Top

Published in:

2020 | OriginalPaper | Chapter

Word-Level Error Correction in Non-autoregressive Neural Machine Translation

Authors : Ziyue Guo, Hongxu Hou, Nier Wu, Shuo Sun

Published in: Neural Information Processing

Publisher: Springer International Publishing

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

Non-Autoregressive neural machine translation (NAT) not only achieves rapid training but also actualizes fast decoding. However, the implementation of parallel decoding is at the expense of quality. Due to the increase of speed, the dependence on the context of the target side is discarded which resulting in the loss of the translation contextual position perception ability. In this paper, we improve the model by adding capsule network layers to extract positional information more effectively and comprehensively, that is, relying on vector neurons to compensate for the defects of traditional scalar neurons to store the position information of a single segment. Besides, word-level error correction on the output of NAT model is used to optimize generated translation. Experiments show that our model is superior to the previous model, with a BLEU score of 26.12 on the WMT2014 En-De task and a BLEU score of 31.93 on the WMT16 Ro-En, and the speed is even more than six times faster than the autoregressive model.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

previous chapter Sparse Lifting of Dense Vectors: A Unified Approach to Word and Sentence Representations

next chapter ANN-Assisted Multi-cloud Scheduling Recommender

https://github.com/moses-smt/mosesdecoder.

Source code of this work is available at https://github.com/salesforce/nonauto-nmt.

https://github.com/harpribot/nlp-metrics/tree/master/bleu.

Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015

Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 8–13 December 2014

Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, CA, USA, 4–9 December 2017, pp. 5998–6008 (2017)

Gu, J., Bradbury, J., Xiong, C., Li, V.O.K., Socher, R.: Non-autoregressive neural machine translation. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, 30 April–3 May 2018

Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. CoRR (2015). http://arxiv.org/abs/1503.02531

Wang, Y., Tian, F., He, D., Qin, T., Zhai, C., Liu, T.: Non-autoregressive machine translation with auxiliary regularization. In: The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, pp. 5377–5384 (2019)

Lee, J., Mansimov, E., Cho, K.: Deterministic non-autoregressive neural sequence modeling by iterative refinement. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 31 October–4 November 2018, pp. 1173–1182. https://www.aclweb.org/anthology/D18-1149

Ghazvininejad, M., Levy, O., Liu, Y., Zettlemoyer, L.: Mask-predict: parallel decoding of conditional masked language models. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP (2019)

Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, pp. 3856–3866 (2017)

10.

Zhou, L., Zhang, J., Zong, C.: Synchronous bidirectional neural machine translation. TACL 7, 91–105 (2019)CrossRef

11.

Shu, R., Lee, J., Nakayama, H.: Latent-variable non-autoregressive neural machine translation with deterministic inference using a delta posterior. CoRR (2019)

12.

Ma, X., Zhou, C., Li, X., Neubig, G.: Flowseq: non-autoregressive conditional sequence generation with generative flow. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP (2019)

Title: Word-Level Error Correction in Non-autoregressive Neural Machine Translation
Authors: Ziyue Guo
Hongxu Hou
Nier Wu
Shuo Sun
Publisher: Springer International Publishing
Book: Neural Information Processing
Print ISBN: 978-3-030-63819-1

Electronic ISBN: 978-3-030-63820-7

Copyright Year: 2020
DOI: https://doi.org/10.1007/978-3-030-63820-7_83

Springer Professional

Abstract

Please log in to get access to your license.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Premium Partner