Neural name tagging for low-resource languages

Loading...
Thumbnail Image
Authors
Zhang, Boliang
Issue Date
2019-08
Type
Electronic thesis
Thesis
Language
ENG
Keywords
Computer science
Research Projects
Organizational Units
Journal Issue
Alternative Title
Abstract
At last, we investigate training LL name taggers without using any LL annotation. We transfer a name tagger that trained on HL annotations to a LL name tagger via two unsupervised approaches: 1) cross-lingual word embedding where we align monolingual word embedding of HL and LL into a shared space, and 2) cross-lingual language model where instead of aligning word embedding, we project the contextualized word embedding (language model) of HL and LL into a shared space.
Description
August 2019
School of Science
Full Citation
Publisher
Rensselaer Polytechnic Institute, Troy, NY
Terms of Use
Journal
Volume
Issue
PubMed ID
DOI
ISSN
EISSN