{"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/sigmoid-activation/papers/67","list_of":"/method/sigmoid-activation","method":"Sigmoid Activation","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":67,"pages_in_order":72,"rows_per_page":100,"rows":[6601,6700],"of":7112,"counts":{"archive_papers_tagged":7112,"with_a_code_link":2470,"where_syntology_ran_a_sample":461,"not_listed_spam_title":0,"listed":7112,"listed_where_code_ran":461,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":386,"every_run_a_failure_of_syntologys_instrument":75,"listed_with_a_run_with_no_instrument_failure":386,"listed_every_run_a_failure_of_syntologys_instrument":75,"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/sigmoid-activation","prev":"/method/sigmoid-activation/papers/66","next":"/method/sigmoid-activation/papers/68","papers":[{"paper":null,"slug":"meta-learning-via-feature-label-memory","title":"Meta-Learning via Feature-Label Memory Network","date":"2017-10-19","arxiv_id":"1710.07110","n_code_links":0,"syntology":null},{"paper":"/paper/sling-a-framework-for-frame-semantic-parsing","slug":"sling-a-framework-for-frame-semantic-parsing","title":"SLING: A framework for frame semantic parsing","date":"2017-10-19","arxiv_id":"1710.07032","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google/sling"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/learning-differentially-private-recurrent","slug":"learning-differentially-private-recurrent","title":"Learning Differentially Private Recurrent Language Models","date":"2017-10-18","arxiv_id":"1710.06963","n_code_links":1,"syntology":null},{"paper":null,"slug":"ohiostate-at-ijcnlp-2017-task-4-exploring","title":"OhioState at IJCNLP-2017 Task 4: Exploring Neural Architectures for Multilingual Customer Feedback Analysis","date":"2017-10-18","arxiv_id":"1710.06931","n_code_links":0,"syntology":null},{"paper":null,"slug":"face-transfer-with-generative-adversarial","title":"Face Transfer with Generative Adversarial Network","date":"2017-10-17","arxiv_id":"1710.06090","n_code_links":0,"syntology":null},{"paper":"/paper/searching-for-activation-functions","slug":"searching-for-activation-functions","title":"Searching for Activation Functions","date":"2017-10-16","arxiv_id":"1710.05941","n_code_links":22,"syntology":{"ran":13,"of":20,"n_ran_checked":8,"n_instrument":5,"unverified":7,"pointer_only":4,"phrase":"13 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified","official":null}},{"paper":null,"slug":"convolutional-attention-based-seq2seq-neural","title":"Convolutional Attention-based Seq2Seq Neural Network for End-to-End ASR","date":"2017-10-12","arxiv_id":"1710.04515","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-in-multiple-multistep-time","title":"Deep Learning in Multiple Multistep Time Series Prediction","date":"2017-10-12","arxiv_id":"1710.04373","n_code_links":0,"syntology":null},{"paper":"/paper/dissent-sentence-representation-learning-from","slug":"dissent-sentence-representation-learning-from","title":"DisSent: Sentence Representation Learning from Explicit Discourse Relations","date":"2017-10-12","arxiv_id":"1710.04334","n_code_links":3,"syntology":null},{"paper":"/paper/discrete-event-continuous-time-rnns","slug":"discrete-event-continuous-time-rnns","title":"Discrete Event, Continuous Time RNNs","date":"2017-10-11","arxiv_id":"1710.04110","n_code_links":1,"syntology":null},{"paper":null,"slug":"stackseq2seq-dual-encoder-seq2seq-recurrent","title":"StackSeq2Seq: Dual Encoder Seq2Seq Recurrent Networks","date":"2017-10-11","arxiv_id":"1710.04211","n_code_links":0,"syntology":null},{"paper":null,"slug":"network-of-recurrent-neural-networks","title":"Network of Recurrent Neural Networks","date":"2017-10-10","arxiv_id":"1710.03414","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-long-short-term-memory-recurrent","title":"Optimizing Long Short-Term Memory Recurrent Neural Networks Using Ant Colony Optimization to Predict Turbine Engine Vibration","date":"2017-10-10","arxiv_id":"1710.03753","n_code_links":0,"syntology":null},{"paper":"/paper/forecasting-across-time-series-databases","slug":"forecasting-across-time-series-databases","title":"Forecasting Across Time Series Databases using Recurrent Neural Networks on Groups of Similar Series: A Clustering Approach","date":"2017-10-09","arxiv_id":"1710.03222","n_code_links":3,"syntology":null},{"paper":"/paper/to-prune-or-not-to-prune-exploring-the","slug":"to-prune-or-not-to-prune-exploring-the","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","date":"2017-10-05","arxiv_id":"1710.01878","n_code_links":4,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"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":null}},{"paper":null,"slug":"identifying-clickbait-a-multi-strategy","title":"Identifying