Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Open accessThe DOI matches its Crossref record; 29 of the 31 references it cites were found in a registry or an index.
Abstract
Kyunghyun Cho, Bart van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, Yoshua Bengio. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“GRU [185] is a variant based on the LSTM, which only contains an update gate and reset gate and has a faster training speed than the LSTM with fewer parameters.”
From Deep Learning for Structural Health Monitoring: Data, Algorithms, Applications, Challenges, and Trends (2023) · cites this paper as [185]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“They are thus well-suited for detecting dependencies and patterns in language-like input.”
From The role of pragmatic mechanisms in referential communication and categorization: An emergent communication model (2026) · cites this paper as [87]
The cited source says what the claim attributes to it.
In the citing paper
“GRU cells are a specific type of Recurrent Neural Networks (RNNs) which have been proven useful for dealing with sequence data such as language.”
From The role of pragmatic mechanisms in referential communication and categorization: An emergent communication model (2026) · cites this paper as [87]
The cited source says what the claim attributes to it.
In the citing paper
“Early work [139-141] mainly relied on recurrent neural networks (e.g., LSTM [142], GRU [143]). Limited by the model's expressiveness, they often suffer from the issue of insufficient diversity.”
From When large language models meet personalization: perspectives of challenges and opportunities (2024) · cites this paper as [143]
The cited source says what the claim attributes to it.
In the citing paper
“Moreover, [Tang et al., 2020] adopts GRU [Cho et al., 2014] on the sequence of hyperplanes to further capture the dynamics among hyperplanes.”
From Temporal Knowledge Graph Completion: A Survey (2023) · cites this paper as Cho et al., 2014
3 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“At each time step t , the hidden state h t (cid:105) of the RNN is updated by where f is a non-linear activation function. f may be as simple as an element-wise logistic sigmoid function and as complex as a long short-term memory (LSTM) unit (Hochreiter and Schmidhuber, 1997).”
BackgroundDistributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 1×
“We have done so by applying the data selection method proposed in (Moore and Lewis, 2010), and its extension to bi-texts (Axelrod et al., 2011).”
Method(2011) · Cited by 6,993
Self-citationADADELTA: An Adaptive Learning Rate Method
Zeiler, M. D. (2012) · arXiv · doi:10.48550/arxiv.1212.5701 · Cited by 5,322 · cited 2×
“95 (Zeiler, 2012).”
MethodStatistical phrase-based translation
Koehn, P., Och, F. J., & Marcu, D. (2003) · Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - NAACL '03 · doi:10.3115/1073445.1073462 · Cited by 3,197 · cited 2×
“In the phrase-based SMT framework introduced in (Koehn et al., 2003) and (Marcu and Wong, 2002), the translation model log p ( e | f ) is factorized into the translation probabilities of matching phrases in the source and target sentences.”
Method(2005) · Cited by 3,125
Supervised Sequence Labelling with Recurrent Neural Networks
Graves, A. (2012) · Studies in Computational Intelligence · doi:10.1007/978-3-642-24797-2 · Cited by 3,120
Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition
Dahl, G. E., Yu, D., Deng, L., & Acero, A. (2012) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2011.2134090 · Cited by 3,011 · cited 1×
“Deep neural networks have shown great success in various applications such as objection recognition (see, e.g., (Krizhevsky et al., 2012)) and speech recognition (see, e.g., (Dahl et al., 2012)).”
BackgroundRecurrent Continuous Translation Models
Kalchbrenner, N., & Blunsom, P. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1176 · Cited by 1,232 · cited 1×
“The closest approach related to the proposed RNN Encoder–Decoder is the Recurrent Continuous Translation Model (Model 2) proposed in (Kalchbrenner and Blunsom, 2013).”
