University of Cambridge > Talks.cam > NLIP Seminar Series > Frontiers in Named Entity Recognition and Linking

Frontiers in Named Entity Recognition and Linking

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Tamara Polajnar.

Recognising mentions of entities in texts, and grounding these into entries in external knowledge bases (e.g. DBpedia), provides a means of describing document semantics and enabling search and indexing for specific concepts and ideas. These tasks, referred to as Named Entity Recognition and Named Entity Linking, have been well-studied in many text domains and genres. In the modern text processing environment, in contrast to dealing with named entities in formal or heavily structured documents such as newswire and official reports, we now deal with very large volumes of uncurated text from sources such as social media, which poses broad and challenging problems in NLP research.

In this talk, we will discuss current issues in social media NLP , and report on new research in both named entity recognition and linking in this genre, detailing specific problem areas and demonstrating new solutions.

This talk is part of the NLIP Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2018 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity