{"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/position-wise-feed-forward-layer/papers/138","list_of":"/method/position-wise-feed-forward-layer","method":"Position-Wise Feed-Forward Layer","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":138,"pages_in_order":139,"rows_per_page":100,"rows":[13701,13800],"of":13895,"counts":{"archive_papers_tagged":13895,"with_a_code_link":6514,"where_syntology_ran_a_sample":2229,"not_listed_spam_title":0,"listed":13895,"listed_where_code_ran":2229,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1902,"every_run_a_failure_of_syntologys_instrument":327,"listed_with_a_run_with_no_instrument_failure":1902,"listed_every_run_a_failure_of_syntologys_instrument":327,"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/position-wise-feed-forward-layer","prev":"/method/position-wise-feed-forward-layer/papers/137","next":"/method/position-wise-feed-forward-layer/papers/139","papers":[{"paper":null,"slug":"towards-a-better-understanding-of-vector","title":"Towards a better understanding of Vector Quantized Autoencoders","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-xl-language-modeling-with-longer","title":"Transformer-XL: Language Modeling with Longer-Term Dependency","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"very-deep-self-attention-networks-for-end-to","title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","date":"2019-04-30","arxiv_id":"1904.13377","n_code_links":0,"syntology":null},{"paper":null,"slug":"softmax-optimizations-for-intel-xeon","title":"Softmax Optimizations for Intel Xeon Processor-based Platforms","date":"2019-04-28","arxiv_id":"1904.12380","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-with-convolutional-context-for","slug":"transformers-with-convolutional-context-for","title":"Transformers with convolutional context for ASR","date":"2019-04-26","arxiv_id":"1904.11660","n_code_links":4,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":null}},{"paper":null,"slug":"low-memory-neural-network-training-a","title":"Low-Memory Neural Network Training: A Technical Report","date":"2019-04-24","arxiv_id":"1904.10631","n_code_links":0,"syntology":null},{"paper":"/paper/190501969","slug":"190501969","title":"Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring","date":"2019-04-22","arxiv_id":"1905.01969","n_code_links":7,"syntology":null},{"paper":"/paper/dynamic-past-and-future-for-neural-machine","slug":"dynamic-past-and-future-for-neural-machine","title":"Dynamic Past and Future for Neural Machine Translation","date":"2019-04-21","arxiv_id":"1904.09646","n_code_links":1,"syntology":null},{"paper":"/paper/190409380","slug":"190409380","title":"Repurposing Entailment for Multi-Hop Question Answering Tasks","date":"2019-04-20","arxiv_id":"1904.09380","n_code_links":4,"syntology":null},{"paper":"/paper/190409408","slug":"190409408","title":"Language Models with Transformers","date":"2019-04-20","arxiv_id":"1904.09408","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cgraywang/gluon-nlp-1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/190409324","slug":"190409324","title":"Mask-Predict: Parallel Decoding of Conditional Masked Language Models","date":"2019-04-19","arxiv_id":"1904.09324","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"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":["facebookresearch/Mask-Predict"],"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/real-time-style-transfer-with-strength","slug":"real-time-style-transfer-with-strength","title":"Real-Time Style Transfer With Strength Control","date":"2019-04-18","arxiv_id":"1904.08643","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-the-behaviors-of-bert-in","title":"Understanding the Behaviors of BERT in Ranking","date":"2019-04-16","arxiv_id":"1904.07531","n_code_links":0,"syntology":null},{"paper":"/paper/personalized-context-aware-re-ranking-for-e","slug":"personalized-context-aware-re-ranking-for-e","title":"Personalized Re-ranking for Recommendation","date":"2019-04-15","arxiv_id":"1904.06813","n_code_links":1,"syntology":null},{"paper":"/paper/an-empirical-study-of-spatial-attention","slug":"an-empirical-study-of-spatial-attention","title":"An Empirical