Sentence Boundary Augmentation For Neural Machine Translation Robustness
| Autor: | Daniel Li, Naveen Arivazhagan, Te I, Colin Cherry, Dirk Padfield |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Sound (cs.SD) Computer Science - Computation and Language Machine translation Computer science Speech recognition Context (language use) Translation (geometry) computer.software_genre Computer Science - Sound Data modeling Machine Learning (cs.LG) Robustness (computer science) Audio and Speech Processing (eess.AS) Speech translation FOS: Electrical engineering electronic engineering information engineering Segmentation computer Computation and Language (cs.CL) Sentence Electrical Engineering and Systems Science - Audio and Speech Processing |
| Zdroj: | ICASSP |
| DOI: | 10.48550/arxiv.2010.11132 |
| Popis: | 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. Comment: 5 pages, 4 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|