Clickbait: A Multi-Strategy Approach Using Neural Networks","date":"2017-10-04","arxiv_id":"1710.01507","n_code_links":0,"syntology":null},{"paper":null,"slug":"person-re-identification-with-vision-and","title":"Person Re-Identification with Vision and Language","date":"2017-10-03","arxiv_id":"1710.01202","n_code_links":0,"syntology":null},{"paper":null,"slug":"3dof-pedestrian-trajectory-prediction-learned","title":"3DOF Pedestrian Trajectory Prediction Learned from Long-Term Autonomous Mobile Robot Deployment Data","date":"2017-09-30","arxiv_id":"1710.00126","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-free-prediction-of-noisy-chaotic-time","title":"Model-free prediction of noisy chaotic time series by deep learning","date":"2017-09-29","arxiv_id":"1710.01693","n_code_links":0,"syntology":null},{"paper":null,"slug":"jointly-trained-sequential-labeling-and","title":"Jointly Trained Sequential Labeling and Classification by Sparse Attention Neural Networks","date":"2017-09-28","arxiv_id":"1709.10191","n_code_links":0,"syntology":null},{"paper":"/paper/tensor-product-generation-networks-for-deep","slug":"tensor-product-generation-networks-for-deep","title":"Tensor Product Generation Networks for Deep NLP Modeling","date":"2017-09-26","arxiv_id":"1709.09118","n_code_links":2,"syntology":null},{"paper":null,"slug":"house-price-prediction-using-lstm","title":"House Price Prediction Using LSTM","date":"2017-09-25","arxiv_id":"1709.08432","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-modal-recurrent-models-for-weight","title":"Cross-modal Recurrent Models for Weight Objective Prediction from Multimodal Time-series Data","date":"2017-09-23","arxiv_id":"1709.08073","n_code_links":0,"syntology":null},{"paper":"/paper/deep-recurrent-nmf-for-speech-separation-by","slug":"deep-recurrent-nmf-for-speech-separation-by","title":"Deep Recurrent NMF for Speech Separation by Unfolding Iterative Thresholding","date":"2017-09-21","arxiv_id":"1709.07124","n_code_links":1,"syntology":null},{"paper":null,"slug":"inducing-distant-supervision-in-suggestion","title":"Inducing Distant Supervision in Suggestion Mining through Part-of-Speech Embeddings","date":"2017-09-21","arxiv_id":"1709.07403","n_code_links":0,"syntology":null},{"paper":null,"slug":"de-identification-of-medical-records-using","title":"De-identification of medical records using conditional random fields and long short-term memory networks","date":"2017-09-20","arxiv_id":"1709.06901","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-modeling-with-highway-lstm","title":"Language Modeling with Highway LSTM","date":"2017-09-19","arxiv_id":"1709.06436","n_code_links":0,"syntology":null},{"paper":"/paper/reducing-complexity-of-hevc-a-deep-learning","slug":"reducing-complexity-of-hevc-a-deep-learning","title":"Reducing Complexity of HEVC: A Deep Learning Approach","date":"2017-09-19","arxiv_id":"1710.01218","n_code_links":1,"syntology":null},{"paper":null,"slug":"social-style-characterization-from-egocentric","title":"Social Style Characterization from Egocentric Photo-streams","date":"2017-09-18","arxiv_id":"1709.05775","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-you-serious-rhetorical-questions-and","title":"Are you serious?: Rhetorical Questions and Sarcasm in Social Media Dialog","date":"2017-09-15","arxiv_id":"1709.05305","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-intrinsic-sparse-structures-within","title":"Learning Intrinsic Sparse Structures within Long Short-Term Memory","date":"2017-09-15","arxiv_id":"1709.05027","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-guiding-multimodal-lstm-when-we-do-not","title":"Self-Guiding Multimodal LSTM - when we do not have a perfect training dataset for image captioning","date":"2017-09-15","arxiv_id":"1709.05038","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-for-automatic-stereotypical","title":"Deep Learning for Automatic Stereotypical Motor Movement Detection using Wearable Sensors in Autism Spectrum Disorders","date":"2017-09-14","arxiv_id":"1709.05956","n_code_links":0,"syntology":null},{"paper":"/paper/dialogue-act-sequence-labeling-using","slug":"dialogue-act-sequence-labeling-using","title":"Dialogue Act Sequence Labeling using Hierarchical encoder with CRF","date":"2017-09-13","arxiv_id":"1709.04250","n_code_links":3,"syntology":null},{"paper":"/paper/rra-recurrent-residual-attention-for-sequence","slug":"rra-recurrent-residual-attention-for-sequence","title":"RRA: Recurrent Residual Attention for Sequence Learning","date":"2017-09-12","arxiv_id":"1709.03714","n_code_links":1,"syntology":null},{"paper":null,"slug":"systran-purely-neural-mt-engines-for-wmt2017","title":"SYSTRAN