Japanese Sentiment Classification using a Tree-Structured Long Short-Term Memory with Attention
This addresses sentiment analysis for Japanese, an incremental improvement over English-focused methods.
The paper tackled the problem of sentiment classification in Japanese without requiring phrase-level annotated corpora by proposing a tree-structured LSTM with attention, achieving state-of-the-art performance.
Previous approaches to training syntax-based sentiment classification models required phrase-level annotated corpora, which are not readily available in many languages other than English. Thus, we propose the use of tree-structured Long Short-Term Memory with an attention mechanism that pays attention to each subtree of the parse tree. Experimental results indicate that our model achieves the state-of-the-art performance in a Japanese sentiment classification task.