Abstract
Close
| Matthias Gallé |
| Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP), Hong Kong, 3-7 November, 2019 |
@inproceedings{galle2019investigating,
title={Investigating the Effectiveness of BPE: The Power of Shorter Sequences},
author={Gall{\'e}, Matthias},
booktitle={Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)},
pages={1375--1381},
year={2019}
}Abstract
Byte-Pair Encoding (BPE) is an unsupervised sub-word tokenization technique, commonly used in neural machine translation and other NLP tasks. Its effectiveness makes it a de facto standard, but the reasons for this are not well understood. We link BPE to the broader family of dictionary-based compression algorithms and compare it with other members of this family. Our experiments across datasets, language pairs, translation models, and vocabulary size show that – given a fixed vocabulary size budget – the fewer tokens an algorithm needs to cover the test set, the better the translation (as measured by BLEU).
