{"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/349","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":349,"pages_in_order":375,"rows_per_page":100,"rows":[34801,34900],"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/348","next":"/method/softmax/papers/350","papers":[{"paper":"/paper/phenotyping-of-clinical-notes-with-improved","slug":"phenotyping-of-clinical-notes-with-improved","title":"Phenotyping of Clinical Notes with Improved Document Classification Models Using Contextualized Neural Language Models","date":"2019-10-30","arxiv_id":"1910.13664","n_code_links":2,"syntology":null},{"paper":null,"slug":"time-to-take-emoji-seriously-they-vastly","title":"Time to Take Emoji Seriously: They Vastly Improve Casual Conversational Models","date":"2019-10-30","arxiv_id":"1910.13793","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-scalable-efficient-and-accurate-deep","title":"Towards Scalable, Efficient and Accurate Deep Spiking Neural Networks with Backward Residual Connections, Stochastic Softmax and Hybridization","date":"2019-10-30","arxiv_id":"1910.13931","n_code_links":0,"syntology":null},{"paper":null,"slug":"191013215","title":"Transformer-based Cascaded Multimodal Speech Translation","date":"2019-10-29","arxiv_id":"1910.13215","n_code_links":0,"syntology":null},{"paper":"/paper/191013291","slug":"191013291","title":"Sentence Embeddings for Russian NLU","date":"2019-10-29","arxiv_id":"1910.13291","n_code_links":1,"syntology":null},{"paper":null,"slug":"191013437","title":"An Empirical Study of Generation Order for Machine Translation","date":"2019-10-29","arxiv_id":"1910.13437","n_code_links":0,"syntology":null},{"paper":null,"slug":"big-bidirectional-insertion-representations","title":"Big Bidirectional Insertion Representations for Documents","date":"2019-10-29","arxiv_id":"1910.13034","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-attention-mechanism-for","slug":"contrastive-attention-mechanism-for","title":"Contrastive Attention Mechanism for Abstractive Sentence Summarization","date":"2019-10-29","arxiv_id":"1910.13114","n_code_links":1,"syntology":null},{"paper":"/paper/inducing-brain-relevant-bias-in-natural","slug":"inducing-brain-relevant-bias-in-natural","title":"Inducing brain-relevant bias in natural language processing models","date":"2019-10-29","arxiv_id":"1911.03268","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["danrsc/bert_brain_neurips_2019"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"learning-rich-image-region-representation-for","title":"Learning Rich Image Region Representation for Visual Question Answering","date":"2019-10-29","arxiv_id":"1910.13077","n_code_links":0,"syntology":null},{"paper":null,"slug":"region-based-convolution-neural-network","title":"Region-based Convolution Neural Network Approach for Accurate Segmentation of Pelvic Radiograph","date":"2019-10-29","arxiv_id":"1910.13231","n_code_links":0,"syntology":null},{"paper":"/paper/a-bert-based-transfer-learning-approach-for","slug":"a-bert-based-transfer-learning-approach-for","title":"A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media","date":"2019-10-28","arxiv_id":"1910.12574","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":null}},{"paper":"/paper/a-simple-but-effective-bert-model-for-dialog","slug":"a-simple-but-effective-bert-model-for-dialog","title":"A Simple but Effective BERT Model for Dialog State Tracking on Resource-Limited Systems","date":"2019-10-28","arxiv_id":"1910.12995","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-temperature-scaling-obtaining-well","slug":"beyond-temperature-scaling-obtaining-well","title":"Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration","date":"2019-10-28","arxiv_id":"1910.12656","n_code_links":3,"syntology":{"ran":6,"of":7,"n_ran_checked":5,"n_instrument":1,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":null}},{"paper":null,"slug":"exploring-kernel-functions-in-the-softmax","title":"Exploring Kernel Functions in the Softmax Layer for Contextual Word Classification","date":"2019-10-28","arxiv_id":"1910.12554","n_code_links":0,"syntology":null},{"paper":"/paper/extreme-classification-in-log-memory-using","slug":"extreme-classification-in-log-memory-using","title":"Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products","date":"2019-10-28","arxiv_id":"1910.13830","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-grained-object-detection-over-scientific","title":"Fine-Grained