Supervised Complementary Entity Recognition with Augmented Key-value Pairs of Knowledge
This work addresses the extraction of complementary entities in product reviews for sentiment analysis, but it appears incremental as it builds on existing CRF methods with knowledge augmentation.
The paper tackled the problem of Complementary Entity Recognition (CER) in sentiment analysis by proposing a supervised sequence labeling method that expands domain knowledge from unlabeled reviews, resulting in improved performance as demonstrated in experiments.
Extracting opinion targets is an important task in sentiment analysis on product reviews and complementary entities (products) are one important type of opinion targets that may work together with the reviewed product. In this paper, we address the problem of Complementary Entity Recognition (CER) as a supervised sequence labeling with the capability of expanding domain knowledge as key-value pairs from unlabeled reviews, by automatically learning and enhancing knowledge-based features. We use Conditional Random Field (CRF) as the base learner and augment CRF with knowledge-based features (called the Knowledge-based CRF or KCRF for short). We conduct experiments to show that KCRF effectively improves the performance of supervised CER task.