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).”
MethodTheano: new features and speed improvements
Bastien, F., Lamblin, P., Pascanu, R., Bergstra, J., Goodfellow, I., Bergeron, A., Bouchard, N., Warde-Farley, D., & Bengio, Y. (2012) · arXiv · doi:10.48550/arxiv.1211.5590 · Cited by 1,005 · cited 1×
“In that case, for a given source phrase, the RNN Encoder–Decoder will need to generate a list of (good) target phrases.”
BackgroundSelf-citationDynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection
Socher, R., Huang, E., Pennin, J., Manning, C. D., & Ng, A. Y. (2011) · neural information processing systems · Cited by 958
Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
Saxe, A., McClelland, J. L., & Ganguli, S. (2014) · International Conference on Learning Representations · Cited by 761
Intelligent Selection of Language Model Training Data
Moore, R. C., & Lewis, W. D. (2010) · Cited by 702
(2014) · International Conference on Learning Representations · Cited by 634
Self-citationBilingual Word Embeddings for Phrase-Based Machine Translation
Zou, W. Y., Socher, R., Cer, D., & Manning, C. D. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1141 · Cited by 518 · cited 4×
“One important difference between the proposed RNN Encoder–Decoder and the approaches in (Zou et al., 2013) and (Chandar et al.”
BackgroundMethodInfluentialContinuous space language models
Schwenk, H. (2007) · Computer Speech & Language · doi:10.1016/j.csl.2006.09.003 · Cited by 516 · cited 9×
“To address the computational complexity of using a CSLM in the decoder a buffer was used to aggregate n-grams during the stack-search performed by the decoder.”
BackgroundMethodInfluentialSelf-citationFast and Robust Neural Network Joint Models for Statistical Machine Translation
Devlin, J., Zbib, R., Huang, Z., Lamar, T., Schwartz, R., & Makhoul, J. (2014) · Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.3115/v1/p14-1129 · Cited by 481 · cited 2×
“(Devlin et al., 2014) proposed to use a feedforward neural network to model a translation model, however, by predicting one word in a target phrase at a time.”
Domain Adaptation via Pseudo In-Domain Data Selection
Axelrod, A. E., He, X., & Gao, J. (2011) · Cited by 473
A phrase-based, joint probability model for statistical machine translation
Marcu, D., & Wong, W. (2002) · Proceedings of the ACL-02 conference on Empirical methods in natural language processing - EMNLP '02 · doi:10.3115/1118693.1118711 · Cited by 470 · cited 1×
“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.”
MethodAdvances in optimizing recurrent networks
Bengio, Y., Boulanger-Lewandowski, N., & Pascanu, R. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6639349 · Cited by 469 · cited 1×
“Furthermore, this may be considered an adaptive variant of a leaky-integration unit (Bengio et al., 2013).”
BackgroundSelf-citationAn Autoencoder Approach to Learning Bilingual Word Representations
P, S. C. A., Lauly, S., Larochelle, H., Khapra, M. M., Ravindran, B., Raykar, V. C., & Saha, A. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1402.1454 · Cited by 309 · cited 2×
“In (Chandar et al., 2014), a feedforward neural network was trained to learn a mapping from a bag-of-words representation of an input phrase to an output phrase.”
BackgroundMethodJoint Language and Translation Modeling with Recurrent Neural Networks
Auli, M., Galley, M., Quirk, C., & Zweig, G. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1106 · Cited by 253 · cited 2×
“More recently, another encoder–decoder model using an RNN was proposed in (Auli et al., 2013), where the decoder is conditioned on a representation of either a source sentence or a source context.”
MethodDecoding with Large-Scale Neural Language Models Improves Translation
Vaswani, A., Zhao, Y., Fossum, V., & Chiang, D. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1140 · Cited by 213 · cited 1×
“The model was used to score partial translations during the decoding process, which generally leads to higher gains in BLEU score than n-best list rescoring (Vaswani et al., 2013).”
MethodContinuous space translation models with neural networks
Le, H.-S., Allauzen, A., & Yvon, F. (2012) · HAL · Cited by 116
Continuous Space Translation Models for Phrase-Based Statistical Machine Translation
Schwenk, H. (2025) · doi:10.57702/tyvla89t · Cited by 110
Self-citationBarnes-Hut-SNEPreprint
van der Maaten, L. J. P. (2013) · arXiv (Cornell University) · Cited by 75
Learning Semantic Representations for the Phrase Translation ModelPreprint
Gao, J., He, X., Yih, W.-T., & Deng, L. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1312.0482 · Cited by 28 · cited 1×
“A similar approach of using bag-of-words representations was proposed in (Gao et al., 2013) as well.”
MethodContinuous Space Language Models for the IWSLT 2006 Task
Schwenk, H., Costa‐jussà, M. R., & Fonollosa, J. A. R. (2006) · HAL · Cited by 23
Self-citation
Cited by
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Self-citationA survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332
“The Gated Recurrent Unit (Cho et al., 2014) is a recent simplification of the LSTM and is also commonly used.”
MethodA Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978386 · Cited by 11,000
Effective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382
“cent NMT work such as (Kalchbrenner and Blunsom, 2013; Sutskever et al., 2014; Cho et al., 2014; Bahdanau et al., 2015; Luong et al., 2015; Jean et al., 2015) have in common.”
BackgroundMethodInfluentialShow, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248
“Some that share the same spirit as our work include Larochelle & Hinton (2010); Denil et al. (2012); Tang et al. (2014) and more recently Gregor et al.”
BackgroundMethodResultInfluentialSelf-citation
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.