{"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/residual-connection/papers/267","list_of":"/method/residual-connection","method":"Residual Connection","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":267,"pages_in_order":285,"rows_per_page":100,"rows":[26601,26700],"of":28401,"counts":{"archive_papers_tagged":28401,"with_a_code_link":12847,"where_syntology_ran_a_sample":3897,"not_listed_spam_title":0,"listed":28401,"listed_where_code_ran":3897,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3291,"every_run_a_failure_of_syntologys_instrument":606,"listed_with_a_run_with_no_instrument_failure":3291,"listed_every_run_a_failure_of_syntologys_instrument":606,"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/residual-connection","prev":"/method/residual-connection/papers/266","next":"/method/residual-connection/papers/268","papers":[{"paper":null,"slug":"human-centric-metric-for-accelerating","title":"Human-centric Metric for Accelerating Pathology Reports Annotation","date":"2019-10-31","arxiv_id":"1911.01226","n_code_links":0,"syntology":null},{"paper":"/paper/image-conditioned-graph-generation-for-road","slug":"image-conditioned-graph-generation-for-road","title":"Image-Conditioned Graph Generation for Road Network Extraction","date":"2019-10-31","arxiv_id":"1910.14388","n_code_links":3,"syntology":null},{"paper":null,"slug":"limit-bert-linguistic-informed-multi-task","title":"LIMIT-BERT : Linguistic Informed Multi-Task BERT","date":"2019-10-31","arxiv_id":"1910.14296","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-defect-microscopy-image-restoration","title":"Multi-defect microscopy image restoration under limited data conditions","date":"2019-10-31","arxiv_id":"1910.14207","n_code_links":0,"syntology":null},{"paper":"/paper/multi-stage-document-ranking-with-bert","slug":"multi-stage-document-ranking-with-bert","title":"Multi-Stage Document Ranking with BERT","date":"2019-10-31","arxiv_id":"1910.14424","n_code_links":3,"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: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/nat-neural-architecture-transformer-for","slug":"nat-neural-architecture-transformer-for","title":"NAT: Neural Architecture Transformer for Accurate and Compact Architectures","date":"2019-10-31","arxiv_id":"1910.14488","n_code_links":1,"syntology":null},{"paper":"/paper/neural-assistant-joint-action-prediction","slug":"neural-assistant-joint-action-prediction","title":"Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning","date":"2019-10-31","arxiv_id":"1910.14613","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-interaction-between-deep-detectors-and","title":"On the Interaction Between Deep Detectors and Siamese Trackers in Video Surveillance","date":"2019-10-31","arxiv_id":"1910.14552","n_code_links":0,"syntology":null},{"paper":null,"slug":"parameter-sharing-decoder-pair-for-auto","title":"Parameter Sharing Decoder Pair for Auto Composing","date":"2019-10-31","arxiv_id":"1910.14270","n_code_links":0,"syntology":null},{"paper":null,"slug":"positional-attention-based-frame","title":"Positional Attention-based Frame Identification with BERT: A Deep Learning Approach to Target Disambiguation and Semantic Frame Selection","date":"2019-10-31","arxiv_id":"1910.14549","n_code_links":0,"syntology":null},{"paper":"/paper/pseudolikelihood-reranking-with-masked","slug":"pseudolikelihood-reranking-with-masked","title":"Masked Language Model Scoring","date":"2019-10-31","arxiv_id":"1910.14659","n_code_links":6,"syntology":{"ran":10,"of":10,"n_ran_checked":7,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["awslabs/mlm-scoring"],"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":null,"slug":"transfer-learning-from-transformers-to-fake","title":"Transfer Learning from Transformers to Fake News Challenge Stance Detection (FNC-1) Task","date":"2019-10-31","arxiv_id":"1910.14353","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-augmented-transformer-architecture-for","title":"An Augmented Transformer Architecture for Natural Language Generation Tasks","date":"2019-10-30","arxiv_id":"1910.13634","n_code_links":0,"syntology":null},{"paper":"/paper/discourse-aware-neural-extractive-model-for","slug":"discourse-aware-neural-extractive-model-for","title":"Discourse-Aware Neural Extractive Text Summarization","date":"2019-10-30","arxiv_id":"1910.14142","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":10,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["jiacheng-xu/DiscoBERT"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lightweight-and-efficient-end-to-end-speech","title":"Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformer","date":"2019-10-30","arxiv_id":"1910.13923","n_code_links":0,"syntology":null},{"paper":null,"slug":"lsh-sampling-breaks-the-computation-chicken","title":"Lsh-sampling Breaks the Computation Chicken-and-egg Loop in Adaptive Stochastic Gradient