BPEmb: Pre-trained Subword Embeddings in 275 Languages (LREC 2018)

Thumbnail
Author
Metadata
Show full item record
Export
Text
BibTex
DataCite XML
JSON

Description

BPEmb is a collection of pre-trained subword unit embeddings in 275 languages, based on Byte-Pair Encoding (BPE). In an evaluation using fine-grained entity typing as testbed, BPEmb performs competitively, and for some languages better than alternative subword approaches, while requiring vastly fewer resources and no tokenization.

Subject

Computer and Information Science;subword embeddings;byte-pair encoding;multilingual

URI

https://doi.org/10.11588/data/V9CXPR

Collections