper":null,"slug":"climp-a-benchmark-for-chinese-language-model","title":"CLiMP: A Benchmark for Chinese Language Model Evaluation","date":"2021-01-26","arxiv_id":"2101.11131","n_code_links":0,"syntology":null},{"paper":null,"slug":"coloring-the-black-box-what-synesthesia-tells","title":"Coloring the Black Box: What Synesthesia Tells Us about Character Embeddings","date":"2021-01-26","arxiv_id":"2101.10565","n_code_links":0,"syntology":null},{"paper":null,"slug":"cptr-full-transformer-network-for-image","title":"CPTR: Full Transformer Network for Image Captioning","date":"2021-01-26","arxiv_id":"2101.10804","n_code_links":0,"syntology":null},{"paper":"/paper/deep-subjecthood-higher-order-grammatical","slug":"deep-subjecthood-higher-order-grammatical","title":"Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERT","date":"2021-01-26","arxiv_id":"2101.11043","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-bert-and-albert-sentence","title":"Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks","date":"2021-01-26","arxiv_id":"2101.10642","n_code_links":0,"syntology":null},{"paper":"/paper/first-align-then-predict-understanding-the","slug":"first-align-then-predict-understanding-the","title":"First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT","date":"2021-01-26","arxiv_id":"2101.11109","n_code_links":1,"syntology":null},{"paper":null,"slug":"named-entity-recognition-in-the-style-of","title":"Named Entity Recognition in the Style of Object Detection","date":"2021-01-26","arxiv_id":"2101.11122","n_code_links":0,"syntology":null},{"paper":null,"slug":"regulatory-compliance-through-doc2doc","title":"Regulatory Compliance through Doc2Doc Information Retrieval: A case study in EU/UK legislation where text similarity has limitations","date":"2021-01-26","arxiv_id":"2101.10726","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthetic-generation-of-three-dimensional","title":"Synthetic Generation of Three-Dimensional Cancer Cell Models from Histopathological Images","date":"2021-01-26","arxiv_id":"2101.11600","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-wireless-control-bus-enabling-efficient","title":"The Wireless Control Bus: Enabling Efficient Multi-hop Event-Triggered Control with Concurrent Transmissions","date":"2021-01-26","arxiv_id":"2101.10961","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hybrid-approach-to-measure-semantic","title":"A Hybrid Approach to Measure Semantic Relatedness in Biomedical Concepts","date":"2021-01-25","arxiv_id":"2101.10196","n_code_links":0,"syntology":null},{"paper":"/paper/egfi-drug-drug-interaction-extraction-and","slug":"egfi-drug-drug-interaction-extraction-and","title":"EGFI: Drug-Drug Interaction Extraction and Generation with Fusion of Enriched Entity and Sentence Information","date":"2021-01-25","arxiv_id":"2101.09914","n_code_links":1,"syntology":null},{"paper":"/paper/multiface-a-generic-training-mechanism-for","slug":"multiface-a-generic-training-mechanism-for","title":"MultiFace: A Generic Training Mechanism for Boosting Face Recognition Performance","date":"2021-01-25","arxiv_id":"2101.09899","n_code_links":1,"syntology":null},{"paper":null,"slug":"randomized-deep-structured-prediction-for","title":"Randomized Deep Structured Prediction for Discourse-Level Processing","date":"2021-01-25","arxiv_id":"2101.10435","n_code_links":0,"syntology":null},{"paper":"/paper/densenet-for-breast-tumor-classification-in","slug":"densenet-for-breast-tumor-classification-in","title":"DenseNet for Breast Tumor Classification in Mammographic Images","date":"2021-01-24","arxiv_id":"2101.09637","n_code_links":2,"syntology":null},{"paper":null,"slug":"does-dialog-length-matter-for-next-response","title":"Does Dialog Length matter for Next Response Selection task? An Empirical Study","date":"2021-01-24","arxiv_id":"2101.09647","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-time-series-forecasting-with","title":"Multi-Task Time Series Forecasting With Shared Attention","date":"2021-01-24","arxiv_id":"2101.09645","n_code_links":0,"syntology":null},{"paper":"/paper/romebert-robust-training-of-multi-exit-bert","slug":"romebert-robust-training-of-multi-exit-bert","title":"RomeBERT: Robust Training of Multi-Exit BERT","date":"2021-01-24","arxiv_id":"2101.09755","n_code_links":1,"syntology":null},{"paper":"/paper/stereotype-and-skew-quantifying-gender-bias","slug":"stereotype-and-skew-quantifying-gender-bias","title":"Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models","date":"2021-01-24","arxiv_id":"2101.09688","n_code_links":1,"syntology":null},{"paper":"/paper/towards-a-better-integration-of-fuzzy-matches","slug":"towards-a-better-integration-of-fuzzy-matches","title":"Towards a Better Integration of Fuzzy Matches in Neural Machine Translation through Data Augmentation","date":"2021-01-24","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/training-multilingual-pre-trained-language","slug":"training-multilingual-pre-trained-language","title":"Training Multilingual Pre-trained Language Model with Byte-level Subwords","date":"2021-01-23","arxiv_id":"2101.09469","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-perspective-combined-recall-and-rank","title":"A multi-perspective combined recall and rank framework for Chinese procedure terminology normalization","date":"2021-01-22","arxiv_id":"2101.09101","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-transformer-model-for-detecting-arabic","title":"BERT Transformer model for Detecting Arabic GPT2 Auto-Generated Tweets","date":"2021-01-22","arxiv_id":"2101.09345","n_code_links":0,"syntology":null},{"paper":"/paper/drug-and-disease-interpretation-learning-with","slug":"drug-and-disease-interpretation-learning-with","title":"Drug and Disease Interpretation Learning with Biomedical Entity Representation Transformer","date":"2021-01-22","arxiv_id":"2101.09311","n_code_links":1,"syntology":null},{"paper":null,"slug":"enriching-non-autoregressive-transformer-with","title":"Enriching Non-Autoregressive Transformer with Syntactic and SemanticStructures for Neural Machine Translation","date":"2021-01-22","arxiv_id":"2101.08942","n_code_links":0,"syntology":null},{"paper":null,"slug":"expression-recognition-analysis-in-the-wild","title":"Expression Recognition Analysis in the Wild","date":"2021-01-22","arxiv_id":"2101.09231","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-lifestyle-factors-for-alzheimer-s","title":"Extracting Lifestyle Factors for Alzheimer's Disease from Clinical Notes Using Deep Learning with Weak Supervision","date":"2021-01-22","arxiv_id":"2101.09244","n_code_links":0,"syntology":null},{"paper":"/paper/hasocone-fire-hasoc2020-using-bert-and","slug":"hasocone-fire-hasoc2020-using-bert-and","title":"HASOCOne@FIRE-HASOC2020: Using BERT and Multilingual BERT models for Hate Speech Detection","date":"2021-01-22","arxiv_id":"2101.09007","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-pre-trained-transformers-and","title":"Multilingual Pre-Trained Transformers and Convolutional NN Classification Models for Technical Domain Identification","date":"2021-01-22","arxiv_id":"2101.09012","n_code_links":0,"syntology":null},{"paper":null,"slug":"solving-the-same-different-task-with","title":"Solving the Same-Different Task with Convolutional Neural Networks","date":"2021-01-22","arxiv_id":"2101.09129","n_code_links":0,"syntology":null},{"paper":"/paper/the-heads-hypothesis-a-unifying-statistical","slug":"the-heads-hypothesis-a-unifying-statistical","title":"The heads hypothesis: A unifying statistical approach towards understanding multi-headed attention in BERT","date":"2021-01-22","arxiv_id":"2101.09115","n_code_links":1,"syntology":null},{"paper":null,"slug":"visual-question-answering-based-on-local","title":"Visual Question Answering based on Local-Scene-Aware Referring Expression Generation","date":"2021-01-22","arxiv_id":"2101.08978","n_code_links":0,"syntology":null},{"paper":"/paper/activity-graph-transformer-for-temporal","slug":"activity-graph-transformer-for-temporal","title":"Activity Graph Transformer for Temporal Action Localization","date":"2021-01-21","arxiv_id":"2101.08540","n_code_links":0,"syntology":null},{"paper":"/paper/daf-re-a-challenging-crowd-sourced-large","slug":"daf-re-a-challenging-crowd-sourced-large","title":"DAF:re: A Challenging, Crowd-Sourced, Large-Scale, Long-Tailed Dataset For Anime Character Recognition","date":"2021-01-21","arxiv_id":"2101.08674","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":["arkel23/animesion"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/evaluating-multilingual-text-encoders-for","slug":"evaluating-multilingual-text-encoders-for","title":"Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval","date":"2021-01-21","arxiv_id":"2101.08370","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":["rlitschk/EncoderCLIR"],"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":"/paper/ghostsr-learning-ghost-features-for-efficient","slug":"ghostsr-learning-ghost-features-for-efficient","title":"GhostSR: Learning Ghost Features for Efficient Image Super-Resolution","date":"2021-01-21","arxiv_id":"2101.08525","n_code_links":4,"syntology":null},{"paper":"/paper/learn-to-dance-with-aist-music-conditioned-3d","slug":"learn-to-dance-with-aist-music-conditioned-3d","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","date":"2021-01-21","arxiv_id":"2101.08779","n_code_links":1,"syntology":null},{"paper":null,"slug":"active-learning-for-sequence-tagging-with","title":"Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates","date":"2021-01-20","arxiv_id":"2101.08133","n_code_links":0,"syntology":null},{"paper":"/paper/classifying-scientific-publications-with-bert","slug":"classifying-scientific-publications-with-bert","title":"Classifying Scientific Publications with BERT -- Is Self-Attention a Feature Selection Method?","date":"2021-01-20","arxiv_id":"2101.08114","n_code_links":1,"syntology":null},{"paper":"/paper/divide-and-conquer-an-ensemble-approach-for","slug":"divide-and-conquer-an-ensemble-approach-for","title":"Divide and Conquer: An Ensemble Approach for Hostile Post Detection in Hindi","date":"2021-01-20","arxiv_id":"2101.07973","n_code_links":1,"syntology":null},{"paper":null,"slug":"fooling-thermal-infrared-pedestrian-detectors","title":"Fooling thermal infrared pedestrian detectors in real world using small bulbs","date":"2021-01-20","arxiv_id":"2101.08154","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-augment-for-data-scarce-domain","slug":"learning-to-augment-for-data-scarce-domain","title":"Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation","date":"2021-01-20","arxiv_id":"2101.08106","n_code_links":0,"syntology":{"ran":2,"of":15,"n_ran_checked":2,"n_instrument":0,"unverified":13,"pointer_only":15,"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) · 13 unverified","official":null}},{"paper":"/paper/open-domain-conversational-search-assistant","slug":"open-domain-conversational-search-assistant","title":"Open-Domain Conversational Search Assistant with Transformers","date":"2021-01-20","arxiv_id":"2101.08197","n_code_links":1,"syntology":null},{"paper":"/paper/pgt-pseudo-relevance-feedback-using-a-graph","slug":"pgt-pseudo-relevance-feedback-using-a-graph","title":"PGT: Pseudo Relevance Feedback Using a Graph-Based Transformer","date":"2021-01-20","arxiv_id":"2101.07918","n_code_links":1,"syntology":null},{"paper":"/paper/updet-universal-multi-agent-reinforcement","slug":"updet-universal-multi-agent-reinforcement","title":"UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers","date":"2021-01-20","arxiv_id":"2101.08001","n_code_links":1,"syntology":null},{"paper":"/paper/fast-convergence-of-detr-with-spatially","slug":"fast-convergence-of-detr-with-spatially","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","date":"2021-01-19","arxiv_id":"2101.07448","n_code_links":2,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["gaopengcuhk/SMCA-DETR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/situation-and-behavior-understanding-by-trope","slug":"situation-and-behavior-understanding-by-trope","title":"Situation and Behavior Understanding by Trope Detection on