CLApr 2, 2016
Online Updating of Word Representations for Part-of-Speech Tagging
arXiv:1604.00502v121 citations
Originality Synthesis-oriented
AI Analysis
This addresses the need for incremental domain adaptation in natural language processing when batch processing is not feasible, though it appears incremental in method.
The paper tackled the problem of adapting word representations for part-of-speech tagging in an online, unsupervised manner as data arrives, and found that this approach performs as well as batch domain adaptation.
We propose online unsupervised domain adaptation (DA), which is performed incrementally as data comes in and is applicable when batch DA is not possible. In a part-of-speech (POS) tagging evaluation, we find that online unsupervised DA performs as well as batch DA.