KaWAT: A Word Analogy Task Dataset for Indonesian
Computation and Language
2019-06-25 v1
Abstract
We introduced KaWAT (Kata Word Analogy Task), a new word analogy task dataset for Indonesian. We evaluated on it several existing pretrained Indonesian word embeddings and embeddings trained on Indonesian online news corpus. We also tested them on two downstream tasks and found that pretrained word embeddings helped either by reducing the training epochs or yielding significant performance gains.
Cite
@article{arxiv.1906.09912,
title = {KaWAT: A Word Analogy Task Dataset for Indonesian},
author = {Kemal Kurniawan},
journal= {arXiv preprint arXiv:1906.09912},
year = {2019}
}
Comments
Extended abstract