Bootstrapping Named Entity Recognition in E-Commerce with Positive Unlabeled Learning
Hanchu Zhang, Leonhard Hennig, Christoph Alt, Changjian Hu, Yao Meng, Chao Wang
Abstract
In this work, we introduce a bootstrapped, iterative NER model that integrates a PU learning algorithm for recognizing named entities in a low-resource setting. Our approach combines dictionary-based labeling with syntactically-informed label expansion to efficiently enrich the seed dictionaries. Experimental results on a dataset of manually annotated e-commerce product descriptions demonstrate the effectiveness of the proposed framework.- Anthology ID:
- 2020.ecnlp-1.1
- Volume:
- Proceedings of the 3rd Workshop on e-Commerce and NLP
- Month:
- July
- Year:
- 2020
- Address:
- Seattle, WA, USA
- Venue:
- ECNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1–6
- Language:
- URL:
- https://aclanthology.org/2020.ecnlp-1.1
- DOI:
- 10.18653/v1/2020.ecnlp-1.1
- Cite (ACL):
- Hanchu Zhang, Leonhard Hennig, Christoph Alt, Changjian Hu, Yao Meng, and Chao Wang. 2020. Bootstrapping Named Entity Recognition in E-Commerce with Positive Unlabeled Learning. In Proceedings of the 3rd Workshop on e-Commerce and NLP, pages 1–6, Seattle, WA, USA. Association for Computational Linguistics.
- Cite (Informal):
- Bootstrapping Named Entity Recognition in E-Commerce with Positive Unlabeled Learning (Zhang et al., ECNLP 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.ecnlp-1.1.pdf