Study of Spatial Attention Mechanisms in Deep Networks","date":"2019-04-11","arxiv_id":"1904.05873","n_code_links":1,"syntology":null},{"paper":null,"slug":"identity-preserving-face-recovery-from-1","title":"Identity-preserving Face Recovery from Stylized Portraits","date":"2019-04-07","arxiv_id":"1904.04241","n_code_links":0,"syntology":null},{"paper":null,"slug":"thisiscompetition-at-semeval-2019-task-9-bert","title":"ThisIsCompetition at SemEval-2019 Task 9: BERT is unstable for out-of-domain samples","date":"2019-04-06","arxiv_id":"1904.03339","n_code_links":0,"syntology":null},{"paper":"/paper/token-level-ensemble-distillation-for","slug":"token-level-ensemble-distillation-for","title":"Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversion","date":"2019-04-06","arxiv_id":"1904.03446","n_code_links":0,"syntology":null},{"paper":null,"slug":"modeling-recurrence-for-transformer","title":"Modeling Recurrence for Transformer","date":"2019-04-05","arxiv_id":"1904.03092","n_code_links":0,"syntology":null},{"paper":"/paper/regional-homogeneity-towards-learning","slug":"regional-homogeneity-towards-learning","title":"Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses","date":"2019-04-01","arxiv_id":"1904.00979","n_code_links":1,"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":["LiYingwei/Regional-Homogeneity"],"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/towards-knowledge-based-personalized-product","slug":"towards-knowledge-based-personalized-product","title":"Towards Knowledge-Based Personalized Product Description Generation in E-commerce","date":"2019-03-29","arxiv_id":"1903.12457","n_code_links":4,"syntology":null},{"paper":"/paper/train-sort-explain-learning-to-diagnose","slug":"train-sort-explain-learning-to-diagnose","title":"Train, Sort, Explain: Learning to Diagnose Translation Models","date":"2019-03-28","arxiv_id":"1903.12017","n_code_links":1,"syntology":null},{"paper":null,"slug":"190410045","title":"Automatic Spelling Correction with Transformer for CTC-based End-to-End Speech Recognition","date":"2019-03-27","arxiv_id":"1904.10045","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tune-bert-for-extractive-summarization","slug":"fine-tune-bert-for-extractive-summarization","title":"Fine-tune BERT for Extractive Summarization","date":"2019-03-25","arxiv_id":"1903.10318","n_code_links":12,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["nlpyang/BertSum"],"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":"knowledge-driven-encode-retrieve-paraphrase","title":"Knowledge-driven Encode, Retrieve, Paraphrase for Medical Image Report Generation","date":"2019-03-25","arxiv_id":"1903.10122","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-multi-level-information-for-dialogue","title":"Learning Multi-Level Information for Dialogue Response Selection by Highway Recurrent Transformer","date":"2019-03-21","arxiv_id":"1903.08953","n_code_links":0,"syntology":null},{"paper":null,"slug":"linguistic-knowledge-and-transferability-of","title":"Linguistic Knowledge and Transferability of Contextual Representations","date":"2019-03-21","arxiv_id":"1903.08855","n_code_links":0,"syntology":null},{"paper":"/paper/selective-attention-for-context-aware-neural","slug":"selective-attention-for-context-aware-neural","title":"Selective Attention for Context-aware Neural Machine Translation","date":"2019-03-21","arxiv_id":"1903.08788","n_code_links":1,"syntology":null},{"paper":"/paper/cloze-driven-pretraining-of-self-attention","slug":"cloze-driven-pretraining-of-self-attention","title":"Cloze-driven Pretraining of Self-attention Networks","date":"2019-03-19","arxiv_id":"1903.07785","n_code_links":0,"syntology":null},{"paper":"/paper/neutron-an-implementation-of-the-transformer","slug":"neutron-an-implementation-of-the-transformer","title":"Neutron: An Implementation of the Transformer Translation Model and its Variants","date":"2019-03-18","arxiv_id":"1903.07402","n_code_links":2,"syntology":null},{"paper":null,"slug":"stnreid-deep-convolutional-networks-with","title":"STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification","date":"2019-03-17","arxiv_id":"1903.07072","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-deep-patent-landscaping-model-using","title":"Deep