Purely Neural MT Engines for WMT2017","date":"2017-09-12","arxiv_id":"1709.03814","n_code_links":0,"syntology":null},{"paper":"/paper/simple-recurrent-units-for-highly","slug":"simple-recurrent-units-for-highly","title":"Simple Recurrent Units for Highly Parallelizable Recurrence","date":"2017-09-08","arxiv_id":"1709.02755","n_code_links":11,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["asappresearch/sru"],"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":"an-unsupervised-long-short-term-memory-neural","title":"An unsupervised long short-term memory neural network for event detection in cell videos","date":"2017-09-07","arxiv_id":"1709.02081","n_code_links":0,"syntology":null},{"paper":"/paper/squeeze-and-excitation-networks","slug":"squeeze-and-excitation-networks","title":"Squeeze-and-Excitation Networks","date":"2017-09-05","arxiv_id":"1709.01507","n_code_links":85,"syntology":{"ran":2,"of":9,"n_ran_checked":0,"n_instrument":2,"unverified":7,"pointer_only":6,"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) · 7 unverified","official":{"repos":["hujie-frank/SENet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"towards-social-pattern-characterization-in","title":"Towards social pattern characterization in egocentric photo-streams","date":"2017-09-05","arxiv_id":"1709.01424","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-bilstm-based-system-for-cross-lingual","title":"A BiLSTM-based System for Cross-lingual Pronoun Prediction","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-joint-sequential-and-relational-model-for","title":"A Joint Sequential and Relational Model for Frame-Semantic Parsing","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-multi-task-learning-for-aspect-term","title":"Deep Multi-Task Learning for Aspect Term Extraction with Memory Interaction","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"distributed-representation-lda-topic","title":"Distributed Representation, LDA Topic Modelling and Deep Learning for Emerging Named Entity Recognition from Social Media","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/end-to-end-neural-relation-extraction-with","slug":"end-to-end-neural-relation-extraction-with","title":"End-to-End Neural Relation Extraction with Global Optimization","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-lstm-models-for-grammatical","title":"Evaluating LSTM models for grammatical function labelling","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/getting-the-most-out-of-amr-parsing","slug":"getting-the-most-out-of-amr-parsing","title":"Getting the Most out of AMR Parsing","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-order-information-and-event","title":"Integrating Order Information and Event Relation for Script Event Prediction","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"inter-weighted-alignment-network-for-sentence","title":"Inter-Weighted Alignment Network for Sentence Pair Modeling","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lct-maltas-submission-to-repeval-2017-shared","title":"LCT-MALTA's Submission to RepEval 2017 Shared Task","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-whats-easy-fully-differentiable","title":"Learning What's Easy: Fully Differentiable Neural Easy-First Taggers","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-response-generation-via-gan-with-an","title":"Neural Response Generation via GAN with an Approximate Embedding Layer","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/position-aware-attention-and-supervised-data","slug":"position-aware-attention-and-supervised-data","title":"Position-aware Attention and Supervised Data Improve Slot Filling","date":"2017-09-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"recovering-question-answering-errors-via","title":"Recovering Question Answering Errors via Query Revision","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"speech-segmentation-with-a-neural-encoder","title":"Speech segmentation with a neural encoder model of working memory","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"stack-based-multi-layer-attention-for","title":"Stack-based Multi-layer Attention for Transition-based Dependency Parsing","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-labeled-segmentation-of-printed-books","title":"The Labeled Segmentation of Printed Books","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-implicit-content-introducing-for","title":"Towards Implicit Content-Introducing for Generative Short-Text Conversation Systems","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-the-understanding-of-gaming-audiences","title":"Towards the Understanding of Gaming Audiences by Modeling Twitch