{"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/label-smoothing/papers/138","list_of":"/method/label-smoothing","method":"Label Smoothing","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":138,"pages_in_order":144,"rows_per_page":100,"rows":[13701,13800],"of":14327,"counts":{"archive_papers_tagged":14327,"with_a_code_link":6651,"where_syntology_ran_a_sample":2259,"not_listed_spam_title":0,"listed":14327,"listed_where_code_ran":2259,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1920,"every_run_a_failure_of_syntologys_instrument":339,"listed_with_a_run_with_no_instrument_failure":1920,"listed_every_run_a_failure_of_syntologys_instrument":339,"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/label-smoothing","prev":"/method/label-smoothing/papers/137","next":"/method/label-smoothing/papers/139","papers":[{"paper":null,"slug":"syntax-infused-transformer-and-bert-models","title":"Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding","date":"2019-11-10","arxiv_id":"1911.06156","n_code_links":0,"syntology":null},{"paper":"/paper/tener-adapting-transformer-encoder-for-name","slug":"tener-adapting-transformer-encoder-for-name","title":"TENER: Adapting Transformer Encoder for Named Entity Recognition","date":"2019-11-10","arxiv_id":"1911.04474","n_code_links":6,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["fastnlp/TENER"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"two-headed-monster-and-crossed-co-attention","title":"Two-Headed Monster And Crossed Co-Attention Networks","date":"2019-11-10","arxiv_id":"1911.03897","n_code_links":0,"syntology":null},{"paper":"/paper/a-reinforced-generation-of-adversarial","slug":"a-reinforced-generation-of-adversarial","title":"A Reinforced Generation of Adversarial Examples for Neural Machine Translation","date":"2019-11-09","arxiv_id":"1911.03677","n_code_links":1,"syntology":null},{"paper":"/paper/graph-to-graph-transformer-for-transition","slug":"graph-to-graph-transformer-for-transition","title":"Graph-to-Graph Transformer for Transition-based Dependency Parsing","date":"2019-11-08","arxiv_id":"1911.03561","n_code_links":1,"syntology":null},{"paper":null,"slug":"question-generation-from-paragraphs-a-tale-of-1","title":"Question Generation from Paragraphs: A Tale of Two Hierarchical Models","date":"2019-11-08","arxiv_id":"1911.03407","n_code_links":0,"syntology":null},{"paper":null,"slug":"resurrecting-submodularity-in-neural","title":"Resurrecting Submodularity for Neural Text Generation","date":"2019-11-08","arxiv_id":"1911.03014","n_code_links":0,"syntology":null},{"paper":"/paper/towards-hierarchical-importance-attribution-1","slug":"towards-hierarchical-importance-attribution-1","title":"Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models","date":"2019-11-08","arxiv_id":"1911.06194","n_code_links":3,"syntology":null},{"paper":null,"slug":"why-deep-transformers-are-difficult-to","title":"Lipschitz Constrained Parameter Initialization for Deep Transformers","date":"2019-11-08","arxiv_id":"1911.03179","n_code_links":0,"syntology":null},{"paper":"/paper/microsoft-research-asias-systems-for-wmt19-1","slug":"microsoft-research-asias-systems-for-wmt19-1","title":"Microsoft Research Asia's Systems for WMT19","date":"2019-11-07","arxiv_id":"1911.06191","n_code_links":0,"syntology":null},{"paper":null,"slug":"porous-lattice-based-transformer-encoder-for","title":"Porous Lattice-based Transformer Encoder for Chinese NER","date":"2019-11-07","arxiv_id":"1911.02733","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-contextualized-sentence","title":"Probing Contextualized Sentence Representations with Visual Awareness","date":"2019-11-07","arxiv_id":"1911.02971","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-end-to-end-approach-for-lexical-stress","title":"An End-to-end Approach for Lexical Stress Detection based on Transformer","date":"2019-11-06","arxiv_id":"1911.04862","n_code_links":0,"syntology":null},{"paper":"/paper/coke-contextualized-knowledge-graph-embedding","slug":"coke-contextualized-knowledge-graph-embedding","title":"CoKE: Contextualized Knowledge Graph Embedding","date":"2019-11-06","arxiv_id":"1911.02168","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["PaddlePaddle/Research","PaddlePaddle/models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enriching-conversation-context-in-retrieval","title":"Enriching Conversation Context in Retrieval-based Chatbots","date":"2019-11-06","arxiv_id":"1911.02290","n_code_links":0,"syntology":null},{"paper":"/paper/fast-transformer-decoding-one-write-head-is","slug":"fast-transformer-decoding-one-write-head-is","title":"Fast Transformer Decoding: One Write-Head is All You Need","date":"2019-11-06","arxiv_id":"1911.02150","n_code_links":4,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":null}},{"paper":"/paper/graph-transformer-networks-1","slug":"graph-transformer-networks-1","title":"Graph