This repository contains experiments in Vietnamese Chunking problems. It is a part of underthesea project.
Sentences : 7855
Unique words : 14245
Top words : ,, ., ", của, là, và, có, một, người, được, không, đã, những, cho, :, ..., ở, trong, với, đến
POS Tags (28): A, Ab, C, CH, Cb, Cc, E, Eb, I, L, M, Mb, N, Nb, Nc, Np, Nu, Ny, P, Pb, R, T, V, Vb, Vy, X, Y, Z
Chunking Tags (21): B-AP, B-MP, B-NP, B-PP, B-QP, B-TP, B-VP, B-WH, B-WP, B-XP, I-AP, I-MP, I-NP, I-PP, I-QP, I-VP, I-WH , I-WP, I-XP, N-NP, O
Setup Environment
# clone project
$ git clone [email protected]:magizbox/underthesea.chunking.git
# create environment
$ cd underthesea.chunking
$ conda create -n uts.chunking python=3.4
$ pip install -r requirement.txt
Run Experiments
$ cd underthesea.chunking
$ source activate uts.chunking
$ python main.py
- Vietnamese Chunking Tools
- Vietnamese Chunking Publications
- Vietnamese Chunking State of The Art
- Vietnamese Chunking Service
Last update: October 2017