Global Inference for aspect and opinion terms co-extraction based on multi-task neural networks

• Main Authors: YU, Jianfei, JIANG, Jing, XIA, Rui
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2019
• Subjects: Benchmark testing; Labeling; Natural language processing; Neural networks; Opinion mining; Sentiment analysis; Standards; Syntactics; Task analysis; Databases and Information Systems; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/4159; https://ink.library.smu.edu.sg/context/sis_research/article/5163/viewcontent/Global_Inference_Aspect_Opinion_2018_afv.pdf
• Institution: Singapore Management University

Extracting aspect terms and opinion terms are two fundamental tasks in opinion mining. The recent success of deep learning has inspired various neural network architectures, which have been shown to achieve highly competitive performance in these two tasks. However, most existing methods fail to exp...