Neural machine translation

Neural machine translation (NMT) is an approach to machine translation that uses an artificial neural network to predict the likelihood of a sequence of words, typically modeling entire sentences in a single integrated model.

Properties

They require only a fraction of the memory needed by traditional statistical machine translation (SMT) models. Furthermore, unlike conventional translation systems, all parts of the neural translation model are trained jointly (end-to-end) to maximize the translation performance.[1][2][3]

History

Deep learning applications appeared first in speech recognition in the 1990s. The first scientific paper on using neural networks in machine translation appeared in 2014, followed by a lot of advances in the following few years. (Large-vocabulary NMT, application to Image captioning, Subword-NMT, Multilingual NMT, Multi-Source NMT, Character-dec NMT, Zero-Resource NMT, Google, Fully Character-NMT, Zero-Shot NMT in 2017) In 2015 there was the first appearance of a NMT system in a public machine translation competition (OpenMT'15). WMT'15 also for the first time had a NMT contender; the following year it already had 90% of NMT systems among its winners.[4]

Workings

NMT departs from phrase-based statistical approaches that use separately engineered subcomponents.[5] Neural machine translation (NMT) is not a drastic step beyond what has been traditionally done in statistical machine translation (SMT). Its main departure is the use of vector representations ("embeddings", "continuous space representations") for words and internal states. The structure of the models is simpler than phrase-based models. There is no separate language model, translation model, and reordering model, but just a single sequence model that predicts one word at a time. However, this sequence prediction is conditioned on the entire source sentence and the entire already produced target sequence. NMT models use deep learning and representation learning.

The word sequence modeling was at first typically done using a recurrent neural network (RNN). A bidirectional recurrent neural network, known as an encoder, is used by the neural network to encode a source sentence for a second RNN, known as a decoder, that is used to predict words in the target language.[6] Recurrent neural networks face difficulties in encoding long inputs into a single vector. This can be compensated by an attention mechanism[7] which allows the decoder to focus on different parts of the input while generating each word of the output. There are further Coverage Models addressing the issues in such attention mechanisms, such as ignoring of past alignment information leading to over-translation and under-translation.[8]

Convolutional Neural Networks (Convnets) are in principle somewhat better for long continuous sequences, but were initially not used due to several weaknesses. These were successfully compensated for in 2017 by using "attention mechanisms".[9]

An attention-based model, the transformer architecture[10] remains the dominant architecture for several language pairs.[11]

gollark: Thus, philosophy bad revert to maths.
gollark: This is moral philosophy and I don't think there are objective answers (directly) here.
gollark: Yes, which is a possible problem. You could also arbitrarily put it at some stage of brain development but I don't know how that works.
gollark: What?
gollark: I'd probably arbitrarily draw the line at where it could reasonably survive independently or something.

References
  1. Kalchbrenner, Nal; Blunsom, Philip (2013). "Recurrent Continuous Translation Models". Proceedings of the Association for Computational Linguistics: 1700–1709.
  2. Sutskever, Ilya; Vinyals, Oriol; Le, Quoc Viet (2014). "Sequence to sequence learning with neural networks". arXiv:1409.3215 [cs.CL].
  3. Kyunghyun Cho; Bart van Merrienboer; Dzmitry Bahdanau; Yoshua Bengio (3 September 2014). "On the Properties of Neural Machine Translation: Encoder–Decoder Approaches". arXiv:1409.1259 [cs.CL].
  4. Bojar, Ondrej; Chatterjee, Rajen; Federmann, Christian; Graham, Yvette; Haddow, Barry; Huck, Matthias; Yepes, Antonio Jimeno; Koehn, Philipp; Logacheva, Varvara; Monz, Christof; Negri, Matteo; Névéol, Aurélie; Neves, Mariana; Popel, Martin; Post, Matt; Rubino, Raphael; Scarton, Carolina; Specia, Lucia; Turchi, Marco; Verspoor, Karin; Zampieri, Marcos (2016). "Findings of the 2016 Conference on Machine Translation" (PDF). ACL 2016 First Conference on Machine Translation (WMT16). The Association for Computational Linguistics: 131–198. Archived from the original (PDF) on 2018-01-27. Retrieved 2018-01-27.
  5. Wołk, Krzysztof; Marasek, Krzysztof (2015). "Neural-based Machine Translation for Medical Text Domain. Based on European Medicines Agency Leaflet Texts". Procedia Computer Science. 64 (64): 2–9. arXiv:1509.08644. Bibcode:2015arXiv150908644W. doi:10.1016/j.procs.2015.08.456.
  6. Dzmitry Bahdanau; Cho Kyunghyun; Yoshua Bengio (2014). "Neural Machine Translation by Jointly Learning to Align and Translate". arXiv:1409.0473 [cs.CL].
  7. Bahdanau, Dzmitry; Cho, Kyunghyun; Bengio, Yoshua (2014-09-01). "Neural Machine Translation by Jointly Learning to Align and Translate". arXiv:1409.0473 [cs.CL].
  8. Tu, Zhaopeng; Lu, Zhengdong; Liu, Yang; Liu, Xiaohua; Li, Hang (2016). "Modeling Coverage for Neural Machine Translation". arXiv:1601.04811 [cs.CL].
  9. Coldewey, Devin (2017-08-29). "DeepL schools other online translators with clever machine learning". TechCrunch. Retrieved 2018-01-27.
  10. Vaswani, Ashish; Shazeer, Noam; Parmar, Niki; Uszkoreit, Jakob; Jones, Llion; Gomez, Aidan N.; Kaiser, Lukasz; Polosukhin, Illia (2017-12-05). "Attention Is All You Need". arXiv:1706.03762 [cs.CL].
  11. Barrault, Loïc; Bojar, Ondřej; Costa-jussà, Marta R.; Federmann, Christian; Fishel, Mark; Graham, Yvette; Haddow, Barry; Huck, Matthias; Koehn, Philipp; Malmasi, Shervin; Monz, Christof (August 2019). "Findings of the 2019 Conference on Machine Translation (WMT19)". Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1). Florence, Italy: Association for Computational Linguistics: 1–61. doi:10.18653/v1/W19-5301.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.