{"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/351","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":351,"pages_in_order":375,"rows_per_page":100,"rows":[35001,35100],"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/350","next":"/method/softmax/papers/352","papers":[{"paper":null,"slug":"towards-interpretable-object-detection-by","title":"Towards Interpretable Object Detection by Unfolding Latent Structures","date":"2019-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"vae-pgn-based-abstractive-model-in-multi","title":"VAE-PGN based Abstractive Model in Multi-stage Architecture for Text Summarization","date":"2019-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/edgecnn-convolutional-neural-network","slug":"edgecnn-convolutional-neural-network","title":"EdgeCNN: Convolutional Neural Network Classification Model with small inputs for Edge Computing","date":"2019-09-30","arxiv_id":"1909.13522","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-resume-parsing-and-finding","title":"End-to-End Resume Parsing and Finding Candidates for a Job Description using BERT","date":"2019-09-30","arxiv_id":"1910.03089","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-head-attention-with-diversity-for","title":"Multi-Head Attention with Diversity for Learning Grounded Multilingual Multimodal Representations","date":"2019-09-30","arxiv_id":"1910.00058","n_code_links":0,"syntology":null},{"paper":"/paper/rnas-architecture-ranking-for-powerful","slug":"rnas-architecture-ranking-for-powerful","title":"ReNAS:Relativistic Evaluation of Neural Architecture Search","date":"2019-09-30","arxiv_id":"1910.01523","n_code_links":4,"syntology":{"ran":4,"of":6,"n_ran_checked":0,"n_instrument":4,"unverified":2,"pointer_only":0,"phrase":"4 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; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["huawei-noah/Efficient-Computing"],"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/fake-news-detection-using-deep-learning","slug":"fake-news-detection-using-deep-learning","title":"Fake news detection using Deep Learning","date":"2019-09-29","arxiv_id":"1910.03496","n_code_links":2,"syntology":null},{"paper":null,"slug":"fusion-of-convolutional-neural-network-and","title":"Fusion of Convolutional Neural Network and Statistical Features for Texture classification","date":"2019-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-based-autonomous-vehicle-control-using","title":"Vision-Based Autonomous Vehicle Control using the Two-Point Visual Driver Control Model","date":"2019-09-29","arxiv_id":"1910.04862","n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-fusion-detector-for-semantic","title":"Feature Fusion Detector for Semantic Cognition of Remote Sensing","date":"2019-09-28","arxiv_id":"1909.13047","n_code_links":0,"syntology":null},{"paper":null,"slug":"gdp-generalized-device-placement-for-dataflow","title":"GDP: Generalized Device Placement for Dataflow Graphs","date":"2019-09-28","arxiv_id":"1910.01578","n_code_links":0,"syntology":null},{"paper":"/paper/meta-r-cnn-towards-general-solver-for","slug":"meta-r-cnn-towards-general-solver-for","title":"Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning","date":"2019-09-28","arxiv_id":"1909.13032","n_code_links":0,"syntology":null},{"paper":"/paper/dmm-net-differentiable-mask-matching-network","slug":"dmm-net-differentiable-mask-matching-network","title":"DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation","date":"2019-09-27","arxiv_id":"1909.12471","n_code_links":1,"syntology":null},{"paper":"/paper/hatemonitors-language-agnostic-abuse","slug":"hatemonitors-language-agnostic-abuse","title":"HateMonitors: Language Agnostic Abuse Detection in Social Media","date":"2019-09-27","arxiv_id":"1909.12642","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-use-of-bert-for-neural-machine","title":"On the use of BERT for Neural Machine Translation","date":"2019-09-27","arxiv_id":"1909.12744","n_code_links":0,"syntology":null},{"paper":null,"slug":"reweighted-proximal-pruning-for-large-scale-1","title":"Reweighted Proximal Pruning for Large-Scale Language Representation","date":"2019-09-27","arxiv_id":"1909.12486","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-class-weight-based-dual-focal-loss","title":"Adaptive Class Weight based