This paper presents an empirical comparison of two strategies for Vietnamese Part-of-Speech (POS) tagging from unsegmented text: (i) a pipeline strategy where we consider the output of a word segmenter as the input of a POS tagger, and (ii) a joint strategy where we predict a combined segmentation and POS tag for each syllable. We also make a comparison between state-of-the-art (SOTA) feature-based and neural network-based models. On the benchmark Vietnamese treebank (Nguyen et al., 2009), experimental results show that the pipeline strategy produces better scores of POS tagging from unsegmented text than the joint strategy, and the highest accuracy is obtained by using a feature-based model.
From Word Segmentation to POS Tagging for Vietnamese
An empirical comparison of pipeline and joint strategies for Vietnamese POS tagging in unsegmented text finds pipeline approaches outperform joint strategies, with feature-based models achieving the highest accuracy.
- Year
- 2017
- Venue
- from-word-segmentation-to-pos-tagging-for-2
- Authors
- 5
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/1711.04951ARXIV-DEFAULT
- TL;DR
- Semantic Scholar