{"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/bpe/papers/185","list_of":"/method/bpe","method":"BPE","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":185,"pages_in_order":190,"rows_per_page":100,"rows":[18401,18500],"of":18975,"counts":{"archive_papers_tagged":18975,"with_a_code_link":8675,"where_syntology_ran_a_sample":2895,"not_listed_spam_title":0,"listed":18975,"listed_where_code_ran":2895,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2443,"every_run_a_failure_of_syntologys_instrument":452,"listed_with_a_run_with_no_instrument_failure":2443,"listed_every_run_a_failure_of_syntologys_instrument":452,"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/bpe","prev":"/method/bpe/papers/184","next":"/method/bpe/papers/186","papers":[{"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":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/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/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":"/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":"/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":"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":"/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/byte-pair-encoding-for-text-to-sql-generation","slug":"byte-pair-encoding-for-text-to-sql-generation","title":"Byte-Pair Encoding for Text-to-SQL Generation","date":"2019-10-20","arxiv_id":"1910.08962","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":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":"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"]}}},{"paper":null,"slug":"facebook-ais-wat19-myanmar-english","title":"Facebook AI's WAT19 Myanmar-English Translation Task Submission","date":"2019-10-15","arxiv_id":"1910.06848","n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-a-bert-based-question-answering-model","title":"Structured Pruning of a BERT-based Question Answering Model","date":"2019-10-14","arxiv_id":"1910.06360","n_code_links":0,"syntology":null},{"paper":"/paper/q8bert-quantized-8bit-bert","slug":"q8bert-quantized-8bit-bert","title":"Q8BERT: Quantized 8Bit BERT","date":"2019-10-14","arxiv_id":"1910.06188","n_code_links":5,"syntology":{"ran":10,"of":11,"n_ran_checked":9,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["intellabs/model-compression-research-package","NervanaSystems/nlp-architect"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/transformers-without-tears-improving-the","slug":"transformers-without-tears-improving-the","title":"Transformers without Tears: Improving the Normalization of Self-Attention","date":"2019-10-14","arxiv_id":"1910.05895","n_code_links":5,"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, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tnq177/transformers_without_tears"],"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":"/paper/stabilizing-transformers-for-reinforcement-1","slug":"stabilizing-transformers-for-reinforcement-1","title":"Stabilizing Transformers for Reinforcement Learning","date":"2019-10-13","arxiv_id":"1910.06764","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"multilingual-question-answering-from","title":"Multilingual Question Answering from Formatted Text applied to Conversational Agents","date":"2019-10-10","arxiv_id":"1910.04659","n_code_links":0,"syntology":null},{"paper":"/paper/on-recognizing-texts-of-arbitrary-shapes-with","slug":"on-recognizing-texts-of-arbitrary-shapes-with","title":"On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention","date":"2019-10-10","arxiv_id":"1910.04396","n_code_links":2,"syntology":null},{"paper":"/paper/alternating-recurrent-dialog-model-with-large","slug":"alternating-recurrent-dialog-model-with-large","title":"Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models","date":"2019-10-09","arxiv_id":"1910.03756","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-adequacy-of-untuned-warmup-for","slug":"on-the-adequacy-of-untuned-warmup-for","title":"On the adequacy of untuned warmup for adaptive optimization","date":"2019-10-09","arxiv_id":"1910.04209","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":null}},{"paper":"/paper/pipemare-asynchronous-pipeline-parallel-dnn","slug":"pipemare-asynchronous-pipeline-parallel-dnn","title":"PipeMare: Asynchronous Pipeline Parallel DNN