@inproceedings{heinzerling-strube-2018-bpemb,
title = "{BPE}mb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages",
author = "Heinzerling, Benjamin and
Strube, Michael",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Hasida, Koiti and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios and
Tokunaga, Takenobu",
booktitle = "Proceedings of the Eleventh International Conference on Language Resources and Evaluation ({LREC} 2018)",
month = may,
year = "2018",
address = "Miyazaki, Japan",
publisher = "European Language Resources Association (ELRA)",
url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/L18-1473/"
}
Markdown (Informal)
[BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages](https://preview.aclanthology.org/jlcl-multiple-ingestion/L18-1473/) (Heinzerling & Strube, LREC 2018)
ACL