Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

portfolio

publications

A bag-of-concepts model improves relation extraction in a narrow knowledge domain with limited data.

Published in In Proceedings of the 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Student Research Workshop (NAACL-HLT SRW), Minneapolis, 2019, 2019

This paper focuses on a traditional relation ex- traction task in the context of limited annotated data and a narrow knowledge domain. We ex- plore this task with a clinical corpus consisting of 200 breast cancer follow-up treatment let- ters in which 16 distinct types of relations are annotated. We experiment with an approach to extracting typed relations called window- bounded co-occurrence (WBC), which uses an adjustable context window around entity men- tions of a relevant type, and compare its per- formance with a more typical intra-sentential co-occurrence baseline. We further introduce a new bag-of-concepts (BoC) approach to fea- ture engineering based on the state-of-the-art word embeddings and word synonyms. We demonstrate the competitiveness of BoC by comparing with methods of higher complex- ity, and explore its effectiveness on this small dataset.

Recommended citation: Jiyu Chen, Karin Verspoor, and Zenan Zhai. "A Bag-of-concepts Model Improves Relation Extraction in a Narrow Knowledge Domain with Limited Data." Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop. 2019. https://www.aclweb.org/anthology/N19-3007.pdf

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.