{"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/adam/papers/233","list_of":"/method/adam","method":"Adam","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":233,"pages_in_order":244,"rows_per_page":100,"rows":[23201,23300],"of":24390,"counts":{"archive_papers_tagged":24390,"with_a_code_link":10944,"where_syntology_ran_a_sample":3424,"not_listed_spam_title":0,"listed":24390,"listed_where_code_ran":3424,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2899,"every_run_a_failure_of_syntologys_instrument":525,"listed_with_a_run_with_no_instrument_failure":2899,"listed_every_run_a_failure_of_syntologys_instrument":525,"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/adam","prev":"/method/adam/papers/232","next":"/method/adam/papers/234","papers":[{"paper":null,"slug":"what-does-bert-learn-from-multiple-choice","title":"What does BERT Learn from Multiple-Choice Reading Comprehension Datasets?","date":"2019-10-28","arxiv_id":"1910.12391","n_code_links":0,"syntology":null},{"paper":"/paper/an-adaptive-and-momental-bound-method-for","slug":"an-adaptive-and-momental-bound-method-for","title":"An Adaptive and Momental Bound Method for Stochastic Learning","date":"2019-10-27","arxiv_id":"1910.12249","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lancopku/AdaMod"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/open-the-boxes-of-words-incorporating-sememes","slug":"open-the-boxes-of-words-incorporating-sememes","title":"Word-level Textual Adversarial Attacking as Combinatorial Optimization","date":"2019-10-27","arxiv_id":"1910.12196","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["thunlp/SememePSO-Attack"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/thieves-on-sesame-street-model-extraction-of","slug":"thieves-on-sesame-street-model-extraction-of","title":"Thieves on Sesame Street! Model Extraction of BERT-based APIs","date":"2019-10-27","arxiv_id":"1910.12366","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-asr-models-by-generation-of","title":"Training ASR models by Generation of Contextual Information","date":"2019-10-27","arxiv_id":"1910.12367","n_code_links":0,"syntology":null},{"paper":null,"slug":"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":null,"slug":"on-the-tunability-of-optimizers-in-deep","title":"Optimizer Benchmarking Needs to Account for Hyperparameter Tuning","date":"2019-10-25","arxiv_id":"1910.11758","n_code_links":0,"syntology":null},{"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":"/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/hierarchical-transformers-for-long-document","slug":"hierarchical-transformers-for-long-document","title":"Hierarchical Transformers for Long Document Classification","date":"2019-10-23","arxiv_id":"1910.10781","n_code_links":3,"syntology":null},{"paper":null,"slug":"relation-module-for-non-answerable-prediction","title":"Relation Module for Non-answerable Prediction on Question Answering","date":"2019-10-23","arxiv_id":"1910.10843","n_code_links":0,"syntology":null},{"paper":null,"slug":"speech-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/an-efficient-ekf-based-algorithm-for-lstm","slug":"an-efficient-ekf-based-algorithm-for-lstm","title":"An Efficient and Effective Second-Order Training Algorithm for LSTM-based Adaptive Learning","date":"2019-10-22","arxiv_id":"1910.09857","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":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":"implementation-of-a-modified-nesterovs","title":"Implementation of a modified Nesterov's Accelerated quasi-Newton Method on Tensorflow","date":"2019-10-21","arxiv_id":"1910.09158","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":"/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":"robust-learning-rate-selection-for-stochastic","title":"Robust Learning Rate Selection for Stochastic Optimization via Splitting Diagnostic","date":"2019-10-18","arxiv_id":"1910.08597","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/bertram-improved-word-embeddings-have-big","slug":"bertram-improved-word-embeddings-have-big","title":"BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance","date":"2019-10-16","arxiv_id":"1910.07181","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["timoschick/bertram"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bridging-the-knowledge-gap-enhancing-question","title":"Bridging the Knowledge Gap: Enhancing Question Answering with World and Domain