{"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/230","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":230,"pages_in_order":244,"rows_per_page":100,"rows":[22901,23000],"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/229","next":"/method/adam/papers/231","papers":[{"paper":"/paper/neural-simile-recognition-with-cyclic","slug":"neural-simile-recognition-with-cyclic","title":"Neural Simile Recognition with Cyclic Multitask Learning and Local Attention","date":"2019-12-19","arxiv_id":"1912.09084","n_code_links":1,"syntology":null},{"paper":"/paper/temporal-fusion-transformers-for","slug":"temporal-fusion-transformers-for","title":"Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting","date":"2019-12-19","arxiv_id":"1912.09363","n_code_links":36,"syntology":{"ran":8,"of":10,"n_ran_checked":4,"n_instrument":4,"unverified":2,"pointer_only":5,"phrase":"8 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; 4 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/a-multi-task-learning-model-for-chinese","slug":"a-multi-task-learning-model-for-chinese","title":"A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term Extraction","date":"2019-12-17","arxiv_id":"1912.07976","n_code_links":6,"syntology":null},{"paper":null,"slug":"cross-lingual-ability-of-multilingual-bert-an-1","title":"Cross-Lingual Ability of Multilingual BERT: An Empirical Study","date":"2019-12-17","arxiv_id":"1912.07840","n_code_links":0,"syntology":null},{"paper":"/paper/m2-meshed-memory-transformer-for-image","slug":"m2-meshed-memory-transformer-for-image","title":"Meshed-Memory Transformer for Image Captioning","date":"2019-12-17","arxiv_id":"1912.08226","n_code_links":2,"syntology":{"ran":8,"of":8,"n_ran_checked":6,"n_instrument":2,"unverified":0,"pointer_only":3,"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) · 0 unverified","official":{"repos":["aimagelab/meshed-memory-transformer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-performance-evaluation-of-multi","title":"The performance evaluation of Multi-representation in the Deep Learning models for Relation Extraction Task","date":"2019-12-17","arxiv_id":"1912.08290","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-malware-representation-based-on","title":"Learning Malware Representation based on Execution Sequences","date":"2019-12-16","arxiv_id":"1912.07250","n_code_links":0,"syntology":null},{"paper":"/paper/parameter-continuation-methods-for-the","slug":"parameter-continuation-methods-for-the","title":"Parameter Continuation Methods for the Optimization of Deep Neural Networks","date":"2019-12-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/unas-differentiable-architecture-search-meets","slug":"unas-differentiable-architecture-search-meets","title":"UNAS: Differentiable Architecture Search Meets Reinforcement Learning","date":"2019-12-16","arxiv_id":"1912.07651","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-is-not-enough-bert-for-finnish","slug":"multilingual-is-not-enough-bert-for-finnish","title":"Multilingual is not enough: BERT for Finnish","date":"2019-12-15","arxiv_id":"1912.07076","n_code_links":1,"syntology":null},{"paper":"/paper/robust-named-entity-recognition-with","slug":"robust-named-entity-recognition-with","title":"Robust Named Entity Recognition with Truecasing Pretraining","date":"2019-12-15","arxiv_id":"1912.07095","n_code_links":0,"syntology":null},{"paper":null,"slug":"bertqa-attention-on-steroids","title":"BERTQA -- Attention on Steroids","date":"2019-12-14","arxiv_id":"1912.10435","n_code_links":0,"syntology":null},{"paper":"/paper/towards-robust-toxic-content-classification","slug":"towards-robust-toxic-content-classification","title":"Towards Robust Toxic Content Classification","date":"2019-12-14","arxiv_id":"1912.06872","n_code_links":1,"syntology":null},{"paper":"/paper/voice-transformer-network-sequence-to","slug":"voice-transformer-network-sequence-to","title":"Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining","date":"2019-12-14","arxiv_id":"1912.06813","n_code_links":2,"syntology":null},{"paper":"/paper/topoact-exploring-the-shape-of-activations-in","slug":"topoact-exploring-the-shape-of-activations-in","title":"TopoAct: Visually Exploring the Shape of Activations in Deep Learning","date":"2019-12-13","arxiv_id":"1912.06332","n_code_links":1,"syntology":null},{"paper":null,"slug":"waldorf-wasteless-language-model-distillation","title":"WaLDORf: Wasteless Language-model Distillation On Reading-comprehension","date":"2019-12-13","arxiv_id":"1912.06638","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-has-a-moral-compass-improvements-of","title":"BERT has a Moral Compass: Improvements of ethical and moral values of machines","date":"2019-12-11","arxiv_id":"1912.05238","n_code_links":0,"syntology":null},{"paper":"/paper/advances-and-open-problems-in-federated","slug":"advances-and-open-problems-in-federated","title":"Advances and Open Problems in Federated Learning","date":"2019-12-10","arxiv_id":"1912.04977","n_code_links":9,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"encoding-musical-style-with-transformer-1","title":"Encoding Musical Style with Transformer Autoencoders","date":"2019-12-10","arxiv_id":"1912.05537","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-transfer-learning-via-bert","title":"Unsupervised Transfer Learning via BERT Neuron Selection","date":"2019-12-10","arxiv_id":"1912.05308","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-a-layout-transfer-network-for","title":"Learning a Layout Transfer Network for Context Aware Object Detection","date":"2019-12-09","arxiv_id":"1912.03865","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-reinforcement-learning-for","title":"Transformer Based Reinforcement Learning For Games","date":"2019-12-09","arxiv_id":"1912.03918","n_code_links":0,"syntology":null},{"paper":"/paper/bidirectional-scene-text-recognition-with-a","slug":"bidirectional-scene-text-recognition-with-a","title":"Bidirectional Scene Text Recognition with a Single Decoder","date":"2019-12-08","arxiv_id":"1912.03656","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-analysis-of-natural-language","title":"Adversarial Analysis of Natural Language Inference Systems","date":"2019-12-07","arxiv_id":"1912.03441","n_code_links":0,"syntology":null},{"paper":null,"slug":"personalized-patent-claim-generation-and","title":"Personalized Patent Claim Generation and Measurement","date":"2019-12-07","arxiv_id":"1912.03502","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-mask-for-transformer-based-end-to","slug":"semantic-mask-for-transformer-based-end-to","title":"Semantic Mask for Transformer based End-to-End Speech Recognition","date":"2019-12-06","arxiv_id":"1912.03010","n_code_links":1,"syntology":null},{"paper":null,"slug":"synchronous-transformers-for-end-to-end","title":"Synchronous Transformers for End-to-End Speech Recognition","date":"2019-12-06","arxiv_id":"1912.02958","n_code_links":0,"syntology":null},{"paper":null,"slug":"weak-supervision-helps-emergence-of-word","title":"Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks","date":"2019-12-06","arxiv_id":"1912.03063","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-adam-beats-sgd-for-attention-models-1","title":"Why are Adaptive Methods Good for Attention Models?","date":"2019-12-06","arxiv_id":"1912.03194","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-contextual-language","title":"Self-Supervised Contextual Language Representation of Radiology Reports to Improve the Identification of Communication Urgency","date":"2019-12-05","arxiv_id":"1912.02703","n_code_links":0,"syntology":null},{"paper":null,"slug":"acquiring-knowledge-from-pre-trained-model-to","title":"Acquiring Knowledge from Pre-trained Model to Neural Machine Translation","date":"2019-12-04","arxiv_id":"1912.01774","n_code_links":0,"syntology":null},{"paper":null,"slug":"amused-a-multi-stream-vector-representation-1","title":"AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue","date":"2019-12-04","arxiv_id":"1912.10160","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exploration-of-data-augmentation-and-1","title":"An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering","date":"2019-12-04","arxiv_id":"1912.02145","n_code_links":0,"syntology":null},{"paper":"/paper/domain-independent-dominance-of-adaptive-1","slug":"domain-independent-dominance-of-adaptive-1","title":"Domain-independent Dominance of Adaptive Methods","date":"2019-12-04","arxiv_id":"1912.01823","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-relation-extraction-using-syntactic","slug":"enhancing-relation-extraction-using-syntactic","title":"Enhancing Relation Extraction Using Syntactic Indicators and Sentential Contexts","date":"2019-12-04","arxiv_id":"1912.01858","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-pretrained-language","title":"A Comparative Study of Pretrained Language Models on Thai Social Text Categorization","date":"2019-12-03","arxiv_id":"1912.01580","n_code_links":0,"syntology":null},{"paper":"/paper/analyzing-and-improving-the-image-quality-of","slug":"analyzing-and-improving-the-image-quality-of","title":"Analyzing and Improving the Image Quality of StyleGAN","date":"2019-12-03","arxiv_id":"1912.04958","n_code_links":126,"syntology":{"ran":68,"of":92,"n_ran_checked":50,"n_instrument":18,"unverified":24,"pointer_only":25,"phrase":"68 ran (of which 0 constructed an object rather than computing a result; 50 with no instrument failure: 3 honoured, 6 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 24 unverified","official":{"repos":["NVlabs/stylegan2"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"joint-graph-based-depth-refinement-and-normal","title":"Joint Graph-based Depth Refinement and Normal Estimation","date":"2019-12-03","arxiv_id":"1912.01306","n_code_links":0,"syntology":null},{"paper":"/paper/tu-wien-trec-deep-learning-19-simple","slug":"tu-wien-trec-deep-learning-19-simple","title":"TU Wien @ TREC Deep Learning '19 -- Simple Contextualization for Re-ranking","date":"2019-12-03","arxiv_id":"1912.01385","n_code_links":1,"syntology":null},{"paper":null,"slug":"audiovisual-transformer-architectures-for","title":"Audiovisual Transformer Architectures for Large-Scale Classification and Synchronization of Weakly Labeled Audio Events","date":"2019-12-02","arxiv_id":"1912.02615","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-for-large-scale-video-segment","title":"BERT for Large-scale Video Segment Classification with Test-time Augmentation","date":"2019-12-02","arxiv_id":"1912.01127","n_code_links":0,"syntology":null},{"paper":"/paper/blimp-a-benchmark-of-linguistic-minimal-pairs","slug":"blimp-a-benchmark-of-linguistic-minimal-pairs","title":"BLiMP: The Benchmark of Linguistic Minimal Pairs for English","date":"2019-12-02","arxiv_id":"1912.00582","n_code_links":4,"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":{"repos":["alexwarstadt/blimp","alexwarstadt/data_generation"],"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":"detecting-gan-generated-errors","title":"Detecting GAN generated errors","date":"2019-12-02","arxiv_id":"1912.00527","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-contextual-embeddings-for","title":"Leveraging Contextual Embeddings for Detecting Diachronic Semantic Shift","date":"2019-12-02","arxiv_id":"1912.01072","n_code_links":0,"syntology":null},{"paper":"/paper/logan-latent-optimisation-for-generative-1","slug":"logan-latent-optimisation-for-generative-1","title":"LOGAN: Latent Optimisation for Generative Adversarial Networks","date":"2019-12-02","arxiv_id":"1912.00953","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":4,"n_instrument":1,"unverified":3,"pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/long-distance-relationships-without-time","slug":"long-distance-relationships-without-time","title":"Long Distance Relationships without Time Travel: Boosting the Performance of a Sparse Predictive Autoencoder in Sequence Modeling","date":"2019-12-02","arxiv_id":"1912.01116","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-scale-self-attention-for-text","title":"Multi-Scale Self-Attention for Text Classification","date":"2019-12-02","arxiv_id":"1912.00544","n_code_links":0,"syntology":null},{"paper":"/paper/neural-academic-paper-generation","slug":"neural-academic-paper-generation","title":"Neural Academic Paper Generation","date":"2019-12-02","arxiv_id":"1912.01982","n_code_links":1,"syntology":null},{"paper":"/paper/neural-predictor-for-neural-architecture","slug":"neural-predictor-for-neural-architecture","title":"Neural Predictor for Neural Architecture Search","date":"2019-12-02","arxiv_id":"1912.00848","n_code_links":2,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"on-policy-reinforcement-learning-with-entropy","title":"Policy Optimization Reinforcement Learning with Entropy Regularization","date":"2019-12-02","arxiv_id":"1912.01557","n_code_links":0,"syntology":null},{"paper":"/paper/solving-arithmetic-word-problems","slug":"solving-arithmetic-word-problems","title":"Solving