Emotes","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-pretraining-for-sequence-to-1","title":"Unsupervised Pretraining for Sequence to Sequence Learning","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"word-sense-disambiguation-with-recurrent","title":"Word Sense Disambiguation with Recurrent Neural Networks","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"world-knowledge-for-reading-comprehension","title":"World Knowledge for Reading Comprehension: Rare Entity Prediction with Hierarchical LSTMs Using External Descriptions","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ynu-hpcc-at-emoint-2017-using-a-cnn-lstm","title":"YNU-HPCC at EmoInt-2017: Using a CNN-LSTM Model for Sentiment Intensity Prediction","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"yzu-nlp-at-emoint-2017-determining-emotion","title":"YZU-NLP at EmoInt-2017: Determining Emotion Intensity Using a Bi-directional LSTM-CNN Model","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"action-classification-and-highlighting-in","title":"Action Classification and Highlighting in Videos","date":"2017-08-31","arxiv_id":"1708.09522","n_code_links":0,"syntology":null},{"paper":"/paper/video-summarization-with-attention-based","slug":"video-summarization-with-attention-based","title":"Video Summarization with Attention-Based Encoder-Decoder Networks","date":"2017-08-31","arxiv_id":"1708.09545","n_code_links":0,"syntology":null},{"paper":"/paper/faster-exact-decoding-and-global-training-for","slug":"faster-exact-decoding-and-global-training-for","title":"Fast(er) Exact Decoding and Global Training for Transition-Based Dependency Parsing via a Minimal Feature Set","date":"2017-08-30","arxiv_id":"1708.09403","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-simple-lstm-model-for-transition-based","title":"A Simple LSTM model for Transition-based Dependency Parsing","date":"2017-08-29","arxiv_id":"1708.08959","n_code_links":0,"syntology":null},{"paper":"/paper/modelling-protagonist-goals-and-desires-in","slug":"modelling-protagonist-goals-and-desires-in","title":"Modelling Protagonist Goals and Desires in First-Person Narrative","date":"2017-08-29","arxiv_id":"1708.09040","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-multi-scale-attention-networks","title":"Hierarchical Multi-scale Attention Networks for Action Recognition","date":"2017-08-25","arxiv_id":"1708.07590","n_code_links":0,"syntology":null},{"paper":"/paper/sparql-as-a-foreign-language","slug":"sparql-as-a-foreign-language","title":"SPARQL as a Foreign Language","date":"2017-08-25","arxiv_id":"1708.07624","n_code_links":1,"syntology":null},{"paper":"/paper/relaxed-spatio-temporal-deep-feature","slug":"relaxed-spatio-temporal-deep-feature","title":"Relaxed Spatio-Temporal Deep Feature Aggregation for Real-Fake Expression Prediction","date":"2017-08-24","arxiv_id":"1708.07335","n_code_links":3,"syntology":null},{"paper":null,"slug":"cold-fusion-training-seq2seq-models-together","title":"Cold Fusion: Training Seq2Seq Models Together with Language Models","date":"2017-08-21","arxiv_id":"1708.06426","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-microsoft-2017-conversational-speech","title":"The Microsoft 2017 Conversational Speech Recognition System","date":"2017-08-21","arxiv_id":"1708.06073","n_code_links":0,"syntology":null},{"paper":null,"slug":"expanding-abbreviations-in-a-strongly-1","title":"Expanding Abbreviations in a Strongly Inflected Language: Are Morphosyntactic Tags Sufficient?","date":"2017-08-20","arxiv_id":"1708.05992","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-networks-compression-for-language","title":"Neural Networks Compression for Language Modeling","date":"2017-08-20","arxiv_id":"1708.05963","n_code_links":0,"syntology":null},{"paper":null,"slug":"solving-a-new-3d-bin-packing-problem-with","title":"Solving a New 3D Bin Packing Problem with Deep Reinforcement Learning Method","date":"2017-08-20","arxiv_id":"1708.05930","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-recurrent-neural-network","title":"Accelerating recurrent neural network training using sequence bucketing and multi-GPU data parallelization","date":"2017-08-18","arxiv_id":"1708.05604","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-improved-residual-lstm-architecture-for","title":"An Improved Residual LSTM Architecture for Acoustic Modeling","date":"2017-08-17","arxiv_id":"1708.05682","n_code_links":0,"syntology":null},{"paper":null,"slug":"belief-tree-search-for-active-object","title":"Belief Tree Search for Active Object Recognition","date":"2017-08-13","arxiv_id":"1708.03901","n_code_links":0,"syntology":null},{"paper":null,"slug":"lattice-long-short-term-memory-for-human","title":"Lattice