Knowledge","date":"2019-10-16","arxiv_id":"1910.07429","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficiency-through-auto-sizing-notre-dame","title":"Efficiency through Auto-Sizing: Notre Dame NLP's Submission to the WNGT 2019 Efficiency Task","date":"2019-10-16","arxiv_id":"1910.07134","n_code_links":0,"syntology":null},{"paper":null,"slug":"evolution-of-transfer-learning-in-natural","title":"Evolution of transfer learning in natural language processing","date":"2019-10-16","arxiv_id":"1910.07370","n_code_links":0,"syntology":null},{"paper":null,"slug":"imperial-college-london-submission-to-vatex","title":"Imperial College London Submission to VATEX Video Captioning Task","date":"2019-10-16","arxiv_id":"1910.07482","n_code_links":0,"syntology":null},{"paper":"/paper/injecting-hierarchy-with-u-net-transformers","slug":"injecting-hierarchy-with-u-net-transformers","title":"Injecting Hierarchy with U-Net Transformers","date":"2019-10-16","arxiv_id":"1910.10488","n_code_links":2,"syntology":null},{"paper":null,"slug":"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/aligning-cross-lingual-entities-with-multi","slug":"aligning-cross-lingual-entities-with-multi","title":"Aligning Cross-Lingual Entities with Multi-Aspect Information","date":"2019-10-15","arxiv_id":"1910.06575","n_code_links":1,"syntology":null},{"paper":"/paper/answering-complex-open-domain-questions","slug":"answering-complex-open-domain-questions","title":"Answering Complex Open-domain Questions Through Iterative Query Generation","date":"2019-10-15","arxiv_id":"1910.07000","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["qipeng/golden-retriever"],"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":"/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":"on-higher-order-moments-in-adam","title":"On Higher-order Moments in Adam","date":"2019-10-15","arxiv_id":"1910.06878","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/stancy-stance-classification-based-on","slug":"stancy-stance-classification-based-on","title":"STANCY: Stance Classification Based on Consistency Cues","date":"2019-10-14","arxiv_id":"1910.06048","n_code_links":1,"syntology":null},{"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/whatcha-lookin-at-deeplifting-berts-attention","slug":"whatcha-lookin-at-deeplifting-berts-attention","title":"Whatcha lookin' at? DeepLIFTing BERT's Attention in Question Answering","date":"2019-10-14","arxiv_id":"1910.06431","n_code_links":1,"syntology":null},{"paper":null,"slug":"progress-notes-classification-and-keyword","title":"Progress Notes Classification and Keyword Extraction using Attention-based Deep Learning Models with BERT","date":"2019-10-13","arxiv_id":"1910.05786","n_code_links":0,"syntology":null},{"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":"/paper/on-robustness-of-neural-ordinary-differential","slug":"on-robustness-of-neural-ordinary-differential","title":"On Robustness of Neural Ordinary Differential Equations","date":"2019-10-12","arxiv_id":"1910.05513","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["HanshuYAN/TisODE"],"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"]}}},{"paper":"/paper/vq-wav2vec-self-supervised-learning-of-1","slug":"vq-wav2vec-self-supervised-learning-of-1","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","date":"2019-10-12","arxiv_id":"1910.05453","n_code_links":3,"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":null}},{"paper":null,"slug":"automatic-segmentation-of-texts-into-units-of","title":"Automatic segmentation of texts into units of meaning for reading assistance","date":"2019-10-11","arxiv_id":"1910.05014","n_code_links":0,"syntology":null},{"paper":"/paper/bipar-a-bilingual-parallel-dataset-for","slug":"bipar-a-bilingual-parallel-dataset-for","title":"BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels","date":"2019-10-11","arxiv_id":"1910.05040","n_code_links":1,"syntology":null},{"paper":"/paper/decaying-momentum-helps-neural-network","slug":"decaying-momentum-helps-neural-network","title":"Demon: Improved Neural Network Training with Momentum Decay","date":"2019-10-11","arxiv_id":"1910.04952","n_code_links":2,"syntology":null},{"paper":"/paper/exbert-a-visual-analysis-tool-to-explore","slug":"exbert-a-visual-analysis-tool-to-explore","title":"exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models","date":"2019-10-11","arxiv_id":"1910.05276","n_code_links":1,"syntology":null},{"paper":"/paper/on-empirical-comparisons-of-optimizers-for","slug":"on-empirical-comparisons-of-optimizers-for","title":"On Empirical Comparisons of Optimizers for