Object Detection over Scientific Document Images with Region Embeddings","date":"2019-10-28","arxiv_id":"1910.12462","n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-inter-speaker-relationship-in-xlnet","title":"Modeling Inter-Speaker Relationship in XLNet for Contextual Spoken Language Understanding","date":"2019-10-28","arxiv_id":"1910.12531","n_code_links":0,"syntology":null},{"paper":null,"slug":"neighborhood-watch-representation-learning","title":"Neighborhood Watch: Representation Learning with Local-Margin Triplet Loss and Sampling Strategy for K-Nearest-Neighbor Image Classification","date":"2019-10-28","arxiv_id":"1911.07940","n_code_links":0,"syntology":null},{"paper":"/paper/sequence-to-sequence-automatic-speech","slug":"sequence-to-sequence-automatic-speech","title":"Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding","date":"2019-10-28","arxiv_id":"1910.12740","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-transducer-end-to-end-speech","slug":"transformer-transducer-end-to-end-speech","title":"Transformer-Transducer: End-to-End Speech Recognition with Self-Attention","date":"2019-10-28","arxiv_id":"1910.12977","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-does-bert-learn-from-multiple-choice","title":"What does BERT Learn from Multiple-Choice Reading Comprehension Datasets?","date":"2019-10-28","arxiv_id":"1910.12391","n_code_links":0,"syntology":null},{"paper":"/paper/an-adaptive-and-momental-bound-method-for","slug":"an-adaptive-and-momental-bound-method-for","title":"An Adaptive and Momental Bound Method for Stochastic Learning","date":"2019-10-27","arxiv_id":"1910.12249","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lancopku/AdaMod"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/open-the-boxes-of-words-incorporating-sememes","slug":"open-the-boxes-of-words-incorporating-sememes","title":"Word-level Textual Adversarial Attacking as Combinatorial Optimization","date":"2019-10-27","arxiv_id":"1910.12196","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["thunlp/SememePSO-Attack"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/thieves-on-sesame-street-model-extraction-of","slug":"thieves-on-sesame-street-model-extraction-of","title":"Thieves on Sesame Street! Model Extraction of BERT-based APIs","date":"2019-10-27","arxiv_id":"1910.12366","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-asr-models-by-generation-of","title":"Training ASR models by Generation of Contextual Information","date":"2019-10-27","arxiv_id":"1910.12367","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-and-control-algorithms-of","title":"Deep Learning and Control Algorithms of Direct Perception for Autonomous Driving","date":"2019-10-26","arxiv_id":"1910.12031","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-an-efficient-network-for-large-scale","title":"Learning an Efficient Network for Large-Scale Hierarchical Object Detection with Data Imbalance: 3rd Place Solution to Open Images Challenge 2019","date":"2019-10-26","arxiv_id":"1910.12044","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparable-study-intrinsic-difficulties-of","title":"A comparable study: Intrinsic difficulties of practical plant diagnosis from wide-angle images","date":"2019-10-25","arxiv_id":"1910.11506","n_code_links":0,"syntology":null},{"paper":"/paper/alet-automated-labeling-of-equipment-and","slug":"alet-automated-labeling-of-equipment-and","title":"ALET (Automated Labeling of Equipment and Tools): A Dataset, a Baseline and a Usecase for Tool Detection in the Wild","date":"2019-10-25","arxiv_id":"1910.11713","n_code_links":1,"syntology":null},{"paper":null,"slug":"dens-a-dataset-for-multi-class-emotion","title":"DENS: A Dataset for Multi-class Emotion Analysis","date":"2019-10-25","arxiv_id":"1910.11769","n_code_links":0,"syntology":null},{"paper":"/paper/hardware-aware-one-shot-neural-architecture-1","slug":"hardware-aware-one-shot-neural-architecture-1","title":"Fast Hardware-Aware Neural Architecture Search","date":"2019-10-25","arxiv_id":"1910.11609","n_code_links":1,"syntology":null},{"paper":"/paper/hubert-untangles-bert-to-improve-transfer-1","slug":"hubert-untangles-bert-to-improve-transfer-1","title":"HUBERT