Long Short-Term Memory for Human Action Recognition","date":"2017-08-13","arxiv_id":"1708.03958","n_code_links":0,"syntology":null},{"paper":"/paper/patient-subtyping-via-time-aware-lstm","slug":"patient-subtyping-via-time-aware-lstm","title":"Patient Subtyping via Time-Aware LSTM Networks","date":"2017-08-13","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-sentence-n-ary-relation-extraction-with","title":"Cross-Sentence N-ary Relation Extraction with Graph LSTMs","date":"2017-08-12","arxiv_id":"1708.03743","n_code_links":0,"syntology":null},{"paper":"/paper/deep-steering-learning-end-to-end-driving","slug":"deep-steering-learning-end-to-end-driving","title":"Deep Steering: Learning End-to-End Driving Model from Spatial and Temporal Visual Cues","date":"2017-08-12","arxiv_id":"1708.03798","n_code_links":1,"syntology":null},{"paper":null,"slug":"tikhonov-regularization-for-long-short-term","title":"Tikhonov Regularization for Long Short-Term Memory Networks","date":"2017-08-09","arxiv_id":"1708.02979","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-deterministic-to-generative-multi-modal","title":"From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning","date":"2017-08-08","arxiv_id":"1708.02478","n_code_links":0,"syntology":null},{"paper":"/paper/regularizing-and-optimizing-lstm-language","slug":"regularizing-and-optimizing-lstm-language","title":"Regularizing and Optimizing LSTM Language Models","date":"2017-08-07","arxiv_id":"1708.02182","n_code_links":45,"syntology":{"ran":6,"of":7,"n_ran_checked":2,"n_instrument":4,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["salesforce/awd-lstm-lm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"improving-speaker-independent-lipreading-with","title":"Improving Speaker-Independent Lipreading with Domain-Adversarial Training","date":"2017-08-04","arxiv_id":"1708.01565","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-activation-regularization-for","slug":"revisiting-activation-regularization-for","title":"Revisiting Activation Regularization for Language RNNs","date":"2017-08-03","arxiv_id":"1708.01009","n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-aware-neural-dialog-system","title":"Domain Aware Neural Dialog System","date":"2017-08-02","arxiv_id":"1708.00897","n_code_links":0,"syntology":null},{"paper":"/paper/enterprise-to-computer-star-trek-chatbot","slug":"enterprise-to-computer-star-trek-chatbot","title":"Enterprise to Computer: Star Trek chatbot","date":"2017-08-02","arxiv_id":"1708.00818","n_code_links":1,"syntology":null},{"paper":"/paper/projectionnet-learning-efficient-on-device","slug":"projectionnet-learning-efficient-on-device","title":"ProjectionNet: Learning Efficient On-Device Deep Networks Using Neural Projections","date":"2017-08-02","arxiv_id":"1708.00630","n_code_links":0,"syntology":null},{"paper":"/paper/temporal-dynamic-graph-lstm-for-action-driven","slug":"temporal-dynamic-graph-lstm-for-action-driven","title":"Temporal Dynamic Graph LSTM for Action-driven Video Object Detection","date":"2017-08-02","arxiv_id":"1708.00666","n_code_links":0,"syntology":null},{"paper":null,"slug":"humorhawk-at-semeval-2017-task-6-mixing","title":"HumorHawk at SemEval-2017 Task 6: Mixing Meaning and Sound for Humor Recognition","date":"2017-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"latent-lstm-allocation-joint-clustering-and","title":"Latent LSTM Allocation: Joint clustering and non-linear dynamic modeling of sequence data","date":"2017-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learned-in-translation-contextualized-word","slug":"learned-in-translation-contextualized-word","title":"Learned in Translation: Contextualized Word Vectors","date":"2017-08-01","arxiv_id":"1708.00107","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["salesforce/cove"],"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":"parsing-with-context-embeddings","title":"Parsing with Context Embeddings","date":"2017-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"stanfords-graph-based-neural-dependency","title":"Stanford's Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task","date":"2017-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/state-frequency-memory-recurrent-neural","slug":"state-frequency-memory-recurrent-neural","title":"State-Frequency Memory Recurrent Neural Networks","date":"2017-08-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"uparse-the-edinburgh-system-for-the-conll","title":"UParse: the Edinburgh system for the CoNLL 2017 UD shared task","date":"2017-08-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"42a3e4f490beff041fdaadcc095b0b8d6cfb015c3e3609fb9035bd24c5e32016","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}