Method
Cited by
Items 1,201–1,296 of 1,296
Mai, S., Hu, H., & Xing, S. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3082398 · Cited by 26
Child speech disorder detection with Siamese recurrent network using speech attribute features
Wang, J., Qin, Y., Peng, Z., & Lee, T. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2320 · Cited by 27
Visual Question Generation: The State of the Art
Patil, C., & Patwardhan, M. (2021) · ACM Computing Surveys · doi:10.1145/3383465 · Cited by 25
Yao, J., & Kowal, J. (2025) · Energy and AI · doi:10.1016/j.egyai.2025.100585 · Cited by 30
Wang, X., Delgado, H., Tak, H., Jung, J.-W., Shim, H.-J., Todisco, M., Kukanov, I., Liu, X., Sahidullah, M., Kinnunen, T., et al. (2026) · Computer Speech & Language · doi:10.1016/j.csl.2025.101825 · Cited by 30
“VITS produces especially high quality synthetic speech and is readily accessible with the open-sourced toolkit ESPNet [65].”
Using Machine Learning to Measure Relatedness Between Genes: A Multi-Features Model
Wang, Y., Yang, S., Zhao, J., Du, W., Liang, Y., Wang, C., Zhou, F., Tian, Y., & Ma, Q. (2019) · Scientific Reports · doi:10.1038/s41598-019-40780-7 · Cited by 26
Language-Agnostic Representation Learning for Product Search on E-Commerce Platforms
Ahuja, A., Rao, N., Katariya, S., Subbian, K., & Reddy, C. K. (2020) · Proceedings of the 13th International Conference on Web Search and Data Mining · doi:10.1145/3336191.3371852 · Cited by 26
Dialog context language modeling with recurrent neural networks
Liu, B., & Lane, I. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7953251 · Cited by 26
TransformerFAM: feedback attention is working memory
Hwang, D., Wang, W., Huo, Z., Sim, K. C., & Mengibar, P. M. (2024) · arXiv · doi:10.48550/arxiv.2404.09173 · Cited by 26
“Recurrent Neural Networks (RNNs) have achieved great success in machine learning by introducing feedback loops (Hochreiter & Schmidhuber, 1997a; Cho et al., 2014).”
BackgroundTransformer Memory for Interactive Visual Navigation in Cluttered Environments
Li, W., Hong, R., Shen, J., Yuan, L., & Lu, Y. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3241803 · Cited by 26
Design in the DARK: Learning Deep Generative Models for De Novo Protein Design
Moffat, L., Kandathil, S. M., & Jones, D. T. (2022) · doi:10.1101/2022.01.27.478087 · Cited by 25
“It uses a combination of two GRUs (Cho et al., 2014) followed by a residual network to predict distograms from a multiple sequence alignment.”
MethodQi, P., Zhang, Y., & Manning, C. D. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.3 · Cited by 23
Robust federated learning with attack-adaptive aggregation
Wan, C. P. (2022) · doi:10.14711/thesis-991012994506603412 · Cited by 24
A comprehensive EHR timeseries pre-training benchmark
McDermott, M., Nestor, B., Kim, E., Zhang, W., Goldenberg, A., Szolovits, P., & Ghassemi, M. (2021) · Proceedings of the Conference on Health, Inference, and Learning · doi:10.1145/3450439.3451877 · Cited by 24
“All models in this work use a GRU model [8] as their encoder E.”
MethodApproximate information state for partially observed systems
Subramanian, J., & Mahajan, A. (2019) · 2019 IEEE 58th Conference on Decision and Control (CDC) · doi:10.1109/cdc40024.2019.9029898 · Cited by 23
TPmod: A Tendency-Guided Prediction Model for Temporal Knowledge Graph Completion
Bai, L., Ma, X., Zhang, M., & Yu, W. (2021) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3443687 · Cited by 23
“It aggregates entity features and relation features, and encodes the temporal dependency with GRU to predict future events.”
MethodDeepAlign: Alignment-Based Process Anomaly Correction Using Recurrent Neural Networks
Nolle, T., Seeliger, A., Thoma, N., & Mühlhäuser, M. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-49435-3_20 · Cited by 23
Deep sequential models for suicidal ideation from multiple source data
Peis, I., Olmos, P. M., Vera-Varela, C., Barrigon, M. L., Courtet, P., Baca-Garcia, E., & Artes-Rodriguez, A. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2919270 · Cited by 22
“complex architectures like Long Short Term Memory (LSTM [23]) or Gated Recurrent Unit (GRUs [24]).”