Transformer Networks","date":"2019-11-06","arxiv_id":"1911.06455","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-answer-by-learning-to-ask-getting","title":"Learning to Answer by Learning to Ask: Getting the Best of GPT-2 and BERT Worlds","date":"2019-11-06","arxiv_id":"1911.02365","n_code_links":0,"syntology":null},{"paper":null,"slug":"predictive-modeling-of-brain-tumor-a-deep","title":"Predictive modeling of brain tumor: A Deep learning approach","date":"2019-11-06","arxiv_id":"1911.02265","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-bidirectional-decoding-with-dynamic","title":"Improving Bidirectional Decoding with Dynamic Target Semantics in Neural Machine Translation","date":"2019-11-05","arxiv_id":"1911.01597","n_code_links":0,"syntology":null},{"paper":"/paper/an-algorithm-for-routing-capsules-in-all","slug":"an-algorithm-for-routing-capsules-in-all","title":"An Algorithm for Routing Capsules in All Domains","date":"2019-11-02","arxiv_id":"1911.00792","n_code_links":1,"syntology":null},{"paper":null,"slug":"machine-translation-evaluation-using-bi","title":"Machine Translation Evaluation using Bi-directional Entailment","date":"2019-11-02","arxiv_id":"1911.00681","n_code_links":0,"syntology":null},{"paper":null,"slug":"aggregating-bidirectional-encoder","title":"Aggregating Bidirectional Encoder Representations Using MatchLSTM for Sequence Matching","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"automatically-extracting-challenge-sets-for-1","title":"Automatically Extracting Challenge Sets for Non-Local Phenomena in Neural Machine Translation","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"combining-global-sparse-gradients-with-local","title":"Combining Global Sparse Gradients with Local Gradients in Distributed Neural Network Training","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cvits-submissions-to-wat-2019","title":"CVIT's submissions to WAT-2019","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/dialect-text-normalization-to-normative","slug":"dialect-text-normalization-to-normative","title":"Dialect Text Normalization to Normative Standard Finnish","date":"2019-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/dialogpt-large-scale-generative-pre-training","slug":"dialogpt-large-scale-generative-pre-training","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","date":"2019-11-01","arxiv_id":"1911.00536","n_code_links":6,"syntology":{"ran":6,"of":12,"n_ran_checked":5,"n_instrument":1,"unverified":6,"pointer_only":12,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["microsoft/DialoGPT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"english-to-hindi-multi-modal-neural-machine","title":"English to Hindi Multi-modal Neural Machine Translation and Hindi Image Captioning","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"enhanced-transformer-model-for-data-to-text","title":"Enhanced Transformer Model for Data-to-Text Generation","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"idiap-nmt-system-for-wat-2019-multimodal","title":"Idiap NMT System for WAT 2019 Multimodal Translation Task","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-answer-selection-and-answer","title":"Improving Answer Selection and Answer Triggering using Hard Negatives","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-generalization-of-transformer-for","title":"Improving Generalization of Transformer for Speech Recognition with Parallel Schedule Sampling and Relative Positional Embedding","date":"2019-11-01","arxiv_id":"1911.00203","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-natural-language-understanding-by","title":"Improving Natural Language Understanding by Reverse Mapping Bytepair Encoding","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"inspecting-unification-of-encoding-and","title":"Inspecting Unification of Encoding and Matching with Transformer: A Case Study of Machine Reading Comprehension","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"long-warm-up-and-self-training-training","title":"Long Warm-up and Self-Training: Training Strategies of NICT-2 NMT System at WAT-2019","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ltrc-mt-simple-textbackslash-effective-hindi","title":"LTRC-MT Simple \\& Effective Hindi-English Neural Machine Translation Systems at WAT 2019","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"mixed-multi-head-self-attention-for-neural","title":"Mixed Multi-Head Self-Attention for Neural Machine Translation","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-relation-between-position-information","title":"On the Relation between Position Information and Sentence Length in Neural Machine Translation","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"our-neural-machine-translation-systems-for","title":"Our Neural