Patent Landscaping Model Using Transformer and Graph Embedding","date":"2019-03-14","arxiv_id":"1903.05823","n_code_links":0,"syntology":null},{"paper":"/paper/episodic-memory-reader-learning-what-to","slug":"episodic-memory-reader-learning-what-to","title":"Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data","date":"2019-03-14","arxiv_id":"1903.06164","n_code_links":1,"syntology":null},{"paper":"/paper/communication-efficient-distributed-sgd-with","slug":"communication-efficient-distributed-sgd-with","title":"Communication-efficient distributed SGD with Sketching","date":"2019-03-12","arxiv_id":"1903.04488","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":["dhroth/sketchedsgd"],"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":null,"slug":"scene-memory-transformer-for-embodied-agents","title":"Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks","date":"2019-03-09","arxiv_id":"1903.03878","n_code_links":0,"syntology":null},{"paper":null,"slug":"dixit-interactive-visual-storytelling-via","title":"Dixit: Interactive Visual Storytelling via Term Manipulation","date":"2019-03-06","arxiv_id":"1903.02230","n_code_links":0,"syntology":null},{"paper":null,"slug":"gq-stn-optimizing-one-shot-grasp-detection","title":"GQ-STN: Optimizing One-Shot Grasp Detection based on Robustness Classifier","date":"2019-03-06","arxiv_id":"1903.02489","n_code_links":0,"syntology":null},{"paper":"/paper/self-adversarial-variational-autoencoder-with","slug":"self-adversarial-variational-autoencoder-with","title":"adVAE: A self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detection","date":"2019-03-03","arxiv_id":"1903.00904","n_code_links":2,"syntology":null},{"paper":"/paper/frequency-domain-transformer-networks-for","slug":"frequency-domain-transformer-networks-for","title":"Frequency Domain Transformer Networks for Video Prediction","date":"2019-03-01","arxiv_id":"1903.00271","n_code_links":1,"syntology":null},{"paper":"/paper/star-transformer","slug":"star-transformer","title":"Star-Transformer","date":"2019-02-25","arxiv_id":"1902.09113","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["dmlc/dgl"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"dynamic-layer-aggregation-for-neural-machine","title":"Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement","date":"2019-02-15","arxiv_id":"1902.05770","n_code_links":0,"syntology":null},{"paper":null,"slug":"machine-reading-comprehension-for-answer-re","title":"Machine Reading Comprehension for Answer Re-Ranking in Customer Support Chatbots","date":"2019-02-12","arxiv_id":"1902.04574","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-deep-image-clustering-with-spatial","title":"Improving Deep Image Clustering With Spatial Transformer Layers","date":"2019-02-09","arxiv_id":"1902.05401","n_code_links":0,"syntology":null},{"paper":null,"slug":"insertion-transformer-flexible-sequence","title":"Insertion Transformer: Flexible Sequence Generation via Insertion Operations","date":"2019-02-08","arxiv_id":"1902.03249","n_code_links":0,"syntology":null},{"paper":null,"slug":"alphastar-an-evolutionary-computation","title":"AlphaStar: An Evolutionary Computation Perspective","date":"2019-02-05","arxiv_id":"1902.01724","n_code_links":0,"syntology":null},{"paper":null,"slug":"insertion-based-decoding-with-automatically","title":"Insertion-based Decoding with automatically Inferred Generation Order","date":"2019-02-04","arxiv_id":"1902.01370","n_code_links":0,"syntology":null},{"paper":"/paper/parameter-efficient-transfer-learning-for-nlp","slug":"parameter-efficient-transfer-learning-for-nlp","title":"Parameter-Efficient Transfer Learning for NLP","date":"2019-02-02","arxiv_id":"1902.00751","n_code_links":17,"syntology":{"ran":14,"of":22,"n_ran_checked":14,"n_instrument":0,"unverified":8,"pointer_only":3,"phrase":"14 ran (of which 3 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["google-research/adapter-bert"],"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":"/paper/adding-interpretable-attention-to-neural","slug":"adding-interpretable-attention-to-neural","title":"Adding Interpretable Attention to Neural Translation