Dual Focal Loss for Improved Semantic Segmentation","date":"2019-09-26","arxiv_id":"1909.11932","n_code_links":0,"syntology":null},{"paper":"/paper/albert-a-lite-bert-for-self-supervised","slug":"albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","arxiv_id":"1909.11942","n_code_links":48,"syntology":{"ran":81,"of":126,"n_ran_checked":59,"n_instrument":22,"unverified":45,"pointer_only":28,"phrase":"81 ran (of which 17 constructed an object rather than computing a result; 59 with no instrument failure: 4 honoured, 0 violated, 55 with no contract checked; 22 where Syntology's instrument failed) · 45 unverified","official":{"repos":["google-research/ALBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"aspect-and-opinion-term-extraction-for-aspect","title":"Aspect and Opinion Term Extraction for Hotel Reviews using Transfer Learning and Auxiliary Labels","date":"2019-09-26","arxiv_id":"1909.11879","n_code_links":0,"syntology":null},{"paper":"/paper/balanced-binary-neural-networks-with-gated","slug":"balanced-binary-neural-networks-with-gated","title":"Balanced Binary Neural Networks with Gated Residual","date":"2019-09-26","arxiv_id":"1909.12117","n_code_links":1,"syntology":null},{"paper":null,"slug":"biomedical-relation-extraction-with-pre","title":"Biomedical relation extraction with pre-trained language representations and minimal task-specific architecture","date":"2019-09-26","arxiv_id":"1909.12411","n_code_links":0,"syntology":null},{"paper":null,"slug":"breast-cancer-diagnosis-with-transfer","title":"Breast Cancer Diagnosis with Transfer Learning and Global Pooling","date":"2019-09-26","arxiv_id":"1909.11839","n_code_links":0,"syntology":null},{"paper":null,"slug":"classification-of-histopathological-biopsy","title":"Classification of Histopathological Biopsy Images Using Ensemble of Deep Learning Networks","date":"2019-09-26","arxiv_id":"1909.11870","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-pre-trained-multilingual-models","title":"Improving Pre-Trained Multilingual Models with Vocabulary Expansion","date":"2019-09-26","arxiv_id":"1909.12440","n_code_links":0,"syntology":null},{"paper":"/paper/monotonic-multihead-attention-1","slug":"monotonic-multihead-attention-1","title":"Monotonic Multihead Attention","date":"2019-09-26","arxiv_id":"1909.12406","n_code_links":3,"syntology":null},{"paper":"/paper/stacnas-towards-stable-and-consistent","slug":"stacnas-towards-stable-and-consistent","title":"Hierarchical Neural Architecture Search via Operator Clustering","date":"2019-09-26","arxiv_id":"1909.11926","n_code_links":1,"syntology":null},{"paper":"/paper/unsupervised-universal-self-attention-network","slug":"unsupervised-universal-self-attention-network","title":"Universal Graph Transformer Self-Attention Networks","date":"2019-09-26","arxiv_id":"1909.11855","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["daiquocnguyen/Graph-Transformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"accurate-and-compact-convolutional-neural","title":"Accurate and Compact Convolutional Neural Networks with Trained Binarization","date":"2019-09-25","arxiv_id":"1909.11366","n_code_links":0,"syntology":null},{"paper":"/paper/attention-convolutional-binary-neural-tree","slug":"attention-convolutional-binary-neural-tree","title":"Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization","date":"2019-09-25","arxiv_id":"1909.11378","n_code_links":2,"syntology":null},{"paper":null,"slug":"extreme-language-model-compression-with-1","title":"Extremely Small BERT Models from Mixed-Vocabulary Training","date":"2019-09-25","arxiv_id":"1909.11687","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-detect-opinion-snippet-for-aspect","title":"Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysis","date":"2019-09-25","arxiv_id":"1909.11297","n_code_links":0,"syntology":null},{"paper":"/paper/mixout-effective-regularization-to-finetune","slug":"mixout-effective-regularization-to-finetune","title":"Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models","date":"2019-09-25","arxiv_id":"1909.11299","n_code_links":2,"syntology":null},{"paper":null,"slug":"pydens-a-python-framework-for-solving","title":"PyDEns: a Python Framework for Solving Differential Equations with Neural