Tools: Natural Language Programming

From MarineLives
Revision as of 07:08, January 3, 2018 by ColinGreenstreet (Talk | contribs) (Created page with "File:Named Entities In Court 2014.JPG|500px|thumb|left|[https://www.academia.edu/6551336/Dominique_Ritze_Caecilia_Zirn_Colin_Greenstreet_Kai_Eckert_Simone_Paolo_Ponzetto_Nam...")

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

The MarineLives wiki contains nearly six million words of semi-diplomatically transcribed early and mid-C17th text. This is one of the larger collections of text derived from C17th manuscript sources, and is certainly the largest English language collection derived from early and mid C17th legal sources.

In 2014, MarineLives collaborated with a team at the University of Mannheim Informatics Department, led by Professor Kai Eckert, to explore the application of Natural Language Programming to the MarineLives corpus.

The output of this collaboration was a paper given in Reykjavik at a workshop on Language Resources and Technologies for Processing and Linking Historical Documents and Archives in association with the LREC Conference, May 2014.