Models Improves Word Alignment","date":"2019-01-31","arxiv_id":"1901.11359","n_code_links":1,"syntology":null},{"paper":"/paper/multi-task-deep-neural-networks-for-natural","slug":"multi-task-deep-neural-networks-for-natural","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2019-01-31","arxiv_id":"1901.11504","n_code_links":7,"syntology":{"ran":9,"of":13,"n_ran_checked":6,"n_instrument":3,"unverified":4,"pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["namisan/mt-dnn"],"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/the-second-conversational-intelligence","slug":"the-second-conversational-intelligence","title":"The Second Conversational Intelligence Challenge (ConvAI2)","date":"2019-01-31","arxiv_id":"1902.00098","n_code_links":2,"syntology":null},{"paper":"/paper/the-evolved-transformer","slug":"the-evolved-transformer","title":"The Evolved Transformer","date":"2019-01-30","arxiv_id":"1901.11117","n_code_links":3,"syntology":null},{"paper":null,"slug":"self-attentive-model-for-headline-generation","title":"Self-Attentive Model for Headline Generation","date":"2019-01-23","arxiv_id":"1901.07786","n_code_links":0,"syntology":null},{"paper":"/paper/transfertransfo-a-transfer-learning-approach","slug":"transfertransfo-a-transfer-learning-approach","title":"TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents","date":"2019-01-23","arxiv_id":"1901.08149","n_code_links":23,"syntology":{"ran":18,"of":26,"n_ran_checked":11,"n_instrument":7,"unverified":8,"pointer_only":7,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified","official":null}},{"paper":"/paper/linearized-multi-sampling-for-differentiable","slug":"linearized-multi-sampling-for-differentiable","title":"Linearized Multi-Sampling for Differentiable Image Transformation","date":"2019-01-22","arxiv_id":"1901.07124","n_code_links":1,"syntology":null},{"paper":"/paper/equalizing-gender-biases-in-neural-machine","slug":"equalizing-gender-biases-in-neural-machine","title":"Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniques","date":"2019-01-10","arxiv_id":"1901.03116","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-turing-completeness-of-modern-neural","title":"On the Turing Completeness of Modern Neural Network Architectures","date":"2019-01-10","arxiv_id":"1901.03429","n_code_links":0,"syntology":null},{"paper":null,"slug":"composite-shape-modeling-via-latent-space","title":"Composite Shape Modeling via Latent Space Factorization","date":"2019-01-09","arxiv_id":"1901.02968","n_code_links":0,"syntology":null},{"paper":"/paper/team-papelo-transformer-networks-at-fever","slug":"team-papelo-transformer-networks-at-fever","title":"Team Papelo: Transformer Networks at FEVER","date":"2019-01-08","arxiv_id":"1901.02534","n_code_links":1,"syntology":null},{"paper":null,"slug":"dppnet-approximating-determinantal-point","title":"DPPNet: Approximating Determinantal Point Processes with Deep Networks","date":"2019-01-07","arxiv_id":"1901.02051","n_code_links":0,"syntology":null},{"paper":null,"slug":"skeleton-transformer-networks-3d-human-pose","title":"Skeleton Transformer Networks: 3D Human Pose and Skinned Mesh from Single RGB Image","date":"2018-12-29","arxiv_id":"1812.11328","n_code_links":0,"syntology":null},{"paper":"/paper/dtmt-a-novel-deep-transition-architecture-for","slug":"dtmt-a-novel-deep-transition-architecture-for","title":"DTMT: A Novel Deep Transition Architecture for Neural Machine Translation","date":"2018-12-19","arxiv_id":"1812.07807","n_code_links":1,"syntology":null},{"paper":null,"slug":"multitask-painting-categorization-by-deep","title":"Multitask Painting Categorization by Deep Multibranch Neural Network","date":"2018-12-19","arxiv_id":"1812.08052","n_code_links":0,"syntology":null},{"paper":null,"slug":"nrityantar-pose-oblivious-indian-classical","title":"Nrityantar: Pose oblivious Indian classical dance sequence classification system","date":"2018-12-13","arxiv_id":"1812.05231","n_code_links":0,"syntology":null},{"paper":null,"slug":"hyperbolic-deep-learning-for-chinese-natural","title":"Hyperbolic Deep Learning for Chinese Natural Language