Generative Modeling of Entity Comparisons in Text

Users frequently rely on online reviews for decision making. In addition to allowing users to evaluate the quality of individual products, reviews also support comparison shopping. One key user activity is to compare two (or more) products based on a specific aspect. However, making a comparison across two different reviews, written by different authors, is not always equitable due to the different standards and preferences of individual authors. Therefore, we focus instead on comparative sentences, whereby two products are compared directly by a review author within a single sentence. We study the problem of comparative relation mining. Given a set of comparative sentences, each relating a pair of entities, our objective is two-fold: to interpret the comparative direction in each sentence, and to determine the relative merits of each entity. This requires mining comparative relations at two levels of resolution: at the sentence level, as well as at the entity level. Our key observation is that there is significant synergy between the two levels. We therefore propose a generative model for comparative text, which jointly models comparative directions at the sentence level, and ranking at the entity level. This model is tested comprehensively on Amazon reviews dataset with good empirical outperformance over the state-of-the-art baselines.