Sentence Boundary Augmentation for Neural Machine Translation Robustness
By Daniel Li, Te I, Naveen Arivazhagan, Colin Cherry, Dirk Ryan Padfield. 2020
19 citations recorded by the source corpus.
Neural Machine Translation (NMT) models have demonstrated strong state of the art performance on translation tasks where well-formed training and evaluation data are pro-vided, but they remain sensitive to inputs that include errors of various types. Specifically, in the context of long-form speech translation systems, where the input transcripts come from Automatic Speech Recognition (ASR), the NMT models have to handle errors including phoneme substitutions, grammatical structure, and sentence boundaries, all of which pose challenges to NMT robustness. Through in-depth error analysis, we show that sentence boundary segmentation has the largest impact on quality, and we develop a simple data augmentation strategy to improve segmentation robustness.
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
- Varun Prashant Gangal
- Soroush Vosoughi
- Eduard H. Hovy
- Teruko Mitamura
- Jason Wei
- Steven Y. Feng
- Sarath Chandar
- Mohit Bansal
In Computer Vision and Pattern Recognition
- Jason Wei
- Sarath Chandar
- Eduard H. Hovy
- Steven Y. Feng
- Teruko Mitamura
- Soroush Vosoughi
- Varun Prashant Gangal
- Quoc V. Le
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): “Li et al. (2020b) Propose a diversity DA method for low-resource NMT by generating diverse synthetic parallel data on both source and target sides using a restricted sampling strategy during decoding.”