BackgroundInterpretable machine learning for high-dimensional trajectories of aging health
Farrell, S., Mitnitski, A., Rockwood, K., & Rutenberg, A. D. (2022) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1009746 · Cited by 22
“We use a 2-layer Gated Recurrent Unit (GRU [63]) for the RNN, with hidden state ht.”
InfluentialLiu, F., Shen, S.-Y., Fu, Z.-W., Wang, H.-Y., Zhou, A.-M., & Qi, J.-Y. (2022) · Entropy · doi:10.3390/e24071010 · Cited by 21
“We adopt length-scaled attention module to improve the performance of the model when applied to various testing sequence length and theoretically interpret the determination of the scaled hyperparameter from a view of entropy.”
Predicting improved protein conformations with a temporal deep recurrent neural network
Pfeiffenberger, E., & Bates, P. A. (2018) · PLOS ONE · doi:10.1371/journal.pone.0202652 · Cited by 21
Analysis of sentence embedding models using prediction tasks in natural language processing
Adi, Y., Kermany, E., Belinkov, Y., Lavi, O., & Goldberg, Y. (2017) · IBM Journal of Research and Development · doi:10.1147/jrd.2017.2702858 · Cited by 21
RETRACTED ARTICLE: Machine learning prediction of the Madden-Julian oscillation
Silini, R., Barreiro, M., & Masoller, C. (2021) · npj Climate and Atmospheric Science · doi:10.1038/s41612-021-00214-6 · Cited by 21
RetractedCurrent limitations in predicting mRNA translation with deep learning models
Schlusser, N., González, A., Pandey, M., & Zavolan, M. (2024) · Genome Biology · doi:10.1186/s13059-024-03369-6 · Cited by 21
“To run the Optimus models on the local scientific computing infrastructure, the model training was re-implemented in a python script, rather than a jupyter notebook as in the git repository cited in [14].”
MethodKaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps
Dao, T., Sohoni, N. S., Gu, A., Eichhorn, M., Blonder, A., Leszczynski, M., Rudra, A., & Ré, C. (2020) · arXiv · doi:10.48550/arxiv.2012.14966 · Cited by 21
QuickEdit: Editing Text and Translations by Crossing Words Out
Grangier, D., & Auli, M. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1025 · Cited by 20
Zhang, P., Gao, X., Miao, M., & Zhao, P. (2022) · Machines · doi:10.3390/machines10121125 · Cited by 20
Decoding visual motions from EEG using attention based RNN.
Yang, D., Liu, Y., Zhou, Z., Yu, Y., & Liang, X. (2020) · Applied Sciences · doi:10.3390/app10165662 · Cited by 20
“Gated Recurrent Unit (GRU) [41], one of the two commonly used RNN variants, is exploited in this study because it not only addresses the gradient vanishing problem associated with RNN but also is more lightweight than the other variant, namely LSTM [42].”
MethodHybrid Recurrent Deep Learning Model for DeepFake Video Detection
Jaiswal, G. (2021) · 2021 IEEE 8th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON) · doi:10.1109/upcon52273.2021.9667632 · Cited by 20
Deep Unsupervised Binary Coding Networks for Multivariate Time Series Retrieval
Zhu, D., Song, D., Chen, Y., Lumezanu, C., Cheng, W., Zong, B., Ni, J., Mizoguchi, T., Yang, T., & Chen, H. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i02.5497 · Cited by 20
“…the temporal information within a multivariate time series segment, similar to Seq2Seq model used in machine translation and video representation (Cho et al. 2014; Sutskever, Vinyals, and Le 2014; Srivastava, Mansimov, and Salakhudinov 2015), we adopt a LSTM encoder to represent the input time…”
MethodUsing deep learning and electronic health records to detect Noonan syndrome in pediatric patients
Yang, Z., Shikany, A., Ni, Y., Zhang, G., Weaver, K. N., & Chen, J. (2022) · Genetics in Medicine · doi:10.1016/j.gim.2022.08.002 · Cited by 20
Meta Learning Backpropagation And Improving It
Kirsch, L., & Schmidhuber, J. (2020) · arXiv · doi:10.48550/arxiv.2012.14905 · Cited by 19
“Introducing variable sharing to Meta RNNs We begin by formalizing Meta RNNs which often use multiplicative gates such as the LSTM [12, 15] or its variant GRU [6].”
MethodHierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation
Deng, Z., Peng, H., Xia, C., Li, J., He, L., & Yu, P. (2020) · Proceedings of the 28th International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.555 · Cited by 19
Out-of-Distribution Dynamics Detection: RL-Relevant Benchmarks and Results
Danesh, M. H., & Fern, A. (2021) · arXiv · doi:10.48550/arxiv.2107.04982 · Cited by 18
“At a high-level RIQN differs from IQN in three ways: 1) Since we are interested in dynamics prediction in problems where observations may not fully capture the state (e.g. nominal policies can have internal memory), we add recurrent memory to the IQN network via a GRU (Cho et al., 2014) layer.”
InfluentialFIVES: Feature Interaction Via Edge Search for Large-Scale Tabular Data
Xie, Y., Wang, Z., Li, Y., Ding, B., Gürel, N. M., Zhang, C., Huang, M., Lin, W., & Zhou, J. (2021) · Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining · doi:10.1145/3447548.3467066 · Cited by 18
HMFP-DBRNN: Real-Time Hand Motion Filtering and Prediction via Deep Bidirectional RNN
Shahtalebi, S., Atashzar, S. F., Patel, R. V., & Mohammadi, A. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2894005 · Cited by 17
Automatic Medical Image Report Generation with Multi-view and Multi-modal Attention Mechanism
Yang, S., Niu, J., Wu, J., & Liu, X. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-60248-2_48 · Cited by 17
On Missingness Features in Machine Learning Models for Critical Care: Observational Study
Singh, J., Sato, M., & Ohkuma, T. (2021) · JMIR Medical Informatics · doi:10.2196/25022 · Cited by 17
“We used a gated RNN variant, specifically a gated recurrent unit (GRU) to model long EHR sequences [39].”
Recurrent Off-policy Baselines for Memory-based Continuous Control
Yang, Z., & Nguyen, H. (2021) · arXiv · doi:10.48550/arxiv.2110.12628 · Cited by 17
“RSAC-LSTM and RSAC-GRU are on par with each other, and both greatly out-performs RSAC-VRNN. representation is an equally reasonable choice.”
MethodInfluentialA Review on Genomics Data Analysis using Machine Learning
Aggarwal, A. K. (2023) · WSEAS TRANSACTIONS ON BIOLOGY AND BIOMEDICINE · doi:10.37394/23208.2023.20.12 · Cited by 17
“Access to high-performance computing resources and expertise in managing and analyzing large-scale genomic datasets can pose barriers for researchers and limit the widespread adoption of these techniques, [80].”
Deep learning approach to detection of colonoscopic information from unstructured reports
Seong, D., Choi, Y. H., Shin, S.-Y., & Yi, B.-K. (2023) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-023-02121-7 · Cited by 16
“Its variants, such as long short-term memory (LSTM) [29] and gated recurrent unit (GRU) [30], have been proposed to overcome the limitation of RNN.”
BackgroundLearning reservoir dynamics with temporal self-modulation
Sakemi, Y., Nobukawa, S., Matsuki, T., Morie, T., & Aihara, K. (2024) · Communications Physics · doi:10.1038/s42005-023-01500-w · Cited by 16
Automation of Legal Precedents Retrieval: Findings from a Literature Review
Mentzingen, H., António, N., & Bacao, F. (2023) · International Journal of Intelligent Systems · doi:10.1155/2023/6660983 · Cited by 16
Cheng, H., Sheng, B., Lee, A., Chaudary, V., Atanasov, A. G., Liu, N., Qiu, Y., Wong, T. Y., Tham, Y.-C., & Zheng, Y. (2024) · doi:10.1101/2024.03.25.586710 · Cited by 15
“In early models like LSTM or GRU (Hochreiter and Schmidhuber, 1997; Cho et al., 2014), machine-101 generated texts could be easily spotted and were generally considered useless in production.”
