Lightweight and efficient neural natural language processing with quaternion networks

• المؤلفون الرئيسيون: TAY, Yi, ZHANG, Aston, LUU, Anh Tuan, RAO, Jinfeng, ZHANG, Shuai, WANG, Shuohang, FU, Jie, HUI, Siu Cheung
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2019
• الموضوعات: OS and Networks; Programming Languages and Compilers
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/scis_studentpub/2; https://ink.library.smu.edu.sg/context/scis_studentpub/article/1002/viewcontent/P19_1145.pdf

Many state-of-the-art neural models for NLP are heavily parameterized and thus memory inefficient. This paper proposes a series of lightweight and memory efficient neural architectures for a potpourri of natural language processing (NLP) tasks. To this end, our models exploit computation using Quate...