Vietnamese punctuation prediction using deep neural networks

• Main Authors: PHAM, Thuy, NGUYEN, Nhu, PHAM, Hong Quang, CAO, Han, NGUYEN, Binh
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2020
• Subjects: Attention model; BiLSTM; Conditional random field; Punctuation prediction; Numerical Analysis and Scientific Computing; South and Southeast Asian Languages and Societies
• Online Access: https://ink.library.smu.edu.sg/sis_research/7817; https://ink.library.smu.edu.sg/context/sis_research/article/8820/viewcontent/VietnamesePunc_av.pdf
• Institution: Singapore Management University

Adding appropriate punctuation marks into text is an essential step in speech-to-text where such information is usually not available. While this has been extensively studied for English, there is no large-scale dataset and comprehensive study in the punctuation prediction problem for the Vietnamese...