2000 character limit reached
KaWAT: A Word Analogy Task Dataset for Indonesian
Published 17 Jun 2019 in cs.CL | (1906.09912v1)
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.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.