Polarity Calibration for Opinion Summarization

arXiv:2404.01706v1 Announce Type: new
Abstract: Opinion summarization is automatically generating summaries from a variety of subjective information, such as product reviews or political opinions. The challenge of opinions summarization lies in presenting divergent or even conflicting opinions. We conduct an analysis of previous summarization models, which reveals their inclination to amplify the polarity bias, emphasizing the majority opinions while ignoring the minority opinions. To address this issue and make the summarizer express both sides of opinions, we introduce the concept …

abstract amplify analysis arxiv bias challenge cs.cl information lies opinion opinions political presenting product product reviews reviews summarization type