Films","date":"2021-01-19","arxiv_id":"2101.07632","n_code_links":1,"syntology":null},{"paper":"/paper/towards-facilitating-empathic-conversations","slug":"towards-facilitating-empathic-conversations","title":"Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach","date":"2021-01-19","arxiv_id":"2101.07714","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-punctuation-restoration-with-bert","slug":"automatic-punctuation-restoration-with-bert","title":"Automatic punctuation restoration with BERT models","date":"2021-01-18","arxiv_id":"2101.07343","n_code_links":1,"syntology":null},{"paper":"/paper/can-a-fruit-fly-learn-word-embeddings-1","slug":"can-a-fruit-fly-learn-word-embeddings-1","title":"Can a Fruit Fly Learn Word Embeddings?","date":"2021-01-18","arxiv_id":"2101.06887","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/inference-for-bart-with-multinomial-outcomes","slug":"inference-for-bart-with-multinomial-outcomes","title":"Inference for BART with Multinomial Outcomes","date":"2021-01-18","arxiv_id":"2101.06823","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-select-for-mimo-radar-based-on","title":"Learning to Select for MIMO Radar based on Hybrid Analog-Digital Beamforming","date":"2021-01-18","arxiv_id":"2101.06837","n_code_links":0,"syntology":null},{"paper":null,"slug":"tlu-net-a-deep-learning-approach-for","title":"TLU-Net: A Deep Learning Approach for Automatic Steel Surface Defect Detection","date":"2021-01-18","arxiv_id":"2101.06915","n_code_links":0,"syntology":null},{"paper":null,"slug":"cost-efficient-online-hyperparameter","title":"Cost-Efficient Online Hyperparameter Optimization","date":"2021-01-17","arxiv_id":"2101.06590","n_code_links":0,"syntology":null},{"paper":"/paper/dual-level-collaborative-transformer-for","slug":"dual-level-collaborative-transformer-for","title":"Dual-Level Collaborative Transformer for Image Captioning","date":"2021-01-16","arxiv_id":"2101.06462","n_code_links":1,"syntology":null},{"paper":"/paper/match-ignition-plugging-pagerank-into","slug":"match-ignition-plugging-pagerank-into","title":"Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching","date":"2021-01-16","arxiv_id":"2101.06423","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-models-for-question","title":"Transformer-Based Models for Question Answering on COVID19","date":"2021-01-16","arxiv_id":"2101.11432","n_code_links":0,"syntology":null},{"paper":null,"slug":"grid-search-hyperparameter-benchmarking-of","title":"Grid Search Hyperparameter Benchmarking of BERT, ALBERT, and LongFormer on DuoRC","date":"2021-01-15","arxiv_id":"2101.06326","n_code_links":0,"syntology":null},{"paper":null,"slug":"hostility-detection-and-covid-19-fake-news","title":"Hostility Detection and Covid-19 Fake News Detection in Social Media","date":"2021-01-15","arxiv_id":"2101.05953","n_code_links":0,"syntology":null},{"paper":null,"slug":"kdlsq-bert-a-quantized-bert-combining","title":"KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization","date":"2021-01-15","arxiv_id":"2101.05938","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-computed-aided-diagnosis-system-in","title":"Towards a Computed-Aided Diagnosis System in Colonoscopy: Automatic Polyp Segmentation Using Convolution Neural Networks","date":"2021-01-15","arxiv_id":"2101.06040","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multiple-classifier-approach-for","title":"A Multiple Classifier Approach for Concatenate-Designed Neural Networks","date":"2021-01-14","arxiv_id":"2101.05457","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-pipeline-for-vision-based-on-orbit","title":"A Pipeline for Vision-Based On-Orbit Proximity Operations Using Deep Learning and Synthetic Imagery","date":"2021-01-14","arxiv_id":"2101.05661","n_code_links":0,"syntology":null},{"paper":"/paper/attention-based-second-order-pooling-network","slug":"attention-based-second-order-pooling-network","title":"Attention-Based Second-Order Pooling Network for Hyperspectral Image Classification","date":"2021-01-14","arxiv_id":null,"n_code_links":1,"syntology":null}],"record_sha256":"c95eda48e2a86bf11db087f0d41f8bc18fb9c96db87f546041323e285765386e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}