Networks","date":"2019-09-25","arxiv_id":"1909.11544","n_code_links":0,"syntology":null},{"paper":"/paper/reducing-transformer-depth-on-demand-with-1","slug":"reducing-transformer-depth-on-demand-with-1","title":"Reducing Transformer Depth on Demand with Structured Dropout","date":"2019-09-25","arxiv_id":"1909.11556","n_code_links":5,"syntology":null},{"paper":null,"slug":"the-good-the-bad-and-the-ugly-evaluating","title":"The Good, the Bad and the Ugly: Evaluating Convolutional Neural Networks for Prohibited Item Detection Using Real and Synthetically Composited X-ray Imagery","date":"2019-09-25","arxiv_id":"1909.11508","n_code_links":0,"syntology":null},{"paper":"/paper/widerperson-a-diverse-dataset-for-dense","slug":"widerperson-a-diverse-dataset-for-dense","title":"WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild","date":"2019-09-25","arxiv_id":"1909.12118","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-mangoes-from-fruit-detection-to-cultivar","title":"Deep Mangoes: from fruit detection to cultivar identification in colour images of mango trees","date":"2019-09-24","arxiv_id":"1909.10939","n_code_links":0,"syntology":null},{"paper":"/paper/fast-and-accurate-convolutional-object","slug":"fast-and-accurate-convolutional-object","title":"Development of Fast Refinement Detectors on AI Edge Platforms","date":"2019-09-24","arxiv_id":"1909.10798","n_code_links":2,"syntology":null},{"paper":"/paper/knowledge-enriched-transformer-for-emotion","slug":"knowledge-enriched-transformer-for-emotion","title":"Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations","date":"2019-09-24","arxiv_id":"1909.10681","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhongpeixiang/KET"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"technical-report-on-conversational-question","title":"Technical report on Conversational Question Answering","date":"2019-09-24","arxiv_id":"1909.10772","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-across-languages-from","title":"Efficiently Reusing Old Models Across Languages via Transfer Learning","date":"2019-09-24","arxiv_id":"1909.10955","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-semantics-from-speech-through","title":"Understanding Semantics from Speech Through Pre-training","date":"2019-09-24","arxiv_id":"1909.10924","n_code_links":0,"syntology":null},{"paper":"/paper/unified-vision-language-pre-training-for","slug":"unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","date":"2019-09-24","arxiv_id":"1909.11059","n_code_links":3,"syntology":{"ran":11,"of":14,"n_ran_checked":8,"n_instrument":3,"unverified":3,"pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["LuoweiZhou/VLP"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"190910227","title":"Deep Convolutions for In-Depth Automated Rock Typing","date":"2019-09-23","arxiv_id":"1909.10227","n_code_links":0,"syntology":null},{"paper":"/paper/190910351","slug":"190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","arxiv_id":"1909.10351","n_code_links":10,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"0 ran · 4 unverified","official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":"/paper/190910430","slug":"190910430","title":"Does BERT Make Any Sense? Interpretable Word Sense Disambiguation with Contextualized Embeddings","date":"2019-09-23","arxiv_id":"1909.10430","n_code_links":1,"syntology":null},{"paper":"/paper/a-link-recognizing-disguised-faces-via-active","slug":"a-link-recognizing-disguised-faces-via-active","title":"A-LINK: Recognizing Disguised Faces via Active Learning based Inter-Domain Knowledge","date":"2019-09-23","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/automatic-identification-and-normalisation-of","slug":"automatic-identification-and-normalisation-of","title":"Automatic Identification and Normalisation of Physical Measurements in Scientific Literature","date":"2019-09-23","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-geological-facies-models-with","title":"Generating Geological Facies Models with Fidelity to Diversity and Statistics of Training Images using Improved Generative Adversarial Networks","date":"2019-09-23","arxiv_id":"1909.10652","n_code_links":0,"syntology":null},{"paper":"/paper/portuguese-named-entity-recognition-using-1","slug":"portuguese-named-entity-recognition-using-1","title":"Portuguese Named Entity Recognition using