Untangles BERT to Improve Transfer across NLP Tasks","date":"2019-10-25","arxiv_id":"1910.12647","n_code_links":1,"syntology":null},{"paper":null,"slug":"l2rs-a-learning-to-rescore-mechanism-for","title":"L2RS: A Learning-to-Rescore Mechanism for Automatic Speech Recognition","date":"2019-10-25","arxiv_id":"1910.11496","n_code_links":0,"syntology":null},{"paper":"/paper/meta-learning-with-dynamic-memory-based","slug":"meta-learning-with-dynamic-memory-based","title":"Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection","date":"2019-10-25","arxiv_id":"1910.11621","n_code_links":1,"syntology":null},{"paper":"/paper/mockingjay-unsupervised-speech-representation","slug":"mockingjay-unsupervised-speech-representation","title":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","date":"2019-10-25","arxiv_id":"1910.12638","n_code_links":7,"syntology":{"ran":8,"of":11,"n_ran_checked":6,"n_instrument":2,"unverified":3,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["andi611/Self-Supervised-Speech-Pretraining-and-Representation-Learning"],"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/on-the-cross-lingual-transferability-of","slug":"on-the-cross-lingual-transferability-of","title":"On the Cross-lingual Transferability of Monolingual Representations","date":"2019-10-25","arxiv_id":"1910.11856","n_code_links":7,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["deepmind/xquad"],"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/speechbert-cross-modal-pre-trained-language","slug":"speechbert-cross-modal-pre-trained-language","title":"SpeechBERT: An Audio-and-text Jointly Learned Language Model for End-to-end Spoken Question Answering","date":"2019-10-25","arxiv_id":"1910.11559","n_code_links":0,"syntology":null},{"paper":"/paper/stabilizing-darts-with-amended-gradient","slug":"stabilizing-darts-with-amended-gradient","title":"Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameters","date":"2019-10-25","arxiv_id":"1910.11831","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-online-end-to-end-transformer","title":"Towards Online End-to-end Transformer Automatic Speech Recognition","date":"2019-10-25","arxiv_id":"1910.11871","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-study-of-efficient-asr-rescoring","title":"An Empirical Study of Efficient ASR Rescoring with Transformers","date":"2019-10-24","arxiv_id":"1910.11450","n_code_links":0,"syntology":null},{"paper":null,"slug":"combining-acoustics-content-and-interaction","title":"Combining Acoustics, Content and Interaction Features to Find Hot Spots in Meetings","date":"2019-10-24","arxiv_id":"1910.10869","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-recognition-with-4kresolution","title":"Emotion recognition with 4kresolution database","date":"2019-10-24","arxiv_id":"1910.11276","n_code_links":0,"syntology":null},{"paper":"/paper/espnet-tts-unified-reproducible-and","slug":"espnet-tts-unified-reproducible-and","title":"ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit","date":"2019-10-24","arxiv_id":"1910.10909","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["r9y9/wavenet_vocoder","espnet/espnet"],"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","unlocated"]}}},{"paper":null,"slug":"promoting-the-knowledge-of-source-syntax-in","title":"Promoting the Knowledge of Source Syntax in Transformer NMT Is Not Needed","date":"2019-10-24","arxiv_id":"1910.11218","n_code_links":0,"syntology":null},{"paper":null,"slug":"unified-multi-scale-feature-abstraction-for","title":"Unified Multi-scale Feature Abstraction for Medical Image Segmentation","date":"2019-10-24","arxiv_id":"1910.11456","n_code_links":0,"syntology":null},{"paper":"/paper/a-transformer-with-interleaved-self-attention","slug":"a-transformer-with-interleaved-self-attention","title":"A Transformer with Interleaved Self-attention and Convolution for Hybrid Acoustic Models","date":"2019-10-23","arxiv_id":"1910.10352","n_code_links":1,"syntology":null},{"paper":null,"slug":"controlling-the-output-length-of-neural","title":"Controlling the Output Length of Neural Machine