Bootstrapping Named Entity Recognition in E-Commerce with Positive Unlabeled Learning
It addresses the lack of annotated datasets for recognizing novel entity types like products in e-commerce, which is an incremental advancement in domain-specific NER.
The paper tackles the problem of Named Entity Recognition in e-commerce by developing a bootstrapped positive-unlabeled learning algorithm, achieving an average F1 score of 72.02% and improving recall by 4.96% over a baseline.
Named Entity Recognition (NER) in domains like e-commerce is an understudied problem due to the lack of annotated datasets. Recognizing novel entity types in this domain, such as products, components, and attributes, is challenging because of their linguistic complexity and the low coverage of existing knowledge resources. To address this problem, we present a bootstrapped positive-unlabeled learning algorithm that integrates domain-specific linguistic features to quickly and efficiently expand the seed dictionary. The model achieves an average F1 score of 72.02% on a novel dataset of product descriptions, an improvement of 3.63% over a baseline BiLSTM classifier, and in particular exhibits better recall (4.96% on average).