Deep Learning","date":"2019-10-11","arxiv_id":"1910.05446","n_code_links":2,"syntology":null},{"paper":"/paper/cross-lingual-alignment-vs-joint-training-a","slug":"cross-lingual-alignment-vs-joint-training-a","title":"Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework","date":"2019-10-10","arxiv_id":"1910.04708","n_code_links":2,"syntology":null},{"paper":"/paper/fuse-multi-faceted-set-expansion-by-coherent","slug":"fuse-multi-faceted-set-expansion-by-coherent","title":"FUSE: Multi-Faceted Set Expansion by Coherent Clustering of Skip-grams","date":"2019-10-10","arxiv_id":"1910.04345","n_code_links":3,"syntology":null},{"paper":"/paper/improving-sample-diversity-of-a-pre-trained","slug":"improving-sample-diversity-of-a-pre-trained","title":"A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings","date":"2019-10-10","arxiv_id":"1910.04760","n_code_links":1,"syntology":null},{"paper":"/paper/multi-label-categorization-of-accounts-of","slug":"multi-label-categorization-of-accounts-of","title":"Multi-label Categorization of Accounts of Sexism using a Neural Framework","date":"2019-10-10","arxiv_id":"1910.04602","n_code_links":1,"syntology":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/structured-pruning-of-large-language-models","slug":"structured-pruning-of-large-language-models","title":"Structured Pruning of Large Language Models","date":"2019-10-10","arxiv_id":"1910.04732","n_code_links":2,"syntology":{"ran":8,"of":12,"n_ran_checked":6,"n_instrument":2,"unverified":4,"pointer_only":2,"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) · 4 unverified","official":{"repos":["asappresearch/flop"],"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/visual-natural-language-query-auto-completion","slug":"visual-natural-language-query-auto-completion","title":"Visual Natural Language Query Auto-Completion for Estimating Instance Probabilities","date":"2019-10-10","arxiv_id":"1910.04887","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-closer-look-at-feature-space-data","title":"A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification","date":"2019-10-09","arxiv_id":"1910.04176","n_code_links":0,"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":null,"slug":"ctrl-z-recovering-from-instability-in","title":"Ctrl-Z: Recovering from Instability in Reinforcement Learning","date":"2019-10-09","arxiv_id":"1910.03732","n_code_links":0,"syntology":null},{"paper":"/paper/is-multilingual-bert-fluent-in-language","slug":"is-multilingual-bert-fluent-in-language","title":"Is Multilingual BERT Fluent in Language Generation?","date":"2019-10-09","arxiv_id":"1910.03806","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":"knowledge-distillation-from-internal","title":"Knowledge Distillation from Internal Representations","date":"2019-10-08","arxiv_id":"1910.03723","n_code_links":0,"syntology":null},{"paper":"/paper/melgan-generative-adversarial-networks-for","slug":"melgan-generative-adversarial-networks-for","title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","date":"2019-10-08","arxiv_id":"1910.06711","n_code_links":21,"syntology":{"ran":6,"of":7,"n_ran_checked":2,"n_instrument":4,"unverified":1,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["descriptinc/melgan-neurips"],"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":["listed","official"]}}},{"paper":null,"slug":"sesamebert-attention-for-anywhere","title":"SesameBERT: Attention for Anywhere","date":"2019-10-08","arxiv_id":"1910.03176","n_code_links":0,"syntology":null},{"paper":"/paper/bert-for-evidence-retrieval-and-claim","slug":"bert-for-evidence-retrieval-and-claim","title":"BERT for Evidence Retrieval and Claim Verification","date":"2019-10-07","arxiv_id":"1910.02655","n_code_links":2,"syntology":{"ran":4,"of":6,"n_ran_checked":0,"n_instrument":4,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/parallel-iterative-edit-models-for-local","slug":"parallel-iterative-edit-models-for-local","title":"Parallel Iterative Edit Models for Local Sequence Transduction","date":"2019-10-07","arxiv_id":"1910.02893","n_code_links":1,"syntology":null},{"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/named-entity-recognition-is-there-a-glass","slug":"named-entity-recognition-is-there-a-glass","title":"Named Entity Recognition -- Is there a glass ceiling?","date":"2019-10-06","arxiv_id":"1910.02403","n_code_links":1,"syntology":null}],"record_sha256":"450ec4e8fc93f58530446debfc9143a9851af62dfd5047d5a48e122110f3afa8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}