Finding entities in language
Entity extraction and classification research at the University of Auckland, using CLAVIN and Stanford NER.
Motivation
Extracting and classifying entities is one way to turn unstructured text into information that software can work with.
Approach
The University of Auckland research internship involved natural-language processing, entity extraction, and classification using CLAVIN and Stanford NER.
What was built
The public record establishes work with these tools and tasks. A detailed account of the dataset and implementation has not yet been added.
Results
No verified numerical results are included in this archive.
Open questions
A fuller note can describe the entity categories, ambiguity cases, and evaluation approach once the source material is available.
References
Exact dates, research artifacts, and references remain to be added.
NLP · Entity extraction · Classification