Arithmetic Word Problems Automatically Using Transformer and Unambiguous Representations","date":"2019-12-02","arxiv_id":"1912.00871","n_code_links":1,"syntology":null},{"paper":"/paper/better-exploration-with-optimistic-actor-1","slug":"better-exploration-with-optimistic-actor-1","title":"Better Exploration with Optimistic Actor Critic","date":"2019-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/fast-and-accurate-stochastic-gradient","slug":"fast-and-accurate-stochastic-gradient","title":"Fast and Accurate Stochastic Gradient Estimation","date":"2019-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"hybrid-8-bit-floating-point-hfp8-training-and","title":"Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks","date":"2019-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/memory-efficient-adaptive-optimization","slug":"memory-efficient-adaptive-optimization","title":"Memory Efficient Adaptive Optimization","date":"2019-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"perceiving-the-arrow-of-time-in","title":"Perceiving the arrow of time in autoregressive motion","date":"2019-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/whats-hidden-in-a-randomly-weighted-neural","slug":"whats-hidden-in-a-randomly-weighted-neural","title":"What's Hidden in a Randomly Weighted Neural Network?","date":"2019-11-29","arxiv_id":"1911.13299","n_code_links":4,"syntology":{"ran":9,"of":9,"n_ran_checked":8,"n_instrument":1,"unverified":0,"pointer_only":5,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/hidden-networks"],"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"]}}},{"paper":null,"slug":"inducing-relational-knowledge-from-bert","title":"Inducing Relational Knowledge from BERT","date":"2019-11-28","arxiv_id":"1911.12753","n_code_links":0,"syntology":null},{"paper":null,"slug":"minimum-bayes-risk-training-of-rnn-transducer","title":"Minimum Bayes Risk Training of RNN-Transducer for End-to-End Speech Recognition","date":"2019-11-28","arxiv_id":"1911.12487","n_code_links":0,"syntology":null},{"paper":"/paper/define-deep-factorized-input-word-embeddings-1","slug":"define-deep-factorized-input-word-embeddings-1","title":"DeFINE: DEep Factorized INput Token Embeddings for Neural Sequence Modeling","date":"2019-11-27","arxiv_id":"1911.12385","n_code_links":1,"syntology":null},{"paper":"/paper/do-attention-heads-in-bert-track-syntactic","slug":"do-attention-heads-in-bert-track-syntactic","title":"Do Attention Heads in BERT Track Syntactic Dependencies?","date":"2019-11-27","arxiv_id":"1911.12246","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-commonsense-in-pre-trained","slug":"evaluating-commonsense-in-pre-trained","title":"Evaluating Commonsense in Pre-trained Language Models","date":"2019-11-27","arxiv_id":"1911.11931","n_code_links":1,"syntology":null},{"paper":null,"slug":"simplebooks-long-term-dependency-book-dataset","title":"SimpleBooks: Long-term dependency book dataset with simplified English vocabulary for word-level language modeling","date":"2019-11-27","arxiv_id":"1911.12391","n_code_links":0,"syntology":null},{"paper":null,"slug":"taking-a-stance-on-fake-news-towards","title":"Taking a Stance on Fake News: Towards Automatic Disinformation Assessment via Deep Bidirectional Transformer Language Models for Stance Detection","date":"2019-11-27","arxiv_id":"1911.11951","n_code_links":0,"syntology":null},{"paper":"/paper/your-local-gan-designing-two-dimensional","slug":"your-local-gan-designing-two-dimensional","title":"Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models","date":"2019-11-27","arxiv_id":"1911.12287","n_code_links":2,"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":["giannisdaras/ylg"],"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/autoencoding-undirected-molecular-graphs-with","slug":"autoencoding-undirected-molecular-graphs-with","title":"Autoencoding Undirected Molecular Graphs With Neural Networks","date":"2019-11-26","arxiv_id":"2001.03517","n_code_links":1,"syntology":null},{"paper":"/paper/deep-learning-with-gaussian-differential","slug":"deep-learning-with-gaussian-differential","title":"Deep Learning with Gaussian Differential