Training","date":"2019-10-09","arxiv_id":"1910.05124","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-state-of-the-art-natural","slug":"transformers-state-of-the-art-natural","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","date":"2019-10-09","arxiv_id":"1910.03771","n_code_links":9,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["huggingface/transformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"smart-training-shallow-memory-aware","title":"SMArT: Training Shallow Memory-aware Transformers for Robotic Explainability","date":"2019-10-07","arxiv_id":"1910.02974","n_code_links":0,"syntology":null},{"paper":"/paper/how-transformer-revitalizes-character-based","slug":"how-transformer-revitalizes-character-based","title":"How Transformer Revitalizes Character-based Neural Machine Translation: An Investigation on Japanese-Vietnamese Translation Systems","date":"2019-10-05","arxiv_id":"1910.02238","n_code_links":1,"syntology":null},{"paper":"/paper/zero-memory-optimization-towards-training-a","slug":"zero-memory-optimization-towards-training-a","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","date":"2019-10-04","arxiv_id":"1910.02054","n_code_links":10,"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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["NVIDIA/Megatron-LM","microsoft/DeepSpeed"],"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":"neural-zero-inflated-quality-estimation-model","title":"Neural Zero-Inflated Quality Estimation Model For Automatic Speech Recognition System","date":"2019-10-03","arxiv_id":"1910.01289","n_code_links":0,"syntology":null},{"paper":"/paper/towards-understanding-of-medical-randomized","slug":"towards-understanding-of-medical-randomized","title":"Towards Understanding of Medical Randomized Controlled Trials by Conclusion Generation","date":"2019-10-03","arxiv_id":"1910.01462","n_code_links":1,"syntology":null},{"paper":null,"slug":"application-of-low-resource-machine","title":"Application of Low-resource Machine Translation Techniques to Russian-Tatar Language Pair","date":"2019-10-01","arxiv_id":"1910.00368","n_code_links":0,"syntology":null},{"paper":"/paper/auto-sizing-the-transformer-network-improving","slug":"auto-sizing-the-transformer-network-improving","title":"Auto-Sizing the Transformer Network: Improving Speed, Efficiency, and Performance for Low-Resource Machine Translation","date":"2019-10-01","arxiv_id":"1910.06717","n_code_links":1,"syntology":null},{"paper":"/paper/dialogue-transformers","slug":"dialogue-transformers","title":"Dialogue Transformers","date":"2019-10-01","arxiv_id":"1910.00486","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficiency-metrics-for-data-driven-models-a-1","title":"Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study","date":"2019-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"entangled-transformer-for-image-captioning","title":"Entangled Transformer for Image Captioning","date":"2019-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/grammatical-error-correction-in-low-resource","slug":"grammatical-error-correction-in-low-resource","title":"Grammatical Error Correction in Low-Resource Scenarios","date":"2019-10-01","arxiv_id":"1910.00353","n_code_links":1,"syntology":null},{"paper":null,"slug":"putting-machine-translation-in-context-with-1","title":"Better Document-Level Machine Translation with Bayes' Rule","date":"2019-10-01","arxiv_id":"1910.00553","n_code_links":0,"syntology":null},{"paper":null,"slug":"tmlab-generative-enhanced-model-gem-for","title":"TMLab: Generative Enhanced Model (GEM) for adversarial attacks","date":"2019-10-01","arxiv_id":"1910.00337","n_code_links":0,"syntology":null},{"paper":"/paper/monotonic-multihead-attention-1","slug":"monotonic-multihead-attention-1","title":"Monotonic Multihead Attention","date":"2019-09-26","arxiv_id":"1909.12406","n_code_links":3,"syntology":null},{"paper":"/paper/unsupervised-universal-self-attention-network","slug":"unsupervised-universal-self-attention-network","title":"Universal Graph Transformer Self-Attention Networks","date":"2019-09-26","arxiv_id":"1909.11855","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["daiquocnguyen/Graph-Transformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/attention-convolutional-binary-neural-tree","slug":"attention-convolutional-binary-neural-tree","title":"Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization","date":"2019-09-25","arxiv_id":"1909.11378","n_code_links":2,"syntology":null},{"paper":null,"slug":"extreme-language-model-compression-with-1","title":"Extremely