{"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/334","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":334,"pages_in_order":375,"rows_per_page":100,"rows":[33301,33400],"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/333","next":"/method/softmax/papers/335","papers":[{"paper":null,"slug":"adversarial-nli-for-factual-correctness-in","title":"Adversarial NLI for Factual Correctness in Text Summarisation Models","date":"2020-05-24","arxiv_id":"2005.11739","n_code_links":0,"syntology":null},{"paper":"/paper/jointly-encoding-word-confusion-network-and","slug":"jointly-encoding-word-confusion-network-and","title":"Jointly Encoding Word Confusion Network and Dialogue Context with BERT for Spoken Language Understanding","date":"2020-05-24","arxiv_id":"2005.11640","n_code_links":1,"syntology":null},{"paper":"/paper/mask-a-flexible-framework-to-facilitate-de","slug":"mask-a-flexible-framework-to-facilitate-de","title":"MASK: A flexible framework to facilitate de-identification of clinical texts","date":"2020-05-24","arxiv_id":"2005.11687","n_code_links":1,"syntology":null},{"paper":"/paper/robust-object-detection-under-occlusion-with","slug":"robust-object-detection-under-occlusion-with","title":"Robust Object Detection under Occlusion with Context-Aware CompositionalNets","date":"2020-05-24","arxiv_id":"2005.11643","n_code_links":0,"syntology":null},{"paper":"/paper/stronger-baselines-for-grammatical-error","slug":"stronger-baselines-for-grammatical-error","title":"Stronger Baselines for Grammatical Error Correction Using Pretrained Encoder-Decoder Model","date":"2020-05-24","arxiv_id":"2005.11849","n_code_links":2,"syntology":null},{"paper":null,"slug":"coronavirus-comparing-covid-19-sars-and-mers","title":"Deep Learning for Reliable Classification of COVID-19, MERS, and SARS from Chest X-Ray Images","date":"2020-05-23","arxiv_id":"2005.11524","n_code_links":0,"syntology":null},{"paper":null,"slug":"devising-malware-characterstics-using","title":"Devising Malware Characterstics using Transformers","date":"2020-05-23","arxiv_id":"2005.12978","n_code_links":0,"syntology":null},{"paper":null,"slug":"joint-training-capsule-network-for-cold-start","title":"Joint Training Capsule Network for Cold Start Recommendation","date":"2020-05-23","arxiv_id":"2005.11467","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-training-for-domain-adaptive-scene-text","title":"Self-Training for Domain Adaptive Scene Text Detection","date":"2020-05-23","arxiv_id":"2005.11487","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-generative-approach-to-titling-and","title":"A Generative Approach to Titling and Clustering Wikipedia Sections","date":"2020-05-22","arxiv_id":"2005.11216","n_code_links":0,"syntology":null},{"paper":null,"slug":"character-level-transformer-based-neural","title":"Character-level Transformer-based Neural Machine Translation","date":"2020-05-22","arxiv_id":"2005.11239","n_code_links":0,"syntology":null},{"paper":"/paper/comparative-study-of-machine-learning-models","slug":"comparative-study-of-machine-learning-models","title":"Comparative Study of Machine Learning Models and BERT on SQuAD","date":"2020-05-22","arxiv_id":"2005.11313","n_code_links":1,"syntology":null},{"paper":null,"slug":"kl-divergence-based-region-proposal-network","title":"KL-Divergence-Based Region Proposal Network for Object Detection","date":"2020-05-22","arxiv_id":"2005.11220","n_code_links":0,"syntology":null},{"paper":"/paper/l2r2-leveraging-ranking-for-abductive","slug":"l2r2-leveraging-ranking-for-abductive","title":"L2R2: Leveraging Ranking for Abductive Reasoning","date":"2020-05-22","arxiv_id":"2005.11223","n_code_links":1,"syntology":null},{"paper":"/paper/living-machines-a-study-of-atypical-animacy","slug":"living-machines-a-study-of-atypical-animacy","title":"Living Machines: A study of atypical animacy","date":"2020-05-22","arxiv_id":"2005.11140","n_code_links":1,"syntology":null},{"paper":"/paper/low-latency-sequence-to-sequence-speech","slug":"low-latency-sequence-to-sequence-speech","title":"Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection","date":"2020-05-22","arxiv_id":"2005.11185","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dannigt/NMTGMinor.lowLatency"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/med-bert-pre-trained-contextualized","slug":"med-bert-pre-trained-contextualized","title":"Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction","date":"2020-05-22","arxiv_id":"2005.12833","n_code_links":1,"syntology":null},{"paper":"/paper/retrieval-augmented-generation-for-knowledge","slug":"retrieval-augmented-generation-for-knowledge","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","date":"2020-05-22","arxiv_id":"2005.11401","n_code_links":18,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"robust-layout-aware-ie-for-visually-rich","title":"Robust