Translation","date":"2019-10-23","arxiv_id":"1910.10408","n_code_links":0,"syntology":null},{"paper":null,"slug":"correction-of-automatic-speech-recognition","title":"Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Model","date":"2019-10-23","arxiv_id":"1910.10697","n_code_links":0,"syntology":null},{"paper":"/paper/deja-vu-double-feature-presentation-in-deep","slug":"deja-vu-double-feature-presentation-in-deep","title":"Deja-vu: Double Feature Presentation and Iterated Loss in Deep Transformer Networks","date":"2019-10-23","arxiv_id":"1910.10324","n_code_links":2,"syntology":null},{"paper":"/paper/efficient-decoupled-neural-architecture","slug":"efficient-decoupled-neural-architecture","title":"Efficient Decoupled Neural Architecture Search by Structure and Operation Sampling","date":"2019-10-23","arxiv_id":"1910.10397","n_code_links":1,"syntology":null},{"paper":null,"slug":"emergent-properties-of-finetuned-language","title":"Emergent Properties of Finetuned Language Representation Models","date":"2019-10-23","arxiv_id":"1910.10832","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-limits-of-transfer-learning","slug":"exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","arxiv_id":"1910.10683","n_code_links":57,"syntology":{"ran":21,"of":31,"n_ran_checked":20,"n_instrument":1,"unverified":10,"pointer_only":0,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified","official":null}},{"paper":null,"slug":"feature-selection-and-extraction-for-graph","title":"Feature Selection and Extraction for Graph Neural Networks","date":"2019-10-23","arxiv_id":"1910.10682","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-transformers-for-long-document","slug":"hierarchical-transformers-for-long-document","title":"Hierarchical Transformers for Long Document Classification","date":"2019-10-23","arxiv_id":"1910.10781","n_code_links":3,"syntology":null},{"paper":null,"slug":"relation-module-for-non-answerable-prediction","title":"Relation Module for Non-answerable Prediction on Question Answering","date":"2019-10-23","arxiv_id":"1910.10843","n_code_links":0,"syntology":null},{"paper":null,"slug":"speech-emotion-recognition-via-contrastive","title":"Speech Emotion Recognition via Contrastive Loss under Siamese Networks","date":"2019-10-23","arxiv_id":"1910.11174","n_code_links":0,"syntology":null},{"paper":null,"slug":"speech-xlnet-unsupervised-acoustic-model","title":"Speech-XLNet: Unsupervised Acoustic Model Pretraining For Self-Attention Networks","date":"2019-10-23","arxiv_id":"1910.10387","n_code_links":0,"syntology":null},{"paper":null,"slug":"tct-a-cross-supervised-learning-method-for","title":"TCT: A Cross-supervised Learning Method for Multimodal Sequence Representation","date":"2019-10-23","arxiv_id":"1911.05186","n_code_links":0,"syntology":null},{"paper":"/paper/complex-transformer-a-framework-for-modeling","slug":"complex-transformer-a-framework-for-modeling","title":"Complex Transformer: A Framework for Modeling Complex-Valued Sequence","date":"2019-10-22","arxiv_id":"1910.10202","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["muqiaoy/dl_signal"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/deep-set-to-set-matching-and-learning","slug":"deep-set-to-set-matching-and-learning","title":"Exchangeable deep neural networks for set-to-set matching and learning","date":"2019-10-22","arxiv_id":"1910.09972","n_code_links":2,"syntology":null},{"paper":null,"slug":"depth-adaptive-transformer","title":"Depth-Adaptive Transformer","date":"2019-10-22","arxiv_id":"1910.10073","n_code_links":0,"syntology":null},{"paper":null,"slug":"embedded-bayesian-network-classifiers","title":"Embedded Bayesian Network Classifiers","date":"2019-10-22","arxiv_id":"1910.09715","n_code_links":0,"syntology":null},{"paper":null,"slug":"establishing-an-evaluation-metric-to-quantify","title":"Establishing an Evaluation Metric to Quantify Climate Change Image Realism","date":"2019-10-22","arxiv_id":"1910.10143","n_code_links":0,"syntology":null},{"paper":"/paper/improving-transformer-based-speech","slug":"improving-transformer-based-speech","title":"Improving Transformer-based Speech Recognition Using Unsupervised