2014 OnthePropertiesofNeuralMachineT
- (Cho et al., 2014) ⇒ Kyunghyun Cho, Bart van Merrienboer, Dzmitry Bahdanau, and Yoshua Bengio. (2014). "On the Properties of Neural Machine Translation: Encoder-Decoder Approaches". In: Proceedings of Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST@EMNLP 2014). DOI:10.3115/v1/W14-4012
Subject Headings: Encoder-Decoder Network, Neural Machine Translation.
Notes
- Version(s) & URL(s):
Cited By
- Google Scholar: ~ 2,372 Citations. Retrieved: 2020-04-12.
- Semantic Scholar: ~ 2,004 Citations. Retrieved: 2020-04-12.
- MS Academic: ~ 2,219 Citations. Retrieved: 2020-04-12.
Quotes
Abstract
Neural machine translation is a relatively new approach to statistical machine translation based purely on neural networks. The neural machine translation models often consist of an encoder and a decoder. The encoder extract]]s a fixed-length representation from a variable-length input sentence, and the decoder generates a correct translation from this representation. In this paper, we focus on analyzing the properties of the neural machine translation using two models; RNN Encoder-Decoder and a newly proposed gated recursive convolutional neural network. We show that the neural machine translation performs relatively well on short sentences without unknown words, but its performance degrades rapidly as the length of the sentence and the number of unknown words increase. Furthermore, we find that the proposed gated recursive convolutional network learns a grammatical structure of a sentence automatically.
1. Introduction
2. Neural Networks for Variable-Length Sequences
3. Purely Neural Machine Translation
4. Experiment Settings
5. Results and Analysis
6. Conclusion and Discussion
Acknowledgments
References
BibTeX
@inproceedings{2014_OnthePropertiesofNeuralMachineT, author = {Kyunghyun Cho and Bart van Merrienboer and [[Dzmitry Bahdanau]] and [[Yoshua Bengio]]}, editor = {Dekai Wu and Marine Carpuat and Xavier Carreras and Eva Maria Vecchi}, title = {On the Properties of Neural Machine Translation: Encoder-Decoder Approaches}, booktitle = {Proceedings of Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST@EMNLP 2014), Doha, Qatar, 25 October 2014}, pages = {103--111}, publisher = {Association for Computational Linguistics}, year = {2014}, url = {https://www.aclweb.org/anthology/W14-4012.pdf}, doi = {10.3115/v1/W14-4012}, }
Author | volume | Date Value | title | type | journal | titleUrl | doi | note | year | |
---|---|---|---|---|---|---|---|---|---|---|
2014 OnthePropertiesofNeuralMachineT | Yoshua Bengio Kyunghyun Cho Bart van Merrienboer Dzmitry Bahdanau | On the Properties of Neural Machine Translation: Encoder-Decoder Approaches | 2014 |