An Analysis of BPE Vocabulary Trimming in Neural Machine Translation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917626970636288 |
|---|---|
| author | Cognetta, Marco Hiraoka, Tatsuya Okazaki, Naoaki Sennrich, Rico Pinter, Yuval |
| author_facet | Cognetta, Marco Hiraoka, Tatsuya Okazaki, Naoaki Sennrich, Rico Pinter, Yuval |
| contents | We explore threshold vocabulary trimming in Byte-Pair Encoding subword tokenization, a postprocessing step that replaces rare subwords with their component subwords. The technique is available in popular tokenization libraries but has not been subjected to rigorous scientific scrutiny. While the removal of rare subwords is suggested as best practice in machine translation implementations, both as a means to reduce model size and for improving model performance through robustness, our experiments indicate that, across a large space of hyperparameter settings, vocabulary trimming fails to improve performance, and is even prone to incurring heavy degradation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00397 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An Analysis of BPE Vocabulary Trimming in Neural Machine Translation Cognetta, Marco Hiraoka, Tatsuya Okazaki, Naoaki Sennrich, Rico Pinter, Yuval Computation and Language We explore threshold vocabulary trimming in Byte-Pair Encoding subword tokenization, a postprocessing step that replaces rare subwords with their component subwords. The technique is available in popular tokenization libraries but has not been subjected to rigorous scientific scrutiny. While the removal of rare subwords is suggested as best practice in machine translation implementations, both as a means to reduce model size and for improving model performance through robustness, our experiments indicate that, across a large space of hyperparameter settings, vocabulary trimming fails to improve performance, and is even prone to incurring heavy degradation. |
| title | An Analysis of BPE Vocabulary Trimming in Neural Machine Translation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.00397 |