@inproceedings{galle-2019-investigating,
title = "Investigating the Effectiveness of {BPE}: The Power of Shorter Sequences",
author = "Gall{\'e}, Matthias",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
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)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1141",
doi = "10.18653/v1/D19-1141",
pages = "1375--1381",
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).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="galle-2019-investigating">
<titleInfo>
<title>Investigating the Effectiveness of BPE: The Power of Shorter Sequences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Gallé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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).</abstract>
<identifier type="citekey">galle-2019-investigating</identifier>
<identifier type="doi">10.18653/v1/D19-1141</identifier>
<location>
<url>https://aclanthology.org/D19-1141</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>1375</start>
<end>1381</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating the Effectiveness of BPE: The Power of Shorter Sequences
%A Gallé, Matthias
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F galle-2019-investigating
%X 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).
%R 10.18653/v1/D19-1141
%U https://aclanthology.org/D19-1141
%U https://doi.org/10.18653/v1/D19-1141
%P 1375-1381
Markdown (Informal)
[Investigating the Effectiveness of BPE: The Power of Shorter Sequences](https://aclanthology.org/D19-1141) (Gallé, EMNLP-IJCNLP 2019)
ACL
- Matthias Gallé. 2019. Investigating the Effectiveness of BPE: The Power of Shorter Sequences. In 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, Hong Kong, China. Association for Computational Linguistics.