Polarity Calibration for Opinion Summarization
This addresses the challenge of presenting divergent opinions in summarization for applications like product reviews or political analysis, though it is an incremental improvement over existing methods.
The paper tackles the problem of polarity bias in opinion summarization, where models tend to amplify majority opinions and ignore minority ones, by introducing polarity calibration to align output summaries with input text polarity, resulting in improved polarity matching while maintaining content and language quality as shown in evaluations on product reviews and political opinions.
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 of polarity calibration, which aims to align the polarity of output summary with that of input text. Specifically, we develop a reinforcement training approach for polarity calibration. This approach feeds the polarity distance between output summary and input text as reward into the summarizer, and also balance polarity calibration with content preservation and language naturality. We evaluate our Polarity Calibration model (PoCa) on two types of opinions summarization tasks: summarizing product reviews and political opinions articles. Automatic and human evaluation demonstrate that our approach can mitigate the polarity mismatch between output summary and input text, as well as maintain the content semantic and language quality.