CER: Complementary Entity Recognition via Knowledge Expansion on Large Unlabeled Product Reviews
This addresses the need for customers to identify compatible products in e-commerce, but it is incremental as it builds on unsupervised techniques for a specific domain.
The paper tackles the problem of Complementary Entity Recognition (CER) from product reviews by proposing an unsupervised method that uses syntactic dependency paths and expands domain knowledge with seed verbs, achieving effective results on 7 popular products with about 1200 reviews.
Product reviews contain a lot of useful information about product features and customer opinions. One important product feature is the complementary entity (products) that may potentially work together with the reviewed product. Knowing complementary entities of the reviewed product is very important because customers want to buy compatible products and avoid incompatible ones. In this paper, we address the problem of Complementary Entity Recognition (CER). Since no existing method can solve this problem, we first propose a novel unsupervised method to utilize syntactic dependency paths to recognize complementary entities. Then we expand category-level domain knowledge about complementary entities using only a few general seed verbs on a large amount of unlabeled reviews. The domain knowledge helps the unsupervised method to adapt to different products and greatly improves the precision of the CER task. The advantage of the proposed method is that it does not require any labeled data for training. We conducted experiments on 7 popular products with about 1200 reviews in total to demonstrate that the proposed approach is effective.