Sentence Boundary Augmentation For Neural Machine Translation Robustness

Abstract

Neural Machine Translation (NMT) models have demonstrated strong state of the art performance on translation tasks where well-formed training and evaluation data are provided, 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.

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyli2020sentence

Related papers

• Robust Neural Machine Translation For Clean And Noisy Speech Transcripts (2019)0.00
• Segaugment: Maximizing The Utility Of Speech Translation Data With Segmentation-based Augmentations (2022)0.00
• Low-latency Neural Speech Translation (2018)9.03
• Assessing The Tolerance Of Neural Machine Translation Systems Against Speech Recognition Errors (2019)2.26
• Improving Robustness Of Neural Inverse Text Normalization Via Data-augmentation, Semi-supervised Learning, And Post-aligning Method (2023)0.00
• Segaug: Ctc-aligned Segmented Augmentation For Robust Rnn-transducer Based Speech Recognition (2025)3.58
• Subtitles To Segmentation: Improving Low-resource Speech-to-text Translation Pipelines (2020)0.00
• Telephonetic: Making Neural Language Models Robust To ASR And Semantic Noise (2019)0.00