BERT-CRF","date":"2019-09-23","arxiv_id":"1909.10649","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["neuralmind-ai/portuguese-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":null,"slug":"190909931","title":"Volume Preserving Image Segmentation with Entropic Regularization Optimal Transport and Its Applications in Deep Learning","date":"2019-09-22","arxiv_id":"1909.09931","n_code_links":0,"syntology":null},{"paper":null,"slug":"190909945","title":"To What Extent Does Downsampling, Compression, and Data Scarcity Impact Renal Image Analysis?","date":"2019-09-22","arxiv_id":"1909.09945","n_code_links":0,"syntology":null},{"paper":"/paper/190909777","slug":"190909777","title":"Generating Positive Bounding Boxes for Balanced Training of Object Detectors","date":"2019-09-21","arxiv_id":"1909.09777","n_code_links":1,"syntology":null},{"paper":null,"slug":"190909779","title":"Self-attention based end-to-end Hindi-English Neural Machine Translation","date":"2019-09-21","arxiv_id":"1909.09779","n_code_links":0,"syntology":null},{"paper":null,"slug":"190909801","title":"Adversarial Learning of General Transformations for Data Augmentation","date":"2019-09-21","arxiv_id":"1909.09801","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-exploration-of-deep-recurrent","title":"An Empirical Exploration of Deep Recurrent Connections and Memory Cells Using Neuro-Evolution","date":"2019-09-20","arxiv_id":"1909.09502","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-meets-chinese-word-segmentation","title":"BERT Meets Chinese Word Segmentation","date":"2019-09-20","arxiv_id":"1909.09292","n_code_links":0,"syntology":null},{"paper":null,"slug":"genetic-neural-architecture-search-for","title":"Genetic Neural Architecture Search for automatic assessment of human sperm images","date":"2019-09-20","arxiv_id":"1909.09432","n_code_links":0,"syntology":null},{"paper":"/paper/allennlp-interpret-a-framework-for-explaining","slug":"allennlp-interpret-a-framework-for-explaining","title":"AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models","date":"2019-09-19","arxiv_id":"1909.09251","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-ways-to-incorporate-additional","title":"How Additional Knowledge can Improve Natural Language Commonsense Question Answering?","date":"2019-09-19","arxiv_id":"1909.08855","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-variational-neural-machine","title":"Improved Variational Neural Machine Translation by Promoting Mutual Information","date":"2019-09-19","arxiv_id":"1909.09237","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-scale-representation-learning-from","title":"Large-scale representation learning from visually grounded untranscribed speech","date":"2019-09-19","arxiv_id":"1909.08782","n_code_links":0,"syntology":null},{"paper":"/paper/summary-level-training-of-sentence-rewriting","slug":"summary-level-training-of-sentence-rewriting","title":"Summary Level Training of Sentence Rewriting for Abstractive Summarization","date":"2019-09-19","arxiv_id":"1909.08752","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-using-cnn-for-handwritten","title":"Transfer Learning using CNN for Handwritten Devanagari Character Recognition","date":"2019-09-19","arxiv_id":"1909.08774","n_code_links":0,"syntology":null},{"paper":"/paper/enriching-bert-with-knowledge-graph","slug":"enriching-bert-with-knowledge-graph","title":"Enriching BERT with Knowledge Graph Embeddings for Document Classification","date":"2019-09-18","arxiv_id":"1909.08402","n_code_links":1,"syntology":null},{"paper":"/paper/improving-natural-language-inference-with-a","slug":"improving-natural-language-inference-with-a","title":"Improving Natural Language Inference with a Pretrained Parser","date":"2019-09-18","arxiv_id":"1909.08217","n_code_links":1,"syntology":null},{"paper":"/paper/ir-nas-neural-architecture-search-for-image","slug":"ir-nas-neural-architecture-search-for-image","title":"Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising","date":"2019-09-18","arxiv_id":"1909.08228","n_code_links":1,"syntology":null},{"paper":"/paper/language-models-and-automated-essay-scoring","slug":"language-models-and-automated-essay-scoring","title":"Language models and Automated Essay Scoring","date":"2019-09-18","arxiv_id":"1909.09482","n_code_links":1,"syntology":null},{"paper":null,"slug":"subword-elmo","title":"Subword