Layout-aware IE for Visually Rich Documents with Pre-trained Language Models","date":"2020-05-22","arxiv_id":"2005.11017","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-context-aware-sarcasm","title":"Transformer-based Context-aware Sarcasm Detection in Conversation Threads from Social Media","date":"2020-05-22","arxiv_id":"2005.11424","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-deep-convolutional-neural","title":"Evaluation of deep convolutional neural networks in classifying human embryo images based on their morphological quality","date":"2020-05-21","arxiv_id":"2005.10912","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-text-data-using-hybrid-transformer","title":"Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning","date":"2020-05-21","arxiv_id":"2005.10407","n_code_links":0,"syntology":null},{"paper":null,"slug":"powering-one-shot-topological-nas-with","title":"Powering One-shot Topological NAS with Stabilized Share-parameter Proxy","date":"2020-05-21","arxiv_id":"2005.10511","n_code_links":0,"syntology":null},{"paper":null,"slug":"simplified-self-attention-for-transformer","title":"Simplified Self-Attention for Transformer-based End-to-End Speech Recognition","date":"2020-05-21","arxiv_id":"2005.10463","n_code_links":0,"syntology":null},{"paper":null,"slug":"taso-time-and-space-optimization-for-memory","title":"TASO: Time and Space Optimization for Memory-Constrained DNN Inference","date":"2020-05-21","arxiv_id":"2005.10709","n_code_links":0,"syntology":null},{"paper":"/paper/text-to-text-pre-training-for-data-to-text","slug":"text-to-text-pre-training-for-data-to-text","title":"Text-to-Text Pre-Training for Data-to-Text Tasks","date":"2020-05-21","arxiv_id":"2005.10433","n_code_links":2,"syntology":null},{"paper":"/paper/a-further-study-of-unsupervised-pre-training","slug":"a-further-study-of-unsupervised-pre-training","title":"A Further Study of Unsupervised Pre-training for Transformer Based Speech Recognition","date":"2020-05-20","arxiv_id":"2005.09862","n_code_links":1,"syntology":null},{"paper":"/paper/a-modified-deep-convolutional-neural-network","slug":"a-modified-deep-convolutional-neural-network","title":"A modified deep convolutional neural network for detecting COVID-19 and pneumonia from chest X-ray images based on the concatenation of Xception and ResNet50V2","date":"2020-05-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/applying-the-transformer-to-character-level","slug":"applying-the-transformer-to-character-level","title":"Applying the Transformer to Character-level Transduction","date":"2020-05-20","arxiv_id":"2005.10213","n_code_links":3,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["shijie-wu/neural-transducer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":"/paper/bertweet-a-pre-trained-language-model-for","slug":"bertweet-a-pre-trained-language-model-for","title":"BERTweet: A pre-trained language model for English Tweets","date":"2020-05-20","arxiv_id":"2005.10200","n_code_links":3,"syntology":null},{"paper":null,"slug":"classification-of-industrial-control-systems","title":"Classification of Industrial Control Systems screenshots using Transfer Learning","date":"2020-05-20","arxiv_id":"2005.10098","n_code_links":0,"syntology":null},{"paper":"/paper/creative-artificial-intelligence-algorithms","slug":"creative-artificial-intelligence-algorithms","title":"Artificial Intelligence versus Maya Angelou: Experimental evidence that people cannot differentiate AI-generated from human-written poetry","date":"2020-05-20","arxiv_id":"2005.09980","n_code_links":1,"syntology":null},{"paper":"/paper/fashionbert-text-and-image-matching-with","slug":"fashionbert-text-and-image-matching-with","title":"FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrieval","date":"2020-05-20","arxiv_id":"2005.09801","n_code_links":3,"syntology":null},{"paper":null,"slug":"investigation-of-large-margin-softmax-in","title":"Investigation