Context-Aware Dynamic Word Embeddings for Aspect Term Extraction

• Published in: IEEE transactions on affective computing Vol. 15; no. 1; pp. 144 - 156
• Main Authors: Xu, Jingyun, Xie, Jiayuan, Cai, Yi, Lin, Zehang, Leung, Ho-Fung, Li, Qing, Chua, Tat-Seng
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Ablation; Artificial neural networks; Aspect term extraction; attention mechanism; Context; Context modeling; Data mining; Embedding; Fans; Feature extraction; Portable computers; sentiment analysis; Task analysis; Touch sensitive screens; word embedding

The aspect term extraction (ATE) task aims to extract aspect terms describing a part or an attribute of a product from review sentences. Most existing works rely on either general or domain embedding to address this problem. Despite the promising results, the importance of general and domain embeddi...