Estimation","date":"2019-10-30","arxiv_id":"1910.14162","n_code_links":0,"syntology":null},{"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":"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":"/paper/bart-denoising-sequence-to-sequence-pre","slug":"bart-denoising-sequence-to-sequence-pre","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","date":"2019-10-29","arxiv_id":"1910.13461","n_code_links":47,"syntology":{"ran":40,"of":53,"n_ran_checked":31,"n_instrument":9,"unverified":13,"pointer_only":13,"phrase":"40 ran (of which 7 constructed an object rather than computing a result; 31 with no instrument failure: 1 honoured, 1 violated, 29 with no contract checked; 9 where Syntology's instrument failed) · 13 unverified","official":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/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":"leanconvnets-low-cost-yet-effective","title":"LeanConvNets: Low-cost Yet Effective Convolutional Neural Networks","date":"2019-10-29","arxiv_id":"1910.13157","n_code_links":0,"syntology":null},{"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":"/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":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":"/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/skip-clip-self-supervised-spatiotemporal","slug":"skip-clip-self-supervised-spatiotemporal","title":"Skip-Clip: Self-Supervised Spatiotemporal Representation Learning by Future Clip Order Ranking","date":"2019-10-28","arxiv_id":"1910.12770","n_code_links":0,"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":"/paper/consistency-regularization-for-generative-1","slug":"consistency-regularization-for-generative-1","title":"Consistency Regularization for Generative Adversarial Networks","date":"2019-10-26","arxiv_id":"1910.12027","n_code_links":0,"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/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/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":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":"/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":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":"/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":"identification-of-primary-angle-closure-on-as","title":"Identification of primary angle-closure on AS-OCT images with Convolutional Neural Networks","date":"2019-10-23","arxiv_id":"1910.10414","n_code_links":0,"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-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/4-connected-shift-residual-networks","slug":"4-connected-shift-residual-networks","title":"4-Connected Shift Residual Networks","date":"2019-10-22","arxiv_id":"1910.09931","n_code_links":1,"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":"/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":"/paper/self-correction-for-human-parsing","slug":"self-correction-for-human-parsing","title":"Self-Correction for Human Parsing","date":"2019-10-22","arxiv_id":"1910.09777","n_code_links":2,"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: 1 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["PeikeLi/Self-Correction-Human-Parsing"],"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":["listed","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":null,"slug":"softgan-learning-generative-models","title":"CycleGAN Voice Conversion of Spectral Envelopes using Adversarial Weights","date":"2019-10-22","arxiv_id":"1910.12614","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":null,"slug":"directed-weighting-group-lasso-for-eltwise","title":"Directed-Weighting Group Lasso for Eltwise Blocked CNN Pruning","date":"2019-10-21","arxiv_id":"1910.09318","n_code_links":0,"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/image-difficulty-curriculum-for-generative","slug":"image-difficulty-curriculum-for-generative","title":"Image Difficulty Curriculum for Generative Adversarial Networks (CuGAN)","date":"2019-10-20","arxiv_id":"1910.08967","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":"/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":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":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":"conservation-ai-live-stream-analysis-for-the","title":"Conservation AI: Live Stream Analysis for the Detection of Endangered Species Using Convolutional Neural Networks and Drone Technology","date":"2019-10-16","arxiv_id":"1910.07360","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":"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},{"paper":null,"slug":"transformer-asr-with-contextual-block","title":"Transformer ASR with Contextual Block Processing","date":"2019-10-16","arxiv_id":"1910.07204","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-whole-document-context-in-neural","title":"Using Whole Document Context in Neural Machine Translation","date":"2019-10-16","arxiv_id":"1910.07481","n_code_links":0,"syntology":null}],"record_sha256":"8feb758afd4ce1dc759fc8b8705feafac7b279ca9365ab54b4d26654a7521c87","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}