Sentiment Analysis with Contextual Embeddings and Self-Attention
This work addresses sentiment analysis for multiple languages, including morphologically rich ones, but appears incremental as it builds on existing contextual embedding techniques.
The authors tackled sentiment analysis by proposing a method using contextual embeddings and self-attention, achieving results comparable to or better than state-of-the-art models across three languages including Polish and German.
In natural language the intended meaning of a word or phrase is often implicit and depends on the context. In this work, we propose a simple yet effective method for sentiment analysis using contextual embeddings and a self-attention mechanism. The experimental results for three languages, including morphologically rich Polish and German, show that our model is comparable to or even outperforms state-of-the-art models. In all cases the superiority of models leveraging contextual embeddings is demonstrated. Finally, this work is intended as a step towards introducing a universal, multilingual sentiment classifier.