Open Relation Extraction



Research areas


Open relation extraction is a core task in Natural Language Understanding. In natural language, relations are expressed by predicates and their arguments, for example, in the sentence ‘Mary loves science’, love is a predicate and Mary and science are the arguments of the relation. Identifying relations is important for extracting knowledge that is later used in applications as Question Answering, Dialogue Systems, Ontology building, and many others. This project is about using deep learning methods to extract relations from written text. The main challenge of this project is is to build a system that is able to extract multiple relations per sentence.


Familiarity with linear algebra, probability, and basic knowledge of machine learning. Knowledge on deep learning would be a plus. Good coding skills in Python.

Background Literature

  • L. Cui, F. Wei, and M. Zhou, “Neural Open Infomation Extraction,”arXiv preprint arXiv:1805.04270, 2018. [Online]. Available:
  • S. Zhang, K. Duh, B. V. Durme, S. Zhang, K. Duh, and B. V. Durme,“Mt/ie: Cross-lingual open information extraction with neural sequence-to-sequence models,” inConference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers,2017, pp. 64–70
  • S. Zheng, F. Wang, H. Bao, Y. Hao, P. Zhou, and B. Xu, “Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme,” inProceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), vol. 1, 2017,pp. 1227–1236. [Online]. Available:


Gain a good understanding of deep learning models for natural language processing, and learn how to implement and apply these techniques in a research project.


Natural Language Processing, Machine learning, Artificial intelligence.

Updated:  1 June 2019/Responsible Officer:  Dean, CECS/Page Contact:  CECS Marketing