Radical-level Ideograph Encoder for RNN-based Sentiment Analysis of Chinese and Japanese
This provides a cost-effective solution for sentiment analysis in non-alphabetic languages, though it is incremental as it builds on existing CNN and RNN methods.
The paper tackled the large vocabulary problem in Chinese and Japanese sentiment analysis by using radical embeddings instead of character or word embeddings, achieving results close to state-of-the-art with 90% smaller vocabulary and significant parameter reductions (e.g., at least 13% fewer than character-based models).
The character vocabulary can be very large in non-alphabetic languages such as Chinese and Japanese, which makes neural network models huge to process such languages. We explored a model for sentiment classification that takes the embeddings of the radicals of the Chinese characters, i.e, hanzi of Chinese and kanji of Japanese. Our model is composed of a CNN word feature encoder and a bi-directional RNN document feature encoder. The results achieved are on par with the character embedding-based models, and close to the state-of-the-art word embedding-based models, with 90% smaller vocabulary, and at least 13% and 80% fewer parameters than the character embedding-based models and word embedding-based models respectively. The results suggest that the radical embedding-based approach is cost-effective for machine learning on Chinese and Japanese.