[Adapt] [Seminar] Methods for Overlapped and Discontinuous Named Entity Recognition

[王绪凯]

Hi Adapters

Named entity recognition(NER) is one fundamental task for natural language processing. The conventional NER task focus on continuous entities, and widely solved by transformer based model. Recently, Research on overlapped and discontinuous named entity recognition (ODNER) has received increasing attention. 

In this seminar, I will introduce ODNER task and some methods to solve this task. The methods are from three paper: “Recognizing continuous and discontinuous adverse drug reaction mentions from social media using lstm-crf. WCMC, 2018.”, “An Effective Transition-based Model for Discontinuous NER. ACL, 2020”, A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognition. ACL, 2021”.

Hope you enjoy it!

Time: Wed 4:00 pm
Venue: SEIEE 3-414

Best Regards,
Xukai Wang