Understanding","date":"2018-12-11","arxiv_id":"1812.10408","n_code_links":0,"syntology":null},{"paper":"/paper/learning-embedding-adaptation-for-few-shot","slug":"learning-embedding-adaptation-for-few-shot","title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","date":"2018-12-10","arxiv_id":"1812.03664","n_code_links":6,"syntology":null},{"paper":null,"slug":"kernel-transformer-networks-for-compact","title":"Kernel Transformer Networks for Compact Spherical Convolution","date":"2018-12-07","arxiv_id":"1812.03115","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-ustc-nel-speech-translation-system-at","title":"The USTC-NEL Speech Translation system at IWSLT 2018","date":"2018-12-06","arxiv_id":"1812.02455","n_code_links":0,"syntology":null},{"paper":"/paper/video-action-transformer-network","slug":"video-action-transformer-network","title":"Video Action Transformer Network","date":"2018-12-06","arxiv_id":"1812.02707","n_code_links":0,"syntology":null},{"paper":"/paper/attending-to-mathematical-language-with","slug":"attending-to-mathematical-language-with","title":"Attending to Mathematical Language with Transformers","date":"2018-12-05","arxiv_id":"1812.02825","n_code_links":3,"syntology":null},{"paper":"/paper/practical-text-classification-with-large-pre","slug":"practical-text-classification-with-large-pre","title":"Practical Text Classification With Large Pre-Trained Language Models","date":"2018-12-04","arxiv_id":"1812.01207","n_code_links":1,"syntology":null},{"paper":null,"slug":"layer-wise-coordination-between-encoder-and","title":"Layer-Wise Coordination between Encoder and Decoder for Neural Machine Translation","date":"2018-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learning-roi-transformer-for-detecting","slug":"learning-roi-transformer-for-detecting","title":"Learning RoI Transformer for Detecting Oriented Objects in Aerial Images","date":"2018-12-01","arxiv_id":"1812.00155","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":5,"n_instrument":5,"unverified":1,"pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/grammars-and-reinforcement-learning-for","slug":"grammars-and-reinforcement-learning-for","title":"Grammars and reinforcement learning for molecule optimization","date":"2018-11-27","arxiv_id":"1811.11222","n_code_links":1,"syntology":null},{"paper":"/paper/iterative-transformer-network-for-3d-point","slug":"iterative-transformer-network-for-3d-point","title":"Iterative Transformer Network for 3D Point Cloud","date":"2018-11-27","arxiv_id":"1811.11209","n_code_links":1,"syntology":null},{"paper":"/paper/gpipe-efficient-training-of-giant-neural","slug":"gpipe-efficient-training-of-giant-neural","title":"GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism","date":"2018-11-16","arxiv_id":"1811.06965","n_code_links":13,"syntology":{"ran":20,"of":25,"n_ran_checked":19,"n_instrument":1,"unverified":5,"pointer_only":16,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":null}},{"paper":null,"slug":"identification-of-internal-faults-in-indirect","title":"Identification of Internal Faults in Indirect Symmetrical Phase Shift Transformers Using Ensemble Learning","date":"2018-11-12","arxiv_id":"1811.04537","n_code_links":0,"syntology":null},{"paper":null,"slug":"input-combination-strategies-for-multi-source-1","title":"Input Combination Strategies for Multi-Source Transformer Decoder","date":"2018-11-12","arxiv_id":"1811.04716","n_code_links":0,"syntology":null},{"paper":"/paper/molecular-transformer-for-chemical-reaction","slug":"molecular-transformer-for-chemical-reaction","title":"Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction","date":"2018-11-06","arxiv_id":"1811.02633","n_code_links":1,"syntology":null},{"paper":"/paper/mesh-tensorflow-deep-learning-for","slug":"mesh-tensorflow-deep-learning-for","title":"Mesh-TensorFlow: Deep Learning for Supercomputers","date":"2018-11-05","arxiv_id":"1811.02084","n_code_links":1,"syntology":null},{"paper":"/paper/simple-distributed-and-accelerated","slug":"simple-distributed-and-accelerated","title":"Simple, Distributed, and Accelerated Probabilistic Programming","date":"2018-11-05","arxiv_id":"1811.02091","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-analysis-of-encoder-representations-in","title":"An Analysis of Encoder Representations in