of Large-Margin Softmax in Neural Language Modeling","date":"2020-05-20","arxiv_id":"2005.10089","n_code_links":0,"syntology":null},{"paper":"/paper/reducing-overlearning-through-disentangled","slug":"reducing-overlearning-through-disentangled","title":"Reducing Overlearning through Disentangled Representations by Suppressing Unknown Tasks","date":"2020-05-20","arxiv_id":"2005.10220","n_code_links":1,"syntology":null},{"paper":null,"slug":"relative-positional-encoding-for-speech","title":"Relative Positional Encoding for Speech Recognition and Direct Translation","date":"2020-05-20","arxiv_id":"2005.09940","n_code_links":0,"syntology":null},{"paper":"/paper/comparing-transformers-and-rnns-on-predicting","slug":"comparing-transformers-and-rnns-on-predicting","title":"Human Sentence Processing: Recurrence or Attention?","date":"2020-05-19","arxiv_id":"2005.09471","n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-lingual-transfer-learning-for-dialogue","title":"Cross-lingual Approaches for Task-specific Dialogue Act Recognition","date":"2020-05-19","arxiv_id":"2005.09260","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-transformers-for-large-scale-speech","title":"Exploring Transformers for Large-Scale Speech Recognition","date":"2020-05-19","arxiv_id":"2005.09684","n_code_links":0,"syntology":null},{"paper":null,"slug":"maskface-multi-task-face-and-landmark","title":"MaskFace: multi-task face and landmark detector","date":"2020-05-19","arxiv_id":"2005.09412","n_code_links":0,"syntology":null},{"paper":"/paper/normalized-attention-without-probability-cage","slug":"normalized-attention-without-probability-cage","title":"Normalized Attention Without Probability Cage","date":"2020-05-19","arxiv_id":"2005.09561","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["OliverRichter/normalized-attention"],"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/self-supervised-transfer-learning-for","slug":"self-supervised-transfer-learning-for","title":"Self-supervised Transfer Learning for Instance Segmentation through Physical Interaction","date":"2020-05-19","arxiv_id":"2005.09484","n_code_links":1,"syntology":null},{"paper":"/paper/should-we-hard-code-the-recurrence-concept-or","slug":"should-we-hard-code-the-recurrence-concept-or","title":"Should we hard-code the recurrence concept or learn it instead ? Exploring the Transformer architecture for Audio-Visual Speech Recognition","date":"2020-05-19","arxiv_id":"2005.09297","n_code_links":1,"syntology":null},{"paper":"/paper/sketch-bert-learning-sketch-bidirectional","slug":"sketch-bert-learning-sketch-bidirectional","title":"Sketch-BERT: Learning Sketch Bidirectional Encoder Representation from Transformers by Self-supervised Learning of Sketch Gestalt","date":"2020-05-19","arxiv_id":"2005.09159","n_code_links":1,"syntology":null},{"paper":null,"slug":"synthesizing-unrestricted-false-positive","title":"Synthesizing Unrestricted False Positive Adversarial Objects Using Generative Models","date":"2020-05-19","arxiv_id":"2005.09294","n_code_links":0,"syntology":null},{"paper":"/paper/table-search-using-a-deep-contextualized","slug":"table-search-using-a-deep-contextualized","title":"Table Search Using a Deep Contextualized Language Model","date":"2020-05-19","arxiv_id":"2005.09207","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-transformer-based-embedding-model-for","title":"A Transformer-based Embedding Model for Personalized Product Search","date":"2020-05-18","arxiv_id":"2005.08936","n_code_links":0,"syntology":null},{"paper":"/paper/are-all-languages-created-equal-in","slug":"are-all-languages-created-equal-in","title":"Are All Languages Created Equal in Multilingual BERT?","date":"2020-05-18","arxiv_id":"2005.09093","n_code_links":1,"syntology":null},{"paper":"/paper/audio-albert-a-lite-bert-for-self-supervised","slug":"audio-albert-a-lite-bert-for-self-supervised","title":"Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation","date":"2020-05-18","arxiv_id":"2005.08575","n_code_links":4,"syntology":null},{"paper":null,"slug":"bayesian-convolutional-neural-network-based","title":"Bayesian convolutional neural network based MRI brain extraction on nonhuman