Encoding Gated Translation Memory into Neural Machine Translation
By Deyi Xiong. 2018
55 citations recorded by the source corpus.
Translation memories (TM) facilitate human translators to reuse existing repetitive translation fragments. In this paper, we propose a novel method to combine the strengths of both TM and neural machine translation (NMT) for high-quality translation. We treat the target translation of a TM match as an additional reference input and encode it into NMT with an extra encoder. A gating mechanism is further used to balance the impact of the TM match on the NMT decoder. Experiment results on the UN corpus demonstrate that when fuzzy matches are higher than 50%, the quality of NMT translation can be significantly improved by over 10 BLEU points.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Luke S. Zettlemoyer
- Graham Neubig
- Marjan Ghazvininejad
- Orhan Firat
- Zhiting Hu
- Ankur Bapna
- Mohit Bansal
- Percy Liang
In Computer Vision and Pattern Recognition
- Ankur Bapna
- Orhan Firat
- Marjan Ghazvininejad
- Luke S. Zettlemoyer
- Graham Neubig
- Olga Vechtomova
- Zhiting Hu
- Rada Mihalcea
In Natural Language Processing
- Luke S. Zettlemoyer
- Graham Neubig
- Marjan Ghazvininejad
- Orhan Firat
- Ankur Bapna
- Zhiting Hu
- Mohit Bansal
- Rada Mihalcea
Citations in the corpus
- Simple and Effective Retrieve-Edit-Rerank Text Generation (2020, background): “, 2018), neural machine translation (NMT) (Gu et al., 2018; Zhang et al., 2018; Cao and Xiong, 2018) and post-editing for NMT (Hokamp, 2017; Dabre et al.”
- Non-Parametric Adaptation for Neural Machine Translation (2019, methodology): “Combined with our architectural improvements, motivated by the target encoder and gated attention from (Cao and Xiong, 2018) and the extended transformer model from (Zhang et al., 2018a), our semi-parametric NMT model is able to out-perform purely neural models in broad multi-domain settings.”
- Neural Fuzzy Repair: Integrating Fuzzy Matches into Neural Machine Translation (2019, methodology): “extra encoder for retrieved TM matches (Cao and Xiong, 2018).”
- Deep Learning for Text Style Transfer: A Survey (2020, background): “(2020), and MSD medical text simplification proposed by Cao et al. (2020), and so on.”