BackgroundOpen-ended remote sensing visual question answering with transformers
Al Rahhal, M. M., Bazi, Y., Alsaleh, S. O., Al-Razgan, M., Mekhalfi, M. L., Al Zuair, M., & Alajlan, N. (2022) · International Journal of Remote Sensing · doi:10.1080/01431161.2022.2145583 · Cited by 15
“…typically adopts end to end encoder-decoder architectures where visual representation and relevant language translation are commonly addressed by means of Convolutional Neural Networks (CNNs) and Long-Short Term Memory Networks, respectively (Wu et al. 2016; Cho et al. 2014; Vinyals et al. 2017).”
BackgroundEysenbach, B., Salakhutdinov, R., & Levine, S. (2021) · arXiv · doi:10.48550/arxiv.2109.03214 · Cited by 15
“While, in theory, the VIB+RNN baseline could implement RPC internally, in practice it achieved lower returns, perhaps because of optimization challenges associated with training LSTMs [7].”
Question Generation With Doubly Adversarial Nets
Bao, J., Gong, Y., Duan, N., Zhou, M., & Zhao, T. (2018) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2018.2859777 · Cited by 14
RaScaNet: Learning Tiny Models by Raster-Scanning Images
Yoo, J., Lee, D., Son, C., Jung, S., Yoo, B., Choi, C., Han, J.-J., & Han, B. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01346 · Cited by 14
“We choose a variant of GRU [4] for the sequential modeling, which adopts 1D convolutions rather than fully connected layers.”
MethodE-BATCH: Energy-Efficient and High-Throughput RNN Batching
Silfa, F., Arnau, J. M., & González, A. (2022) · ACM Transactions on Architecture and Code Optimization · doi:10.1145/3499757 · Cited by 14
“For this reason, the Long Short Term Memory (LSTM) [12] and Gated Recurrent Unit (GRU) [13] architectures were proposed.”
MethodSkip-attention encoder–decoder framework for human motion prediction
Zhang, R., Shu, X., Yan, R., Zhang, J., & Song, Y. (2022) · Multimedia Systems · doi:10.1007/s00530-021-00807-4 · Cited by 13
Market Manipulation: An Adversarial Learning Framework for Detection and Evasion
Wang, X., & Wellman, M. P. (2020) · Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/638 · Cited by 13
QAScore—An Unsupervised Unreferenced Metric for the Question Generation Evaluation
Ji, T., Lyu, C., Jones, G., Zhou, L., & Graham, Y. (2022) · Entropy · doi:10.3390/e24111514 · Cited by 12
Cross-Subject EEG Signal Classification with Deep Neural Networks Applied to Motor Imagery
Riyad, M., Khalil, M., & Adib, A. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-22885-9_12 · Cited by 12
Exploration and preference satisfaction trade-off in reward-free learning
Sajid, N., Tigas, P., Zakharov, A., Fountas, Z., & Friston, K. (2021) · arXiv · doi:10.48550/arxiv.2106.04316 · Cited by 11
“Formally, this consists of the following: 1) a GRU [12] based deterministic recurrent model, ht = fθ(h<t, s<t, π<t); 2) latent state posterior, Qφ(st|ht, ot) ∼ Cat, and prior, P (s) ∼ Cat(D); 3) transition model, Pθ(st|ht) ∼ Cat; 3) image predictor (or emission model), Qφ(ot|ht, st) ∼ Bernoulli; and 4) reward model, Q…”
BackgroundTRHyTE: Temporal Knowledge Graph Embedding Based on Temporal-Relational Hyperplanes
Yuan, L., Li, Z., Qu, J., Zhang, T., Liu, A., Zhao, L., & Chen, Z. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-00123-9_10 · Cited by 11
Wang, S., Duan, F., & Zhang, M. (2020) · Applied Sciences · doi:10.3390/app10217465 · Cited by 10
“The CNN network is used to extract relevant features, and the Gated Recurrent Unit (GRU) network [30] is used as a classifier to classify the experimental tasks to study whether the subjects carry out the episodic memory task will cause significant changes in the physiological state of the brain.”
