FLORS is a part-of-speech tagger that is fast in training and tagging, uses local context only, performs robustly on target domains in unsupervised domain adaptation and is simple in architecture and feature representation.
You can download two different versions of FLORS: one is the original version (Schnabel & Schütze 2014) based on batch learning, one is the modified version (Yin, Schnabel, Schütze 2015) that performs online representation learning (i.e., domain adaptation is performed by incrementally adapting word representations to the new domain).
On this page you can find links to the source code, usage instructions, pretrained models, and the supplementary results on test sets of SANCL.
EMNLP'2015, Wenpeng Yin, Tobias Schnabel and Hinrich Schütze. Online Updating of Word Representations for Part-of-Speech Taggging (bib)
Contact: Wenpeng Yin (email@example.com)
For Original FLORS: