Dictionary-based Data Augmentation for Cross-Domain Neural Machine Translation
By Wei Peng, Chongxuan Huang, Tianhao Li, Yun Chen, Qun Liu. 2020
27 citations recorded by the source corpus.
Existing data augmentation approaches for neural machine translation (NMT) have predominantly relied on back-translating in-domain (IND) monolingual corpora. These methods suffer from issues associated with a domain information gap, which leads to translation errors for low frequency and out-of-vocabulary terminology. This paper proposes a dictionary-based data augmentation (DDA) method for cross-domain NMT. DDA synthesizes a domain-specific dictionary with general domain corpora to automatically generate a large-scale pseudo-IND parallel corpus. The generated pseudo-IND data can be used to enhance a general domain trained baseline. The experiments show that the DDA-enhanced NMT models demonstrate consistent significant improvements, outperforming the baseline models by 3.75-11.53 BLEU. The proposed method is also able to further improve the performance of the back-translation based and IND-finetuned NMT models. The improvement is associated with the enhanced domain coverage produced by DDA.
Subfields: Artificial Intelligence, 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
- Varun Prashant Gangal
- Soroush Vosoughi
- Eduard H. Hovy
- Teruko Mitamura
- Jason Wei
- Steven Y. Feng
- Sarath Chandar
- Mohit Bansal
In Natural Language Processing
- Varun Prashant Gangal
- Eduard H. Hovy
- Teruko Mitamura
- Soroush Vosoughi
- Jason Wei
- Steven Y. Feng
- Sarath Chandar
- Mohit Bansal
Citations in the corpus
- A Survey of Data Augmentation Approaches for NLP (2021, methodology): “Peng et al. (2020) Propose dictionary-based DA (DDA) for cross-domain NMT by synthesizing a domain-specific dictionary and automatically generating a pseudo in-domain parallel corpus.”
- Neural Machine Translation for Low-resource Languages: A Survey (2021, unknown): “One solution is to use a bilingual dictionary and replace all the words [137] or rare words [146] in the selected sentences of a monolingual corpus with the words in the other language in order to generate its translation.”