Morphologically-aware vocabulary reduction of word embeddings

• Main Authors: CHIA, Chong Cher, TKACHENKO, Maksim, LAUW, Hady Wirawan
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2023
• 主題: Word embeddings; compression; vocabulary reduction; Databases and Information Systems; Numerical Analysis and Scientific Computing; Theory and Algorithms
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/7608; https://ink.library.smu.edu.sg/context/sis_research/article/8611/viewcontent/wiiat22.pdf

We propose SubText, a compression mechanism via vocabulary reduction. The crux is to judiciously select a subset of word embeddings which support the reconstruction of the remaining word embeddings based on their form alone. The proposed algorithm considers the preservation of the original embedding...