Privacy","date":"2019-11-26","arxiv_id":"1911.11607","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"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) · 1 unverified","official":{"repos":["woodyx218/Deep-Learning-with-GDP"],"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/efficient-attention-mechanism-for-handling","slug":"efficient-attention-mechanism-for-handling","title":"Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs","date":"2019-11-26","arxiv_id":"1911.11390","n_code_links":1,"syntology":null},{"paper":"/paper/low-rank-factorization-for-compact-multi-head","slug":"low-rank-factorization-for-compact-multi-head","title":"Low Rank Factorization for Compact Multi-Head Self-Attention","date":"2019-11-26","arxiv_id":"1912.00835","n_code_links":1,"syntology":null},{"paper":"/paper/password-conditioned-anonymization-and","slug":"password-conditioned-anonymization-and","title":"Password-conditioned Anonymization and Deanonymization with Face Identity Transformers","date":"2019-11-26","arxiv_id":"1911.11759","n_code_links":1,"syntology":null},{"paper":null,"slug":"relevance-promoting-language-model-for-short","title":"Relevance-Promoting Language Model for Short-Text Conversation","date":"2019-11-26","arxiv_id":"1911.11489","n_code_links":0,"syntology":null},{"paper":"/paper/single-headed-attention-rnn-stop-thinking","slug":"single-headed-attention-rnn-stop-thinking","title":"Single Headed Attention RNN: Stop Thinking With Your Head","date":"2019-11-26","arxiv_id":"1911.11423","n_code_links":5,"syntology":null},{"paper":"/paper/191111236","slug":"191111236","title":"RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds","date":"2019-11-25","arxiv_id":"1911.11236","n_code_links":9,"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":{"repos":["QingyongHu/RandLA-Net"],"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":"learning-to-reuse-translations-guiding-neural","title":"Learning to Reuse Translations: Guiding Neural Machine Translation with Examples","date":"2019-11-25","arxiv_id":"1911.10732","n_code_links":0,"syntology":null},{"paper":"/paper/who-did-they-respond-to-conversation","slug":"who-did-they-respond-to-conversation","title":"Who did They Respond to? Conversation Structure Modeling using Masked Hierarchical Transformer","date":"2019-11-25","arxiv_id":"1911.10666","n_code_links":1,"syntology":null},{"paper":"/paper/a-fully-natural-gradient-scheme-for-improving","slug":"a-fully-natural-gradient-scheme-for-improving","title":"A Fully Natural Gradient Scheme for Improving Inference of the Heterogeneous Multi-Output Gaussian Process Model","date":"2019-11-22","arxiv_id":"1911.10225","n_code_links":1,"syntology":null},{"paper":null,"slug":"factorized-multimodal-transformer-for","title":"Factorized Multimodal Transformer for Multimodal Sequential Learning","date":"2019-11-22","arxiv_id":"1911.09826","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-n-gram-language-models-with-pre","title":"Improving N-gram Language Models with Pre-trained Deep Transformer","date":"2019-11-22","arxiv_id":"1911.10235","n_code_links":0,"syntology":null},{"paper":null,"slug":"neuron-interaction-based-representation","title":"Neuron Interaction Based Representation Composition for Neural Machine Translation","date":"2019-11-22","arxiv_id":"1911.09877","n_code_links":0,"syntology":null},{"paper":null,"slug":"spectral-graph-transformer-networks-for-brain","title":"Spectral Graph Transformer Networks for Brain Surface Parcellation","date":"2019-11-22","arxiv_id":"1911.10118","n_code_links":0,"syntology":null},{"paper":"/paper/automatically-neutralizing-subjective-bias-in","slug":"automatically-neutralizing-subjective-bias-in","title":"Automatically Neutralizing Subjective Bias in Text","date":"2019-11-21","arxiv_id":"1911.09709","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":12,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rpryzant/neutralizing-bias"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/chemical-protein-interaction-extraction-via","slug":"chemical-protein-interaction-extraction-via","title":"Chemical-protein Interaction Extraction via Gaussian Probability Distribution and External Biomedical Knowledge","date":"2019-11-21","arxiv_id":"1911.09487","n_code_links":1,"syntology":null},{"paper":null,"slug":"paraphrasing-with-large-language-models-1","title":"Paraphrasing with Large Language