KaWAT: A Word Analogy Task Dataset for Indonesian

Code

• github.com/kata-ai/kawat
  OfficialIn papernone★ 0
• github.com/kata-ai/id-word2vec
  OfficialIn papernone★ 0

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.

Tasks

Reproductions