ELMo","date":"2019-09-18","arxiv_id":"1909.08357","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-bert-for-word-sense-disambiguation","title":"Using BERT for Word Sense Disambiguation","date":"2019-09-18","arxiv_id":"1909.08358","n_code_links":0,"syntology":null},{"paper":"/paper/do-nlp-models-know-numbers-probing-numeracy","slug":"do-nlp-models-know-numbers-probing-numeracy","title":"Do NLP Models Know Numbers? Probing Numeracy in Embeddings","date":"2019-09-17","arxiv_id":"1909.07940","n_code_links":1,"syntology":null},{"paper":"/paper/extracting-evidence-of-supplement-drug","slug":"extracting-evidence-of-supplement-drug","title":"SUPP.AI: Finding Evidence for Supplement-Drug Interactions","date":"2019-09-17","arxiv_id":"1909.08135","n_code_links":1,"syntology":null},{"paper":null,"slug":"impact-of-novel-aggregation-methods-for","title":"Impact of novel aggregation methods for flexible, time-sensitive EHR prediction without variable selection or cleaning","date":"2019-09-17","arxiv_id":"1909.08981","n_code_links":0,"syntology":null},{"paper":"/paper/k-bert-enabling-language-representation-with","slug":"k-bert-enabling-language-representation-with","title":"K-BERT: Enabling Language Representation with Knowledge Graph","date":"2019-09-17","arxiv_id":"1909.07606","n_code_links":2,"syntology":null},{"paper":"/paper/megatron-lm-training-multi-billion-parameter","slug":"megatron-lm-training-multi-billion-parameter","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","date":"2019-09-17","arxiv_id":"1909.08053","n_code_links":10,"syntology":{"ran":12,"of":47,"n_ran_checked":7,"n_instrument":5,"unverified":35,"pointer_only":15,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 35 unverified","official":{"repos":["NVIDIA/Megatron-LM"],"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/re-obj-jointly-learning-the-foreground-and","slug":"re-obj-jointly-learning-the-foreground-and","title":"re-OBJ: Jointly Learning the Foreground and Background for Object Instance Re-identification","date":"2019-09-17","arxiv_id":"1909.07704","n_code_links":1,"syntology":null},{"paper":null,"slug":"relaxed-softmax-for-learning-from-positive","title":"Relaxed Softmax for learning from Positive and Unlabeled data","date":"2019-09-17","arxiv_id":"1909.08079","n_code_links":0,"syntology":null},{"paper":null,"slug":"simple-yet-effective-bridge-reasoning-for","title":"Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering","date":"2019-09-17","arxiv_id":"1909.07597","n_code_links":0,"syntology":null},{"paper":"/paper/span-based-joint-entity-and-relation","slug":"span-based-joint-entity-and-relation","title":"Span-based Joint Entity and Relation Extraction with Transformer Pre-training","date":"2019-09-17","arxiv_id":"1909.07755","n_code_links":3,"syntology":null},{"paper":null,"slug":"a-self-attentional-neural-architecture-for","title":"A Self-Attentional Neural Architecture for Code Completion with Multi-Task Learning","date":"2019-09-16","arxiv_id":"1909.06983","n_code_links":0,"syntology":null},{"paper":"/paper/acoustic-scene-analysis-with-multi-head","slug":"acoustic-scene-analysis-with-multi-head","title":"Acoustic scene analysis with multi-head attention networks","date":"2019-09-16","arxiv_id":"1909.08961","n_code_links":1,"syntology":null},{"paper":null,"slug":"hybrid-neural-models-for-sequence-modelling","title":"Hybrid Neural Models For Sequence Modelling: The Best Of Three Worlds","date":"2019-09-16","arxiv_id":"1909.07102","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-neural-machine-translation-for","slug":"multilingual-neural-machine-translation-for","title":"Multilingual Neural Machine Translation for Zero-Resource Languages","date":"2019-09-16","arxiv_id":"1909.07342","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-separability-of-classes-with-the-cross","title":"On the Separability of Classes with the Cross-Entropy Loss Function","date":"2019-09-16","arxiv_id":"1909.06930","n_code_links":0,"syntology":null},{"paper":"/paper/pose-neural-fabrics-search","slug":"pose-neural-fabrics-search","title":"Pose Neural Fabrics Search","date":"2019-09-16","arxiv_id":"1909.07068","n_code_links":2,"syntology":null},{"paper":"/paper/probing-natural-language-inference-models","slug":"probing-natural-language-inference-models","title":"Probing Natural Language Inference Models through Semantic Fragments","date":"2019-09-16","arxiv_id":"1909.07521","n_code_links":3,"syntology":null},{"paper":"/paper/automatically-extracting-challenge-sets-for","slug":"automatically-extracting-challenge-sets-for","title":"Automatically Extracting Challenge Sets for Non local Phenomena in Neural Machine Translation","date":"2019-09-15","arxiv_id":"1909.06814","n_code_links":1,"syntology":null},{"paper":"/paper/cascade-rpn-delving-into-high-quality-region","slug":"cascade-rpn-delving-into-high-quality-region","title":"Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution","date":"2019-09-15","arxiv_id":"1909.06720","n_code_links":2,"syntology":null},{"paper":"/paper/cross-lingual-bert-transformation-for-zero","slug":"cross-lingual-bert-transformation-for-zero","title":"Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing","date":"2019-09-15","arxiv_id":"1909.06775","n_code_links":1,"syntology":null},{"paper":null,"slug":"i-mad-a-novel-interpretable-malware-detector","title":"I-MAD: Interpretable Malware Detector Using Galaxy Transformer","date":"2019-09-15","arxiv_id":"1909.06865","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-and-power-evaluation-of-ai","title":"Benchmarking the Performance and Energy Efficiency of AI Accelerators for AI Training","date":"2019-09-15","arxiv_id":"1909.06842","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficiency-metrics-for-data-driven-models-a","title":"Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study","date":"2019-09-14","arxiv_id":"1909.06618","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-architecture-search-for-class","title":"Neural Architecture Search for Class-incremental Learning","date":"2019-09-14","arxiv_id":"1909.06686","n_code_links":0,"syntology":null},{"paper":"/paper/ouroboros-on-accelerating-training-of","slug":"ouroboros-on-accelerating-training-of","title":"Ouroboros: On Accelerating Training of Transformer-Based Language Models","date":"2019-09-14","arxiv_id":"1909.06695","n_code_links":1,"syntology":null},{"paper":"/paper/scalable-gaussian-process-classification-with","slug":"scalable-gaussian-process-classification-with","title":"Scalable Gaussian Process Classification with Additive Noise for Various Likelihoods","date":"2019-09-14","arxiv_id":"1909.06541","n_code_links":1,"syntology":null},{"paper":"/paper/tree-transformer-integrating-tree-structures","slug":"tree-transformer-integrating-tree-structures","title":"Tree Transformer: Integrating Tree Structures into Self-Attention","date":"2019-09-14","arxiv_id":"1909.06639","n_code_links":3,"syntology":{"ran":9,"of":10,"n_ran_checked":7,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"9 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yaushian/Tree-Transformer"],"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/a-comparative-study-on-transformer-vs-rnn-in","slug":"a-comparative-study-on-transformer-vs-rnn-in","title":"A Comparative Study on Transformer vs RNN in Speech Applications","date":"2019-09-13","arxiv_id":"1909.06317","n_code_links":2,"syntology":null},{"paper":"/paper/addressing-semantic-drift-in-question","slug":"addressing-semantic-drift-in-question","title":"Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering","date":"2019-09-13","arxiv_id":"1909.06356","n_code_links":2,"syntology":{"ran":13,"of":19,"n_ran_checked":11,"n_instrument":2,"unverified":6,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["ZhangShiyue/QGforQA"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/brain-like-object-recognition-with-high","slug":"brain-like-object-recognition-with-high","title":"Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs","date":"2019-09-13","arxiv_id":"1909.06161","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dicarlolab/cornet","dicarlolab/neurips2019"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"defending-against-adversarial-attacks-by-3","title":"Defending Against Adversarial Attacks by Suppressing the Largest Eigenvalue of Fisher Information Matrix","date":"2019-09-13","arxiv_id":"1909.06137","n_code_links":0,"syntology":null}],"record_sha256":"bafd48b01a99db241c80803541ae8e3303dbff51f132fd36bb03a066af4dc49d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}