Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary on ShortScience.org

doi.org
sci-hub
scholar.google.com

Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary
Fang, Meng and Cohn, Trevor
Association for Computational Linguistics - 2017 via Local Bibsonomy
Keywords: dblp

Summaries/Notes 1

[link] Summary by Tim Miller 7 years ago

They get multilingual alignments from dictionaries, then train a Bilstm pos tagger in source language, then automatically tag many tokens in the target language, then manually annotate 1000 tokens in target language, then train a system with combined loss over distant tagging and gold tagging. They add an additional output layer that is learned for the gold annotations.

Your comment:

Write your summary here (You can use $\LaTeX$ and markdown syntax):

Anon Private