Pre-training","date":"2019-10-22","arxiv_id":"1910.09932","n_code_links":1,"syntology":null},{"paper":"/paper/mrqa-2019-shared-task-evaluating","slug":"mrqa-2019-shared-task-evaluating","title":"MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension","date":"2019-10-22","arxiv_id":"1910.09753","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mrqa/MRQA-Shared-Task-2019"],"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":"sequence-to-sequence-singing-synthesis-using","title":"Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformer","date":"2019-10-22","arxiv_id":"1910.09989","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-acoustic-modeling-for","slug":"transformer-based-acoustic-modeling-for","title":"Transformer-based Acoustic Modeling for Hybrid Speech Recognition","date":"2019-10-22","arxiv_id":"1910.09799","n_code_links":0,"syntology":null},{"paper":null,"slug":"depth-wise-decomposition-for-accelerating","title":"Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks","date":"2019-10-21","arxiv_id":"1910.09455","n_code_links":0,"syntology":null},{"paper":"/paper/improving-vehicle-re-identification-using-cnn","slug":"improving-vehicle-re-identification-using-cnn","title":"Improving Vehicle Re-Identification using CNN Latent Spaces: Metrics Comparison and Track-to-track Extension","date":"2019-10-21","arxiv_id":"1910.09458","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-make-generalizable-and-diverse","title":"Learning to Make Generalizable and Diverse Predictions for Retrosynthesis","date":"2019-10-21","arxiv_id":"1910.09688","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-cnn-fast-and-reliable-tool-for","slug":"transformer-cnn-fast-and-reliable-tool-for","title":"Transformer-CNN: Fast and Reliable tool for QSAR","date":"2019-10-21","arxiv_id":"1911.06603","n_code_links":1,"syntology":null},{"paper":"/paper/personalizing-graph-neural-networks-with","slug":"personalizing-graph-neural-networks-with","title":"Personalized Graph Neural Networks with Attention Mechanism for Session-Aware Recommendation","date":"2019-10-20","arxiv_id":"1910.08887","n_code_links":3,"syntology":null},{"paper":null,"slug":"pid-a-new-benchmark-dataset-to-classify-and","title":"Pavement Image Datasets: A New Benchmark Dataset to Classify and Densify Pavement Distresses","date":"2019-10-20","arxiv_id":"1910.11123","n_code_links":0,"syntology":null},{"paper":"/paper/targeted-estimation-of-heterogeneous","slug":"targeted-estimation-of-heterogeneous","title":"Targeted Estimation of Heterogeneous Treatment Effect in Observational Survival Analysis","date":"2019-10-20","arxiv_id":"1910.08877","n_code_links":1,"syntology":null},{"paper":"/paper/monalog-a-lightweight-system-for-natural","slug":"monalog-a-lightweight-system-for-natural","title":"MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity","date":"2019-10-19","arxiv_id":"1910.08772","n_code_links":1,"syntology":null},{"paper":"/paper/spatial-aware-online-adversarial","slug":"spatial-aware-online-adversarial","title":"SPARK: Spatial-aware Online Incremental Attack Against Visual Tracking","date":"2019-10-19","arxiv_id":"1910.08681","n_code_links":1,"syntology":null},{"paper":null,"slug":"xl-editor-post-editing-sentences-with-xlnet","title":"XL-Editor: Post-editing Sentences with XLNet","date":"2019-10-19","arxiv_id":"1910.10479","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-mutual-information-maximization-perspective-1","title":"A Mutual Information Maximization Perspective of Language Representation Learning","date":"2019-10-18","arxiv_id":"1910.08350","n_code_links":0,"syntology":null},{"paper":"/paper/bobby2-buffer-based-robust-high-speed-object","slug":"bobby2-buffer-based-robust-high-speed-object","title":"BOBBY2: Buffer Based Robust High-Speed Object Tracking","date":"2019-10-18","arxiv_id":"1910.08263","n_code_links":1,"syntology":null},{"paper":null,"slug":"combinatorial-losses-through-generalized","title":"Differentiable Combinatorial Losses through Generalized Gradients of Linear Programs","date":"2019-10-18","arxiv_id":"1910.08211","n_code_links":0,"syntology":null},{"paper":"/paper/concept-pointer-network-for-abstractive","slug":"concept-pointer-network-for-abstractive","title":"Concept Pointer Network for Abstractive Summarization","date":"2019-10-18","arxiv_id":"1910.08486","n_code_links":1,"syntology":null},{"paper":"/paper/evading-real-time-person-detectors-by","slug":"evading-real-time-person-detectors-by","title":"Adversarial T-shirt! Evading Person Detectors in A Physical