A Hierarchical End-to-End Model for Jointly Improving Text Summarization and Sentiment Classification
This work addresses the problem of enhancing both text summarization and sentiment classification simultaneously for applications like review analysis, but it is incremental as it builds on existing joint learning approaches.
The paper tackled the joint improvement of text summarization and sentiment classification by proposing a hierarchical end-to-end model that treats sentiment classification as a further summarization of text summarization output, achieving better performance than strong baselines on Amazon online reviews datasets.
Text summarization and sentiment classification both aim to capture the main ideas of the text but at different levels. Text summarization is to describe the text within a few sentences, while sentiment classification can be regarded as a special type of summarization which "summarizes" the text into a even more abstract fashion, i.e., a sentiment class. Based on this idea, we propose a hierarchical end-to-end model for joint learning of text summarization and sentiment classification, where the sentiment classification label is treated as the further "summarization" of the text summarization output. Hence, the sentiment classification layer is put upon the text summarization layer, and a hierarchical structure is derived. Experimental results on Amazon online reviews datasets show that our model achieves better performance than the strong baseline systems on both abstractive summarization and sentiment classification.