Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary
Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary
Fang, Meng and Cohn, Trevor
2017
Paper summary
tmills
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.