Models","date":"2019-11-21","arxiv_id":"1911.09661","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-hierarchy-emerges-in-deep-generative","slug":"semantic-hierarchy-emerges-in-deep-generative","title":"Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis","date":"2019-11-21","arxiv_id":"1911.09267","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"wildmix-dataset-and-spectro-temporal","title":"WildMix Dataset and Spectro-Temporal Transformer Model for Monoaural Audio Source Separation","date":"2019-11-21","arxiv_id":"1911.09783","n_code_links":0,"syntology":null},{"paper":null,"slug":"joint-emotion-label-space-modelling-for","title":"Joint Emotion Label Space Modelling for Affect Lexica","date":"2019-11-20","arxiv_id":"1911.08782","n_code_links":0,"syntology":null},{"paper":null,"slug":"marionette-few-shot-face-reenactment","title":"MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets","date":"2019-11-19","arxiv_id":"1911.08139","n_code_links":0,"syntology":null},{"paper":"/paper/towards-lingua-franca-named-entity","slug":"towards-lingua-franca-named-entity","title":"Towards Lingua Franca Named Entity Recognition with BERT","date":"2019-11-19","arxiv_id":"1912.01389","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-non-toxic-landscapes-automatic-toxic","title":"Towards non-toxic landscapes: Automatic toxic comment detection using DNN","date":"2019-11-19","arxiv_id":"1911.08395","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-natural-question-answering-with-1","title":"Unsupervised Natural Question Answering with a Small Model","date":"2019-11-19","arxiv_id":"1911.08340","n_code_links":0,"syntology":null},{"paper":null,"slug":"convergence-analysis-of-a-momentum-algorithm-1","title":"Convergence Analysis of a Momentum Algorithm with Adaptive Step Size for Non Convex Optimization","date":"2019-11-18","arxiv_id":"1911.07596","n_code_links":0,"syntology":null},{"paper":"/paper/graph-transformer-for-graph-to-sequence","slug":"graph-transformer-for-graph-to-sequence","title":"Graph Transformer for Graph-to-Sequence Learning","date":"2019-11-18","arxiv_id":"1911.07470","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":7,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"7 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["jcyk/gtos"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/improving-relation-classification-by-entity","slug":"improving-relation-classification-by-entity","title":"Improving Relation Classification by Entity Pair Graph","date":"2019-11-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/muse-parallel-multi-scale-attention-for","slug":"muse-parallel-multi-scale-attention-for","title":"MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning","date":"2019-11-17","arxiv_id":"1911.09483","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["lancopku/MUSE"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"unsupervised-visual-representation-learning-2","title":"Unsupervised Visual Representation Learning with Increasing Object Shape Bias","date":"2019-11-17","arxiv_id":"1911.07272","n_code_links":0,"syntology":null},{"paper":null,"slug":"music-theme-recognition-using-cnn-and-self","title":"Music theme recognition using CNN and self-attention","date":"2019-11-16","arxiv_id":"1911.07041","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-reading-comprehension-with-linguistic","title":"Robust Reading Comprehension with Linguistic Constraints via Posterior Regularization","date":"2019-11-16","arxiv_id":"1911.06948","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-efficient-co-adaptation-of-morphology","title":"Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning","date":"2019-11-15","arxiv_id":"1911.06832","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-robustness-of-language-models-for","title":"Evaluating robustness of language models for chief complaint extraction from patient-generated text","date":"2019-11-15","arxiv_id":"1911.06915","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-exploration-through-latent","title":"Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient","date":"2019-11-15","arxiv_id":"1911.06833","n_code_links":0,"syntology":null}],"record_sha256":"3cf7c836df57971fc0a39e8d13238142ce2ddfa42cdd34a9c350115b633c830a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}