MethodLeveraging effectiveness and efficiency in Page Stream Deep Segmentation
Braz, F. A., da Silva, N. C., & Lima, J. A. S. (2021) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2021.104394 · Cited by 10
AttAuth: An implicit authentication framework for smartphone users using multimodality data
Zhao, C., Gao, F., & Shen, Z. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3314717 · Cited by 10
CrisisLTLSum: A Benchmark for Local Crisis Event Timeline Extraction and Summarization
Faghihi, H. R., Alhafni, B., Zhang, K., Ran, S., Tetreault, J., & Jaimes, A. (2022) · arXiv · doi:10.48550/arxiv.2210.14190 · Cited by 9
“BERT-GRU For the BERT-GRU sequence labeling model, we use BERT base uncased to get the contextual representation for each tweet.”
MethodInfluentialAttention Mechanism for Human Motion Prediction
Al-aqel, A. F., & Ali Khan, M. (2020) · 2020 3rd International Conference on Computer Applications & Information Security (ICCAIS) · doi:10.1109/iccais48893.2020.9096777 · Cited by 7
Deepfake Detection Based on Incompatibility Between Multiple Modes
Zhang, Y., Zhan, J., Jiang, W., & Fan, Z. (2021) · 2021 International Conference on Intelligent Technology and Embedded Systems (ICITES) · doi:10.1109/icites53477.2021.9637096 · Cited by 7
LLM meets ML: Data-efficient Anomaly Detection on Unstable Logs
Hadadi, F., Xu, Q., Bianculli, D., & Briand, L. (2024) · arXiv · doi:10.48550/arxiv.2406.07467 · Cited by 7
Mutual influence between language and perception in multi-agent communication games
Ohmer, X., Marino, M., Franke, M., & König, P. (2022) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1010658 · Cited by 6
“The language module, l ( · ) , consists Figure 1: Schematic visualization of sender and receiver architecture and their interaction in one round of the reference game.”
Colas, J. T., O’Doherty, J. P., & Grafton, S. T. (2024) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1011950 · Cited by 6
Exploring the Knowledge of an Outstanding Protein to Protein Interaction Transformer
Yang, S., Cheng, P., Liu, Y., Feng, D., & Wang, S. (2024) · IEEE/ACM Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2024.3381825 · Cited by 6
“DNN-PPI [14] uses CNN stacked with a long-short-term memory network [23] to extract protein feature.”
MethodHardy, E., & Badets, F. (2021) · arXiv · doi:10.48550/arxiv.2103.04792 · Cited by 6
“We can observe that for a fixed hidden dimension, the MGU has twice as many parameters as the tanh-RNN but two thirds of the GRU.”
BackgroundInfluentialA Mobility Forecasting Framework with Vertical Federated Learning
Errounda, F. Z., & Liu, Y. (2022) · 2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC) · doi:10.1109/compsac54236.2022.00050 · Cited by 6
Towards Generating Summaries for Lexically Confusing Code through Code Erosion
Yan, F., & Li, M. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/512 · Cited by 6
An Image Captioning Model Based on Bidirectional Depth Residuals and its Application
Zhou, Z., Xu, L., Wang, C., Xie, W., Wang, S., Ge, S., & Zhang, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3057091 · Cited by 6
“In order to extract the association features between words that are far away from each other, long short-term memory network (LSTM) [9] and bidirectional RNN model [10] have been proposed one after another, then Cho et al. improved on the basis of LSTM and proposed the GRU [11] model.”
BackgroundMethodUnlocking the Power of Deep PICO Extraction: Step-wise Medical NER Identification
Zhang, T., Yu, Y., Mei, J., Tang, Z., Zhang, X., & Li, S. (2020) · arXiv · doi:10.48550/arxiv.2005.06601 · Cited by 6
“There are a lot of works using natural language processing (NLP) algorithms to extract medical NERs and classify them into different classes.”