primates","date":"2020-05-18","arxiv_id":"2005.08460","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-filter-compression-for-cnn-inference","title":"Cross-filter compression for CNN inference acceleration","date":"2020-05-18","arxiv_id":"2005.09034","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-wait-k-models-for-simultaneous","slug":"efficient-wait-k-models-for-simultaneous","title":"Efficient Wait-k Models for Simultaneous Machine Translation","date":"2020-05-18","arxiv_id":"2005.08595","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["elbayadm/attn2d"],"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":null,"slug":"entropy-augmented-entropy-regularized","title":"Entropy-Augmented Entropy-Regularized Reinforcement Learning and a Continuous Path from Policy Gradient to Q-Learning","date":"2020-05-18","arxiv_id":"2005.08844","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-too-a-language-model-first-approach-for","slug":"gpt-too-a-language-model-first-approach-for","title":"GPT-too: A language-model-first approach for AMR-to-text generation","date":"2020-05-18","arxiv_id":"2005.09123","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["IBM/GPT-too-AMR2text"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"large-scale-object-detection-in-the-wild-from","title":"Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels","date":"2020-05-18","arxiv_id":"2005.08455","n_code_links":0,"syntology":null},{"paper":null,"slug":"many-to-many-voice-transformer-network","title":"Many-to-Many Voice Transformer Network","date":"2020-05-18","arxiv_id":"2005.08445","n_code_links":0,"syntology":null},{"paper":null,"slug":"semeval-2020-task-5-detecting-counterfactuals","title":"Yseop at SemEval-2020 Task 5: Cascaded BERT Language Model for Counterfactual Statement Analysis","date":"2020-05-18","arxiv_id":"2005.08519","n_code_links":0,"syntology":null},{"paper":"/paper/spatio-temporal-graph-transformer-networks","slug":"spatio-temporal-graph-transformer-networks","title":"Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction","date":"2020-05-18","arxiv_id":"2005.08514","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["Majiker/STAR"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"weak-attention-suppression-for-transformer","title":"Weak-Attention Suppression For Transformer Based Speech Recognition","date":"2020-05-18","arxiv_id":"2005.09137","n_code_links":0,"syntology":null},{"paper":"/paper/a-better-use-of-audio-visual-cues-dense-video","slug":"a-better-use-of-audio-visual-cues-dense-video","title":"A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer","date":"2020-05-17","arxiv_id":"2005.08271","n_code_links":2,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"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":{"repos":["v-iashin/BMT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/adversarial-training-for-commonsense","slug":"adversarial-training-for-commonsense","title":"Adversarial Training for Commonsense Inference","date":"2020-05-17","arxiv_id":"2005.08156","n_code_links":1,"syntology":null},{"paper":"/paper/building-a-hebrew-semantic-role-labeling","slug":"building-a-hebrew-semantic-role-labeling","title":"Building a Hebrew Semantic Role Labeling Lexical Resource from Parallel Movie Subtitles","date":"2020-05-17","arxiv_id":"2005.08206","n_code_links":1,"syntology":null},{"paper":null,"slug":"context-based-quotation-recommendation","title":"Context-Based Quotation Recommendation","date":"2020-05-17","arxiv_id":"2005.08319","n_code_links":0,"syntology":null},{"paper":"/paper/cross-lingual-low-resource-set-to-description","slug":"cross-lingual-low-resource-set-to-description","title":"Cross-Lingual Low-Resource Set-to-Description Retrieval for Global E-Commerce","date":"2020-05-17","arxiv_id":"2005.08188","n_code_links":1,"syntology":null},{"paper":null,"slug":"support-bert-predicting-quality-of-question","title":"Support-BERT: Predicting Quality of Question-Answer Pairs in MSDN using Deep Bidirectional Transformer","date":"2020-05-17","arxiv_id":"2005.08294","n_code_links":0,"syntology":null},{"paper":"/paper/tabert-pretraining-for-joint-understanding-of","slug":"tabert-pretraining-for-joint-understanding-of","title":"TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data","date":"2020-05-17","arxiv_id":"2005.08314","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-deep-learning-based-wearable-healthcare-iot","title":"A