S²GSL: Incorporating Segment to Syntactic Enhanced Graph Structure Learning for Aspect-based Sentiment Analysis.
Bingfeng ChenQihan OuyangYongqi LuoBoyan XuRuichu CaiZhifeng HaoPublished in: ACL (1) (2024)
Keyphrases
- sentiment analysis
- structure learning
- graphical models
- bayesian networks
- sentiment classification
- sentiment words
- opinion mining
- sentiment lexicon
- conditional independence
- text classification
- sentence level
- markov logic networks
- parameter estimation
- natural language
- directed acyclic graph
- product reviews
- text mining
- transfer learning
- directed graph
- belief propagation
- network structure
- random walk
- natural language processing
- learning algorithm
- maximum likelihood estimation
- markov networks
- machine learning
- probabilistic model
- pairwise
- reinforcement learning
- product features
- knowledge base