Text simplification for Malay corpus: A Review
Salehah Omar, Juhaida Abu Bakar, Maslinda Mohd Nadzir, Nor Hazlyna Harun, Nooraini Binti Yusoff · 2021
Text Simplification (TS) is one of the directions for recent studies in NLP. The TS aims to rewrite the complicated text into a simpler sentence, which is easier to understand by human and machine. Several applications such as the development of the Simple Wikipedia corpus are derived from those studies. The studies involve a different technique in order to achieve the objective of TS in terms of structure and the meaning of human language. In this paper, we used narrative review as review methodology and highlighted the purpose of TS, TS-user, TS approaches and techniques, datasets, evaluation metrics as well as challenges in formalizing TS in Malay corpus. Promising results are expected for TS in Malay corpus.