Deep Learning based Wearable Healthcare IoT Device for AI-enabled Hearing Assistance Automation","date":"2020-05-16","arxiv_id":"2005.08076","n_code_links":0,"syntology":null},{"paper":null,"slug":"cert-contrastive-self-supervised-learning-for","title":"CERT: Contrastive Self-supervised Learning for Language Understanding","date":"2020-05-16","arxiv_id":"2005.12766","n_code_links":0,"syntology":null},{"paper":"/paper/conformer-convolution-augmented-transformer","slug":"conformer-convolution-augmented-transformer","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","date":"2020-05-16","arxiv_id":"2005.08100","n_code_links":25,"syntology":{"ran":6,"of":7,"n_ran_checked":5,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"intellicode-compose-code-generation-using","title":"IntelliCode Compose: Code Generation Using Transformer","date":"2020-05-16","arxiv_id":"2005.08025","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-affective-bidirectional-1","title":"Leveraging Affective Bidirectional Transformers for Offensive Language Detection","date":"2020-05-16","arxiv_id":"2006.01266","n_code_links":0,"syntology":null},{"paper":"/paper/recurrent-chunking-mechanisms-for-long-text","slug":"recurrent-chunking-mechanisms-for-long-text","title":"Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehension","date":"2020-05-16","arxiv_id":"2005.08056","n_code_links":1,"syntology":null},{"paper":null,"slug":"spike-triggered-non-autoregressive","title":"Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition","date":"2020-05-16","arxiv_id":"2005.07903","n_code_links":0,"syntology":null},{"paper":null,"slug":"streaming-transformer-based-acoustic-models","title":"Streaming Transformer-based Acoustic Models Using Self-attention with Augmented Memory","date":"2020-05-16","arxiv_id":"2005.08042","n_code_links":0,"syntology":null},{"paper":"/paper/challenges-in-emotion-style-transfer-an","slug":"challenges-in-emotion-style-transfer-an","title":"Challenges in Emotion Style Transfer: An Exploration with a Lexical Substitution Pipeline","date":"2020-05-15","arxiv_id":"2005.07617","n_code_links":1,"syntology":null},{"paper":null,"slug":"contextualizing-asr-lattice-rescoring-with","title":"Contextualizing ASR Lattice Rescoring with Hybrid Pointer Network Language Model","date":"2020-05-15","arxiv_id":"2005.07394","n_code_links":0,"syntology":null},{"paper":"/paper/covid-twitter-bert-a-natural-language","slug":"covid-twitter-bert-a-natural-language","title":"COVID-Twitter-BERT: A Natural Language Processing Model to Analyse COVID-19 Content on Twitter","date":"2020-05-15","arxiv_id":"2005.07503","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["digitalepidemiologylab/covid-twitter-bert"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cross-lingual-transfer-of-twitter-sentiment","title":"Cross-lingual Transfer of Sentiment Classifiers","date":"2020-05-15","arxiv_id":"2005.07456","n_code_links":0,"syntology":null},{"paper":null,"slug":"finding-experts-in-transformer-models","title":"Finding Experts in Transformer Models","date":"2020-05-15","arxiv_id":"2005.07647","n_code_links":0,"syntology":null},{"paper":null,"slug":"hnas-hierarchical-neural-architecture-search","title":"Progressive Automatic Design of Search Space for One-Shot Neural Architecture Search","date":"2020-05-15","arxiv_id":"2005.07564","n_code_links":0,"syntology":null},{"paper":null,"slug":"jdi-t-jointly-trained-duration-informed","title":"JDI-T: Jointly trained Duration Informed Transformer for Text-To-Speech without Explicit Alignment","date":"2020-05-15","arxiv_id":"2005.07799","n_code_links":0,"syntology":null},{"paper":null,"slug":"keis-just-at-semeval-2020-task-12-identifying","title":"KEIS@JUST at SemEval-2020 Task 12: Identifying Multilingual Offensive Tweets Using Weighted Ensemble and Fine-Tuned BERT","date":"2020-05-15","arxiv_id":"2005.07820","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-entity-linking-on-technical-service","title":"Neural Entity Linking on Technical Service Tickets","date":"2020-05-15","arxiv_id":"2005.07604","n_code_links":0,"syntology":null},{"paper":"/paper/optimizing-neural-architecture-search-using","slug":"optimizing-neural-architecture-search-using","title":"Optimizing Neural Architecture Search using Limited GPU Time in a Dynamic Search Space: A Gene Expression Programming