Expert-Guided Contrastive Opinion Summarization for Controversial Issues
Jinlong Guo, Yujie Lu, Tatsunori Mori, Catherine L. Blake · 2015
This paper presents a new model for the task of contrastive opinion summarization (COS) particularly for controversial issues. Traditional COS methods, which mainly rely on sentence similarity measures are not sufficient for a complex controversial issue. We therefore propose an Expert-Guided Contrastive Opinion Summarization (ECOS) model. Compared to previous methods, our model can (1) integrate expert opinions with ordinary opinions from social media and (2) better align the contrastive arguments under the guidance of expert prior opinion. We create a new data set about a complex social issue with "sufficient" controversy and experimental results on this data show that the proposed model are effective for (1) producing better arguments summary in understanding a controversial issue and (2) generating contrastive sentence pairs.