Small BERT Models from Mixed-Vocabulary Training","date":"2019-09-25","arxiv_id":"1909.11687","n_code_links":0,"syntology":null},{"paper":"/paper/reducing-transformer-depth-on-demand-with-1","slug":"reducing-transformer-depth-on-demand-with-1","title":"Reducing Transformer Depth on Demand with Structured Dropout","date":"2019-09-25","arxiv_id":"1909.11556","n_code_links":5,"syntology":null},{"paper":"/paper/knowledge-enriched-transformer-for-emotion","slug":"knowledge-enriched-transformer-for-emotion","title":"Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations","date":"2019-09-24","arxiv_id":"1909.10681","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhongpeixiang/KET"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transfer-learning-across-languages-from","title":"Efficiently Reusing Old Models Across Languages via Transfer Learning","date":"2019-09-24","arxiv_id":"1909.10955","n_code_links":0,"syntology":null},{"paper":"/paper/unified-vision-language-pre-training-for","slug":"unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","date":"2019-09-24","arxiv_id":"1909.11059","n_code_links":3,"syntology":{"ran":11,"of":14,"n_ran_checked":8,"n_instrument":3,"unverified":3,"pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["LuoweiZhou/VLP"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/190910351","slug":"190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","arxiv_id":"1909.10351","n_code_links":10,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"0 ran · 4 unverified","official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":null,"slug":"190909779","title":"Self-attention based end-to-end Hindi-English Neural Machine Translation","date":"2019-09-21","arxiv_id":"1909.09779","n_code_links":0,"syntology":null},{"paper":null,"slug":"190909801","title":"Adversarial Learning of General Transformations for Data Augmentation","date":"2019-09-21","arxiv_id":"1909.09801","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-ways-to-incorporate-additional","title":"How Additional Knowledge can Improve Natural Language Commonsense Question Answering?","date":"2019-09-19","arxiv_id":"1909.08855","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-variational-neural-machine","title":"Improved Variational Neural Machine Translation by Promoting Mutual Information","date":"2019-09-19","arxiv_id":"1909.09237","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-and-automated-essay-scoring","slug":"language-models-and-automated-essay-scoring","title":"Language models and Automated Essay Scoring","date":"2019-09-18","arxiv_id":"1909.09482","n_code_links":1,"syntology":null},{"paper":"/paper/megatron-lm-training-multi-billion-parameter","slug":"megatron-lm-training-multi-billion-parameter","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","date":"2019-09-17","arxiv_id":"1909.08053","n_code_links":10,"syntology":{"ran":12,"of":47,"n_ran_checked":7,"n_instrument":5,"unverified":35,"pointer_only":15,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 35 unverified","official":{"repos":["NVIDIA/Megatron-LM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"hybrid-neural-models-for-sequence-modelling","title":"Hybrid Neural Models For Sequence Modelling: The Best Of Three Worlds","date":"2019-09-16","arxiv_id":"1909.07102","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-neural-machine-translation-for","slug":"multilingual-neural-machine-translation-for","title":"Multilingual Neural Machine Translation for Zero-Resource Languages","date":"2019-09-16","arxiv_id":"1909.07342","n_code_links":1,"syntology":null},{"paper":"/paper/automatically-extracting-challenge-sets-for","slug":"automatically-extracting-challenge-sets-for","title":"Automatically Extracting Challenge Sets for Non local Phenomena in Neural Machine Translation","date":"2019-09-15","arxiv_id":"1909.06814","n_code_links":1,"syntology":null},{"paper":"/paper/cross-lingual-bert-transformation-for-zero","slug":"cross-lingual-bert-transformation-for-zero","title":"Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing","date":"2019-09-15","arxiv_id":"1909.06775","n_code_links":1,"syntology":null},{"paper":null,"slug":"i-mad-a-novel-interpretable-malware-detector","title":"I-MAD: Interpretable Malware Detector Using Galaxy Transformer","date":"2019-09-15","arxiv_id":"1909.06865","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-and-power-evaluation-of-ai","title":"Benchmarking the Performance and Energy Efficiency of AI Accelerators for AI Training","date":"2019-09-15","arxiv_id":"1909.06842","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficiency-metrics-for-data-driven-models-a","title":"Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study","date":"2019-09-14","arxiv_id":"1909.06618","n_code_links":0,"syntology":null},{"paper":"/paper/ouroboros-on-accelerating-training-of","slug":"ouroboros-on-accelerating-training-of","title":"Ouroboros: On Accelerating Training of Transformer-Based Language Models","date":"2019-09-14","arxiv_id":"1909.06695","n_code_links":1,"syntology":null},{"paper":"/paper/tree-transformer-integrating-tree-structures","slug":"tree-transformer-integrating-tree-structures","title":"Tree Transformer: Integrating Tree Structures into Self-Attention","date":"2019-09-14","arxiv_id":"1909.06639","n_code_links":3,"syntology":{"ran":9,"of":10,"n_ran_checked":7,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yaushian/Tree-Transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/a-comparative-study-on-transformer-vs-rnn-in","slug":"a-comparative-study-on-transformer-vs-rnn-in","title":"A Comparative Study on Transformer vs RNN in Speech Applications","date":"2019-09-13","arxiv_id":"1909.06317","n_code_links":2,"syntology":null},{"paper":null,"slug":"neural-machine-translation-with-4-bit","title":"Neural Machine Translation with 4-Bit Precision and Beyond","date":"2019-09-13","arxiv_id":"1909.06091","n_code_links":0,"syntology":null},{"paper":null,"slug":"sanvis-visual-analytics-for-understanding","title":"SANVis: Visual Analytics for Understanding Self-Attention Networks","date":"2019-09-13","arxiv_id":"1909.09595","n_code_links":0,"syntology":null},{"paper":null,"slug":"scene-graph-parsing-by-attention-graph","title":"Scene Graph Parsing by Attention Graph","date":"2019-09-13","arxiv_id":"1909.06273","n_code_links":0,"syntology":null},{"paper":null,"slug":"cuni-system-for-the-building-educational-1","title":"CUNI System for the Building Educational Applications 2019 Shared Task: Grammatical Error Correction","date":"2019-09-12","arxiv_id":"1909.05553","n_code_links":0,"syntology":null},{"paper":"/paper/ctrl-a-conditional-transformer-language-model-1","slug":"ctrl-a-conditional-transformer-language-model-1","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","date":"2019-09-11","arxiv_id":"1909.05858","n_code_links":8,"syntology":{"ran":14,"of":14,"n_ran_checked":11,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"14 ran (of which 3 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/frustratingly-easy-natural-question-answering","slug":"frustratingly-easy-natural-question-answering","title":"Frustratingly Easy Natural Question Answering","date":"2019-09-11","arxiv_id":"1909.05286","n_code_links":0,"syntology":null},{"paper":null,"slug":"global-locality-in-event-extraction","title":"Global Locality in Biomedical Relation and Event Extraction","date":"2019-09-11","arxiv_id":"1909.04822","n_code_links":0,"syntology":null},{"paper":"/paper/how-does-bert-answer-questions-a-layer-wise","slug":"how-does-bert-answer-questions-a-layer-wise","title":"How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations","date":"2019-09-11","arxiv_id":"1909.04925","n_code_links":2,"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":["bvanaken/explain-BERT-QA"],"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":null,"slug":"forecaster-a-graph-transformer-for","title":"Forecaster: A Graph Transformer for Forecasting Spatial and Time-Dependent Data","date":"2019-09-09","arxiv_id":"1909.04019","n_code_links":0,"syntology":null},{"paper":"/paper/pretrained-language-models-for-sequential","slug":"pretrained-language-models-for-sequential","title":"Pretrained Language Models for Sequential Sentence Classification","date":"2019-09-09","arxiv_id":"1909.04054","n_code_links":1,"syntology":null}],"record_sha256":"c87b4163e80c9aadbbf551dcf1a1bd2f65830f935d5d20dfcacd731c6dfefa64","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}