Approach","date":"2020-05-15","arxiv_id":"2005.07669","n_code_links":1,"syntology":null},{"paper":null,"slug":"resmonet-a-residual-mobile-based-network-for","title":"Convolutional Neural Network for emotion recognition to assist psychiatrists and psychologists during the COVID-19 pandemic: experts opinion","date":"2020-05-15","arxiv_id":"2005.07649","n_code_links":0,"syntology":null},{"paper":"/paper/spelling-error-correction-with-soft-masked","slug":"spelling-error-correction-with-soft-masked","title":"Spelling Error Correction with Soft-Masked BERT","date":"2020-05-15","arxiv_id":"2005.07421","n_code_links":5,"syntology":{"ran":14,"of":17,"n_ran_checked":13,"n_instrument":1,"unverified":3,"pointer_only":3,"phrase":"14 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/a-pre-training-technique-to-localize-medical","slug":"a-pre-training-technique-to-localize-medical","title":"Pre-training technique to localize medical BERT and enhance biomedical BERT","date":"2020-05-14","arxiv_id":"2005.07202","n_code_links":1,"syntology":null},{"paper":null,"slug":"anisotropy-links-cell-shapes-to-tissue-flow","title":"Anisotropy links cell shapes to tissue flow during convergent extension","date":"2020-05-14","arxiv_id":"2005.07283","n_code_links":0,"syntology":null},{"paper":null,"slug":"nit-agartala-nlp-team-at-semeval-2020-task-8","title":"NIT-Agartala-NLP-Team at SemEval-2020 Task 8: Building Multimodal Classifiers to tackle Internet Humor","date":"2020-05-14","arxiv_id":"2005.06943","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-mixture-of-h-1-heads-is-better-than-h-heads","title":"A Mixture of $h-1$ Heads is Better than $h$ Heads","date":"2020-05-13","arxiv_id":"2005.06537","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-learning-for-bone-shadow-exclusion-in","title":"Context Learning for Bone Shadow Exclusion in CheXNet Accuracy Improvement","date":"2020-05-13","arxiv_id":"2005.06189","n_code_links":0,"syntology":null},{"paper":"/paper/entity-enriched-neural-models-for-clinical","slug":"entity-enriched-neural-models-for-clinical","title":"Entity-Enriched Neural Models for Clinical Question Answering","date":"2020-05-13","arxiv_id":"2005.06587","n_code_links":2,"syntology":null},{"paper":null,"slug":"large-scale-multi-actor-generative-dialog","title":"Large Scale Multi-Actor Generative Dialog Modeling","date":"2020-05-13","arxiv_id":"2005.06114","n_code_links":0,"syntology":null},{"paper":"/paper/neural-architecture-search-for-gliomas","slug":"neural-architecture-search-for-gliomas","title":"Neural Architecture Search for Gliomas Segmentation on Multimodal Magnetic Resonance Imaging","date":"2020-05-13","arxiv_id":"2005.06338","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-global-convergence-rates-of-softmax","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods","date":"2020-05-13","arxiv_id":"2005.06392","n_code_links":0,"syntology":null},{"paper":"/paper/parallel-corpus-filtering-via-pre-trained","slug":"parallel-corpus-filtering-via-pre-trained","title":"Parallel Corpus Filtering via Pre-trained Language Models","date":"2020-05-13","arxiv_id":"2005.06166","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-unstoppable-rise-of-computational","title":"The Unstoppable Rise of Computational Linguistics in Deep Learning","date":"2020-05-13","arxiv_id":"2005.06420","n_code_links":0,"syntology":null},{"paper":null,"slug":"apple-defect-detection-using-deep-learning","title":"Apple Defect Detection Using Deep Learning Based Object Detection For Better Post Harvest Handling","date":"2020-05-12","arxiv_id":"2005.06089","n_code_links":0,"syntology":null},{"paper":"/paper/discriminative-multi-modality-speech","slug":"discriminative-multi-modality-speech","title":"Discriminative Multi-modality Speech Recognition","date":"2020-05-12","arxiv_id":"2005.05592","n_code_links":2,"syntology":null},{"paper":"/paper/on-the-robustness-of-language-encoders","slug":"on-the-robustness-of-language-encoders","title":"On the Robustness of Language Encoders against Grammatical Errors","date":"2020-05-12","arxiv_id":"2005.05683","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":["uclanlp/ProbeGrammarRobustness"],"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"]}}}],"record_sha256":"a0e968ede9f98ac362c9330fc6339cb27b49adac75e163587876dbe5bcbd59c0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}