BackgroundPrevent the Language Model from being Overconfident in Neural Machine Translation
Miao, M., Meng, F., Liu, Y., Zhou, X.-H., & Zhou, J. (2021) · arXiv · doi:10.48550/arxiv.2105.11098 · Cited by 5
Recommending Reforming Trip to a Group of Users
Abbas, R., Amran, G. A., Alsanad, A., Ma, S., Almisned, F. A., Huang, J., Al Bakhrani, A. A., Ahmed, A. B., & Alzahrani, A. I. (2022) · Electronics · doi:10.3390/electronics11071037 · Cited by 5
“To be specific, the fge is shown by Equation (2): fge(c) = ReLU(ReLU(cW1 + B1)W2 + B2) (2) while c = (dX, dY) is the direction of a POI, b1 and b2 are the biases, W1 and W2 are the weights, and ReLU [23] denotes a rectified linear activation unit.”
BackgroundInfluentialExploring Uncertainty Measures for Image-Caption Embedding-and-Retrieval Task
Hama, K., Matsubara, T., Uehara, K., & Cai, J. (2019) · arXiv · doi:10.48550/arxiv.1904.08504 · Cited by 5
Fine-Grained Fault Sensitivity Analysis of Vision Transformers Under Soft Errors
He, J., Liu, Y., Xu, C., Liao, X., & Yang, Y. (2025) · Electronics · doi:10.3390/electronics14122418 · Cited by 4
Yaman, O. (2025) · Drones · doi:10.3390/drones9110807 · Cited by 4
“[22], simplify the LSTM structure by combining the forget and input gates, thereby reducing computational complexity while maintaining comparable performance.”
Public Transit Arrival Prediction: a Seq2Seq RNN Approach
Bhutani, N., Pachal, S., & Achar, A. (2022) · arXiv · doi:10.48550/arxiv.2210.01655 · Cited by 3
“Note that these synchronised inputs at the decoder are absent in the classic ED application for machine translation [23], [24].”
BackgroundIrie, K., Csordás, R., & Schmidhuber, J. (2023) · arXiv · doi:10.48550/arxiv.2310.16076 · Cited by 3
“…(2001); Schmidhuber et al. (2002); Weiss et al. (2018b); Suzgun et al. (2019a)), unlike its simplified versions such as the gated recurrent unit (GRU; Cho et al. (2014); Gers et al. (2000)), the Quasi-RNN (Bradbury et al. (2017); see Merrill et al. (2020)) or the simple sigmoid RNN (Elman, 1988).”
BackgroundMemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory
Modarressi, A., Köksal, A., Imani, A., Fayyaz, M., & Schütze, H. (2024) · arXiv · doi:10.48550/arxiv.2404.11672 · Cited by 3
Relation-Aware Question Answering for Heterogeneous Knowledge Graphs
Du, H., Huang, Q., Li, C., Zhang, C., Li, Y., & Zhao, D. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.906 · Cited by 2
Clustering of Temporal and Visual Data: Recent Advancements
Mudgal, P. (2026) · Data · doi:10.3390/data11010007 · Cited by 2
“These models have been extensively applied in time-series clustering tasks by first encoding input sequences into latent embeddings, which are then clustered using traditional algorithms such as k-means or DBSCAN [80,81].”
