Automatic Extract Product-Entity from Untagged Review

In this paper, we present a new method to extract product entity from Chinese customer reviews. The approach requires no segmentation, no domain dictionary and little prior domain knowledge, which is more suitable for domain with resource-limited. Quite different from the previous work, the proposed method first get the entity candidates use a general version bootstrapping algorithm and then distribute the credits from the seed entities to other entity candidates based on graph's topology structure. Experiments on COAE2008 corpus shows that the method proposed here is effective.