Transformer-Based Machine Translation","date":"2018-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-syntactic-trees-from-transformer","title":"Extracting Syntactic Trees from Transformer Encoder Self-Attentions","date":"2018-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-self-attention-network-for-machine","title":"Hybrid Self-Attention Network for Machine Translation","date":"2018-11-01","arxiv_id":"1811.00253","n_code_links":0,"syntology":null},{"paper":null,"slug":"convolutional-self-attention-network","title":"Convolutional Self-Attention Network","date":"2018-10-31","arxiv_id":"1810.13320","n_code_links":0,"syntology":null},{"paper":null,"slug":"weakly-supervised-grammatical-error","title":"Weakly Supervised Grammatical Error Correction using Iterative Decoding","date":"2018-10-31","arxiv_id":"1811.01710","n_code_links":0,"syntology":null},{"paper":null,"slug":"parallel-attention-mechanisms-in-neural","title":"Parallel Attention Mechanisms in Neural Machine Translation","date":"2018-10-29","arxiv_id":"1810.12427","n_code_links":0,"syntology":null},{"paper":"/paper/recurrent-transformer-networks-for-semantic","slug":"recurrent-transformer-networks-for-semantic","title":"Recurrent Transformer Networks for Semantic Correspondence","date":"2018-10-29","arxiv_id":"1810.12155","n_code_links":1,"syntology":null},{"paper":"/paper/semi-supervised-target-level-sentiment","slug":"semi-supervised-target-level-sentiment","title":"Variational Semi-supervised Aspect-term Sentiment Analysis via Transformer","date":"2018-10-24","arxiv_id":"1810.10437","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-analysis-of-attention-mechanisms-the-case","title":"An Analysis of Attention Mechanisms: The Case of Word Sense Disambiguation in Neural Machine Translation","date":"2018-10-17","arxiv_id":"1810.07595","n_code_links":0,"syntology":null},{"paper":"/paper/improving-the-transformer-translation-model","slug":"improving-the-transformer-translation-model","title":"Improving the Transformer Translation Model with Document-Level Context","date":"2018-10-08","arxiv_id":"1810.03581","n_code_links":3,"syntology":{"ran":1,"of":12,"n_ran_checked":1,"n_instrument":0,"unverified":11,"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) · 11 unverified","official":{"repos":["Glaceon31/Document-Transformer","thumt/THUMT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":10,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-transformer-based-multi-source-automatic","title":"A Transformer-Based Multi-Source Automatic Post-Editing System","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"alibaba-submission-for-wmt18-quality","title":"Alibaba Submission for WMT18 Quality Estimation Task","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"alibabas-neural-machine-translation-systems","title":"Alibaba's Neural Machine Translation Systems for WMT18","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cuni-submissions-in-wmt18","title":"CUNI Submissions in WMT18","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cuni-transformer-neural-mt-system-for-wmt18","title":"CUNI Transformer Neural MT System for WMT18","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"input-combination-strategies-for-multi-source","title":"Input Combination Strategies for Multi-Source Transformer Decoder","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-encoder-transformer-network-for","title":"Multi-encoder Transformer Network for Automatic Post-Editing","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-source-transformer-with-combined-losses","title":"Multi-source transformer with combined losses for automatic post editing","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-machine-translation-with-the","title":"Neural Machine Translation with the Transformer and Multi-Source Romance Languages for the Biomedical WMT 2018 task","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ntts-neural-machine-translation-systems-for","title":"NTT's Neural Machine Translation Systems for WMT 2018","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"a735bed8c95d32baf160cf19dec538fb374cbcec49c9b1f2e278b261eb2929f8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}