Deep Just-In-Time Inconsistency Detection Between Comments and Source Code
Panthaplackel, S., Li, J. J., Gligoric, M., & Mooney, R. J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i1.16119 · Cited by 2
Exploring Transformer Extrapolation
Qin, Z., Zhong, Y., & Deng, H. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i17.29855 · Cited by 2
Temporal subgraph contrastive learning for anomaly detection on dynamic attributed graphs
Yu, Y., Li, X., Shao, M., Sun, Y., & Wang, W. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06402-8 · Cited by 2
EpyNN: Educational python for Neural Networks
Malard, F., Danner, L., Rouzies, E., Meyer, J. G., Lescop, E., & Olivier-Van Stichelen, S. (2022) · SoftwareX · doi:10.1016/j.softx.2022.101140 · Cited by 2
Exploring Transformer Extrapolation
Qin, Z., Zhong, Y., & Deng, H. (2023) · arXiv · doi:10.48550/arxiv.2307.10156 · Cited by 2
XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX
Nikulin, A., Kurenkov, V., Zisman, I., Agarkov, A., Sinii, V., & Kolesnikov, S. (2024) · Advances in Neural Information Processing Systems 37 · doi:10.52202/079017-1390 · Cited by 3
“While our implementation is greatly simplified in comparison to Ada (Team et al., 2023), it encap-sulates the main principles and is easy to understand and modify, e.g., swapping simple GRU (Cho et al., 2014) for more modern and efficient state space models (Lu et al., 2023).”
MethodDisDock : A Deep Learning Method for Metal Ion‐Protein Redocking
Lin, M., Li, K., Zhang, Y., Pan, F., Wu, W., & Zhang, J. (2025) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26791 · Cited by 1
DisDock: A Deep Learning Method for Metal Ion-Protein Redocking
(2023) · doi:10.1101/2023.12.07.570531 · Cited by 1
Birwadkar, R. (2025) · Journal of Computer and Forensic Sciences · doi:10.5937/jcfs4-64419
Kobrock, K., Ohmer, X., Bruni, E., & Gotzner, N. (2026) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1014326
“Both our speaker and listener agents are implemented as neural networks with feed-forward (dense) layers for embedding the input objects and Gated-Recurrent-Unit (GRU) [87] cells to encode (speaker) or decode (listener) the messages.”
MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
von Oswald, J., Scherrer, N., Kobayashi, S., Versari, L., Yang, S., Mittal, S., Schlegel, M., Maile, K., Schimpf, Y., Sieberling, O., et al. (2025) · arXiv
“Even more, studies on simplified LSTM variants, such as the Gated Recurrent Unit [19], have shown the forget gate to be fundamental for the effectiveness of recurrent sequence models [108].”
Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairs
Furelos-Blanco, D., Pert, C., Kelbel, F., Spies, A. F., Russo, A., & Dennis, M. (2025) · arXiv
“The resulting embedding is processed by a gated recurrent unit (GRU; Cho et al. 2014) producing 512 features.”
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
“Recurrent neural networks, long short-term memory [12] and gated recurrent [7] neural networks in particular, have been firmly established as state of the art approaches in sequence modeling and transduction problems such as language modeling and machine translation [29, 2, 5].”
BackgroundNavFormer: A Transformer Architecture for Robot Target-Driven Navigation in Unknown and Dynamic Environments
Wang, H., Tan, A. H., & Nejat, G. (2024) · arXiv · Cited by 40
“In[22],aGatedRecurrent Unit (GRU) [27] was incorporated in [21] to account for historical observations to improve temporal reasoning in unknown environments.”
MethodOrder Matters: Sequence to sequence for sets
Vinyals, O., Bengio, S., & Kudlur, M. (2015) · arXiv · doi:10.48550/arxiv.1511.06391
Adding Gradient Noise Improves Learning for Very Deep Networks
Neelakantan, A., Vilnis, L., Le, Q. V., Sutskever, I., Kaiser, L., Kurach, K., & Martens, J. (2015) · arXiv · doi:10.48550/arxiv.1511.06807
Metadata
- Authors
- Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y.
- Affiliations
- Le Mans Université (FR)
- Polytechnique Montréal (CA)
- Venue
- Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Published
- 2014
- Pages
- 1724-1734
- OpenAlex
- W2157331557
- Cited by
- 25,545
- References
- 31
- Citations by year
- 2026: 1895 · 2025: 2591 · 2024: 2721 · 2023: 3047 · 2022: 3245 · 2021: 3534 · 2020: 3063 · 2019: 2494 · 2018: 1644 · 2017: 816 · 2016: 349 · 2015: 119 · 2014: 22
- FWCI
- 256.40
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- HAL (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Keywords
- statistical machine translation, neural machine translation, phrase embeddings, sequence-to-sequence models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.