Virach Sornlertlamvanich, Hiroki Nomoto, Sunisa Wittayapanyanon, Atsushi Kasuga, Kenji Okano, Wataru Okubo, Yunjin Nam, Yoshimi Miyake, Thuzar Hlaing, Ryuko Taniguchi, Sri Budi Lestari
Virach Sornlertlamvanich, Hiroki Nomoto, Sunisa Wittayapanyanon, Atsushi Kasuga, Kenji Okano, Wataru Okubo, Yunjin Nam, Yoshimi Miyake, Thuzar Hlaing, Ryuko Taniguchi, Sri Budi Lestari
复制标题
Virach Sornlertlamvanich、Hiroki Nomoto、Sunisa Wittayapanyanon、Atsushi Kasuga、Kenji Okano、Wataru Okubo、Yunjin Nam、Yoshimi Miyake、Thuzar Hlaing、Ryuko Taniguchi、Sri Budi Lestari
DOI:
10.1109/icbir54589.2022.9786494
复制
发表时间:
2022
期刊:
影响因子:
--
通讯作者:
Sri Budi Lestari
中科院分区:
文献类型:
--
作者:
Virach Sornlertlamvanich;Hiroki Nomoto;Sunisa Wittayapanyanon;Atsushi Kasuga;Kenji Okano;Wataru Okubo;Yunjin Nam;Yoshimi Miyake;Thuzar Hlaing;Ryuko Taniguchi;Sri Budi Lestari
This paper describes the encoding scheme for pronoun substitutes and address terms in eight Asian languages based on the vocative studies. The target languages are selected according to the availability of the language experts and resources. The nature of pronoun substitutes and address terms expression across the languages can be confirmed by the concepts defined in the WordNet. In this study, a workbench for text data collection (WordList) has been carefully designed to maintain the input data consistency and the semantic linkage between the target languages. The WordList is a web-based application facilitating an online collaborative data input. It maintains the data in MongoDB, and supports JSON and CSV format file exporting for database backup and batch data cleansing for further expression pattern study.