Empirical Evaluation of Active Learning Techniques for Neural MT

Xiangkai Zeng, Sarthak Garg, Rajen Chatterjee, Udhyakumar Nallasamy, Matthias Paulik


Abstract
Active learning (AL) for machine translation (MT) has been well-studied for the phrase-based MT paradigm. Several AL algorithms for data sampling have been proposed over the years. However, given the rapid advancement in neural methods, these algorithms have not been thoroughly investigated in the context of neural MT (NMT). In this work, we address this missing aspect by conducting a systematic comparison of different AL methods in a simulated AL framework. Our experimental setup to compare different AL methods uses: i) State-of-the-art NMT architecture to achieve realistic results; and ii) the same dataset (WMT’13 English-Spanish) to have fair comparison across different methods. We then demonstrate how recent advancements in unsupervised pre-training and paraphrastic embedding can be used to improve existing AL methods. Finally, we propose a neural extension for an AL sampling method used in the context of phrase-based MT - Round Trip Translation Likelihood (RTTL). RTTL uses a bidirectional translation model to estimate the loss of information during translation and outperforms previous methods.
Anthology ID:
D19-6110
Volume:
Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
84–93
Language:
URL:
https://aclanthology.org/D19-6110
DOI:
10.18653/v1/D19-6110
Bibkey:
Cite (ACL):
Xiangkai Zeng, Sarthak Garg, Rajen Chatterjee, Udhyakumar Nallasamy, and Matthias Paulik. 2019. Empirical Evaluation of Active Learning Techniques for Neural MT. In Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019), pages 84–93, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Empirical Evaluation of Active Learning Techniques for Neural MT (Zeng et al., EMNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/D19-6110.pdf