Bootstrapping Named Entity Recognition in E-Commerce with Positive Unlabeled Learning

Hanchu Zhang, Leonhard Hennig, Christoph Alt, Changjian Hu, Yao Meng, Chao Wang

In: Proceedings of the Third Workshop on e-Commerce and NLP. Annual Meeting of the Association for Computational Linguistics (ACL-2020) ECNLP 3 befindet sich ACL 2020 July 9 Seattle Washington United States Association for Computational Linguistics 7/2020.


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 3.6% over a baseline BiLSTM classifier, and in particular exhibits better recall (4.96% on average)


Weitere Links

low_resource_NER.pdf (pdf, 274 KB)

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence