R
Ruyang Xu
Researcher at South China Normal University
Publications - 6
Citations - 228
Ruyang Xu is an academic researcher from South China Normal University. The author has contributed to research in topics: Sentiment analysis & Context (language use). The author has an hindex of 3, co-authored 6 publications receiving 77 citations.
Papers
More filters
Journal ArticleDOI
LCF: A Local Context Focus Mechanism for Aspect-Based Sentiment Classification
TL;DR: A Local Context Focus (LCF) mechanism is proposed for aspect-based sentiment classification based on Multi-head Self-Attention (MHSA), and utilizes the Context features Dynamic Mask (CDM) and Context Features Dynamic Weighted (CDW) layers to pay more attention to the local context words.
Journal ArticleDOI
A multi-task learning model for Chinese-oriented aspect polarity classification and aspect term extraction
TL;DR: A multi-task learning model for Chinese-oriented aspect-based sentiment analysis, namely LCF-ATEPC, which equips the capability of extracting aspect term and inferring aspect term polarity synchronously and is effective to analyze both Chinese and English comments simultaneously.
Posted Content
A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term Extraction
TL;DR: Based on the local context focus (LCF) mechanism, this article proposed a multi-task learning model for Chinese-oriented aspect-based sentiment analysis, namely LCF-ATEPC.
Journal ArticleDOI
Multifeature Interactive Fusion Model for Aspect-Based Sentiment Analysis
TL;DR: This work proposes a multifeature interactive fusion model for aspect-based sentiment analysis that has a better performance compared with the baseline models and applies the attention mechanism to calculate fusion weight of features, so that the key features information plays a more significant role in the sentiment analysis.
Journal ArticleDOI
Comprehensive Document Summarization with Refined Self-Matching Mechanism
TL;DR: In this work, the self-matching mechanism is incorporated into the extractive summarization system at the encoder side, which allows theencoder to optimize the encoding information at the global level and effectively improves the memory capacity of conventional LSTM.