A Hierarchical End-to-End Model for Jointly Improving Text Summarization and Sentiment Classification

Abstract

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 endto-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.

Towards Personalized Review Summarization via User-Aware Sequence Network

“…All these studies focus on review summarization in the multiple review scenario, while our work focuses on personalization issues in single review summarization scenario. Ma et al (2018) is also related to our work, which jointly models review summarization and sentiment classification in an unified framework. However, this work also ignores the effect of users on review summarization, while our task is personalized review summaization and our model can consider the effect of users on review summarization.…”

“…To perform personalized review summarization, we propose a User-aware Sequence Network (USN). USN is based on sequence to sequence models (Seq2Seq), which are popular methods in machine translation (Bahdanau, Cho, and Bengio 2015;Zhao et al 2018), text summarization (Rush, Chopra, and Weston 2015;See, Liu, and Manning 2017; and review summarization (Lu and Wang 2016;Ma et al 2018). Our major updates over standard Seq2Seq are three-fold.…”

Attribute-aware Sequence Network for Review Summarization

“…All of these studies focus on review summarization in the multiple review scenario, while our work focuses on the single review scenario. Recent review summarization studies (Ma et al, 2018;Yang et al, 2018a,b) also focus on the scenario. Ma et al (2018) jointly models review summarization and sentiment classification in a unified framework.…”

Learning Sentiment Memories for Sentiment Modification without Parallel Data

“…The proposed sentiment-memory based autoencoder (Bengio et al, 2009;Ma et al, 2018b) learns the idea of memory network (Weston et al, 2014;Sukhbaatar et al, 2015) but simplifies the process. Our work is also related to the generation tasks (Wang et al, 2017;Liu et al, 2018;Ma et al, 2018a;. These tasks usually generate texts that preserve main information of input texts.…”