Text Segmentation for Analysing Different Languages

Abstract

Abstract. Over the past several years, researchers have applied different methods of text segmentation. Text segmentation is defined as a method of splitting a document into smaller segments, assuming with its own relevant meaning. Those segments can be classified into the tag, word, sentence, topic, phrase and any information unit. Firstly, this study reviews the different types of text segmentation methods used in different types of documentation, and later discusses the various reasons for utilizing it in opinion mining. The main contribution of this study includes a summarisation of research papers from the past 10 years that applied text segmentation as their main approach in text analysing. Results show that word segmentation was successfully and widely used for processing different languages.

A Chinese ancient book digital humanities research platform to support digital humanities research

“…They regarded that the text segmentation is more important than word segmentation while reading a Chinese ancient text for DH research. Actually, text segmentation will also influence the accuracy of Chinese word segmentation of an ancient text (Pak and Teh, 2016). Therefore, developing a text segmentation scheme with high accuracy for Chinese ancient texts is a more urgent issue than word segmentation, particularly in using the ATAS to support reading Chinese ancient text without punctuations.…”