Machine Translation Systems for WAT 2019","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"recurrent-positional-embedding-for-neural","title":"Recurrent Positional Embedding for Neural Machine Translation","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"recycling-a-pre-trained-bert-encoder-for","title":"Recycling a Pre-trained BERT Encoder for Neural Machine Translation","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sarahs-participation-in-wat-2019","title":"Sarah's Participation in WAT 2019","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"self-adaptive-scaling-for-learnable-residual","title":"Self-Adaptive Scaling for Learnable Residual Structure","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"supervised-neural-machine-translation-based","title":"Supervised neural machine translation based on data augmentation and improved training \\& inference process","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"systran-wat-2019-russian-japanese-news","title":"SYSTRAN @ WAT 2019: Russian-Japanese News Commentary task","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"systran-wngt-2019-dgt-task","title":"SYSTRAN @ WNGT 2019: DGT Task","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-concordia-nlg-surface-realizer-at-srst","title":"The Concordia NLG Surface Realizer at SRST 2019","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-and-seq2seq-model-for-paraphrase","title":"Transformer and seq2seq model for Paraphrase Generation","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-model-for-single-documents","title":"Transformer-based Model for Single Documents Neural Summarization","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-dissection-an-unified-1","title":"Transformer Dissection: An Unified Understanding for Transformer's Attention via the Lens of Kernel","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transforming-delete-retrieve-generate-1","title":"``Transforming'' Delete, Retrieve, Generate Approach for Controlled Text Style Transfer","date":"2019-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/attention-is-all-you-need-for-chinese-word","slug":"attention-is-all-you-need-for-chinese-word","title":"Attention Is All You Need for Chinese Word Segmentation","date":"2019-10-31","arxiv_id":"1910.14537","n_code_links":1,"syntology":null},{"paper":null,"slug":"document-level-neural-machine-translation-2","title":"Document-level Neural Machine Translation with Associated Memory Network","date":"2019-10-31","arxiv_id":"1910.14528","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":"/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":"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":"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":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":"191013215","title":"Transformer-based Cascaded Multimodal Speech Translation","date":"2019-10-29","arxiv_id":"1910.13215","n_code_links":0,"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/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":"/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":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/model-agnostic-approaches-to-handling-noisy","slug":"model-agnostic-approaches-to-handling-noisy","title":"Model-agnostic Approaches to Handling Noisy Labels When Training Sound Event Classifiers","date":"2019-10-26","arxiv_id":"1910.12004","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":"label-smoothing-and-logit-squeezing-a","title":"Label Smoothing and Logit Squeezing: A Replacement for Adversarial Training?","date":"2019-10-25","arxiv_id":"1910.11585","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":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":"/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":"/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":"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":"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":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":"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":"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":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":"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":"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},{"paper":"/paper/enhancing-the-transformer-with-explicit-1","slug":"enhancing-the-transformer-with-explicit-1","title":"Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving","date":"2019-10-15","arxiv_id":"1910.06611","n_code_links":3,"syntology":{"ran":8,"of":11,"n_ran_checked":8,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["ischlag/TP-Transformer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}}],"record_sha256":"846ea102c50e76dec92c5dc339d21e1a2fe89c75d1935ff2a65d26626da07c27","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}