World","date":"2019-10-18","arxiv_id":"1910.11099","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"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":null}},{"paper":null,"slug":"model-compression-with-two-stage-multi","title":"Model Compression with Two-stage Multi-teacher Knowledge Distillation for Web Question Answering System","date":"2019-10-18","arxiv_id":"1910.08381","n_code_links":0,"syntology":null},{"paper":null,"slug":"big-mood-relating-transformers-to-explicit","title":"BIG MOOD: Relating Transformers to Explicit Commonsense Knowledge","date":"2019-10-17","arxiv_id":"1910.07713","n_code_links":0,"syntology":null},{"paper":null,"slug":"fully-quantized-transformer-for-improved","title":"Fully Quantized Transformer for Machine Translation","date":"2019-10-17","arxiv_id":"1910.10485","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-semantic-similarity-of-clinical","slug":"measuring-semantic-similarity-of-clinical","title":"Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations","date":"2019-10-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-retrosynthetic-pathways-using-a","title":"Predicting retrosynthetic pathways using a combined linguistic model and hyper-graph exploration strategy","date":"2019-10-17","arxiv_id":"1910.08036","n_code_links":0,"syntology":null},{"paper":"/paper/question-classification-with-deep","slug":"question-classification-with-deep","title":"Question Classification with Deep Contextualized Transformer","date":"2019-10-17","arxiv_id":"1910.10492","n_code_links":1,"syntology":null},{"paper":null,"slug":"universal-text-representation-from-bert-an","title":"Universal Text Representation from BERT: An Empirical Study","date":"2019-10-17","arxiv_id":"1910.07973","n_code_links":0,"syntology":null},{"paper":"/paper/aerial-images-processing-for-car-detection","slug":"aerial-images-processing-for-car-detection","title":"Aerial Images Processing for Car Detection using Convolutional Neural Networks: Comparison between Faster R-CNN and YoloV3","date":"2019-10-16","arxiv_id":"1910.07234","n_code_links":1,"syntology":null},{"paper":"/paper/bertram-improved-word-embeddings-have-big","slug":"bertram-improved-word-embeddings-have-big","title":"BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance","date":"2019-10-16","arxiv_id":"1910.07181","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["timoschick/bertram"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bridging-the-knowledge-gap-enhancing-question","title":"Bridging the Knowledge Gap: Enhancing Question Answering with World and Domain Knowledge","date":"2019-10-16","arxiv_id":"1910.07429","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficiency-through-auto-sizing-notre-dame","title":"Efficiency through Auto-Sizing: Notre Dame NLP's Submission to the WNGT 2019 Efficiency Task","date":"2019-10-16","arxiv_id":"1910.07134","n_code_links":0,"syntology":null},{"paper":null,"slug":"evolution-of-transfer-learning-in-natural","title":"Evolution of transfer learning in natural language processing","date":"2019-10-16","arxiv_id":"1910.07370","n_code_links":0,"syntology":null},{"paper":null,"slug":"imperial-college-london-submission-to-vatex","title":"Imperial College London Submission to VATEX Video Captioning Task","date":"2019-10-16","arxiv_id":"1910.07482","n_code_links":0,"syntology":null},{"paper":"/paper/injecting-hierarchy-with-u-net-transformers","slug":"injecting-hierarchy-with-u-net-transformers","title":"Injecting Hierarchy with U-Net Transformers","date":"2019-10-16","arxiv_id":"1910.10488","n_code_links":2,"syntology":null},{"paper":null,"slug":"memory-augmented-recurrent-networks-for","title":"Memory-Augmented Recurrent Networks for Dialogue Coherence","date":"2019-10-16","arxiv_id":"1910.10487","n_code_links":0,"syntology":null},{"paper":null,"slug":"mix-review-alleviate-forgetting-in-the","title":"Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models","date":"2019-10-16","arxiv_id":"1910.07117","n_code_links":0,"syntology":null},{"paper":null,"slug":"offline-handwritten-mathematical-symbol","title":"Offline handwritten mathematical symbol recognition utilising deep learning","date":"2019-10-16","arxiv_id":"1910.07395","n_code_links":0,"syntology":null}],"record_sha256":"623b2b71a5da2863f020186c9dcfe155c895ada73891d42f98192ad48bf8f317","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}