A Commercial Perspective on Reference

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

3 Citations (Scopus)


I briefly describe some of the commercial work
which Arria NLG is doing in referring expression
algorithms, and highlight differences between
what is commercially important (at least
to Arria) and the NLG research literature. Arria’s
focus is on high-quality algorithms for
types of reference which are important in its
systems. These algorithms need to be parametrisable
for different genres and domains,
usable in hybrid systems which include some
canned text, and support variation.
Original languageEnglish
Title of host publicationProceedings of The 10th International Natural Language Generation conference
Publication statusPublished - 2017
Event10th International Natural Language Generation conference - , Spain
Duration: 4 Sept 20177 Sept 2017


Conference10th International Natural Language Generation conference

Bibliographical note

Many thanks to the many people on the Arria team
(too many to list here) who have worked on developing,
testing, and documenting the above-mentioned
algorithms. My thanks also to Kees van
Deemter and other members of the Aberdeen University
CLAN research group for their very valuable
advice and suggestions; and to the anonymous reviewers
for their comments and suggestions.

Cite this