A Commercial Perspective on Reference

Ehud Baruch Reiter

doi:10.18653/v1/W17-3519

A Commercial Perspective on Reference

Ehud Baruch Reiter

Computing Science

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

3 Citations (Scopus)

Abstract

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 language	English
Title of host publication	Proceedings of The 10th International Natural Language Generation conference
Publisher	ACL
Pages	134-138
DOIs	https://doi.org/10.18653/v1/W17-3519
Publication status	Published - 2017
Event	10th International Natural Language Generation conference - , Spain Duration: 4 Sep 2017 → 7 Sep 2017

Conference

Conference	10th International Natural Language Generation conference
Country/Territory	Spain
Period	4/09/17 → 7/09/17

Access to Document

10.18653/v1/W17-3519Licence: Unspecified

Cite this

@inproceedings{0923e4b5c08c42eea131aae4e8c3ea30,

title = "A Commercial Perspective on Reference",

abstract = "I briefly describe some of the commercial workwhich Arria NLG is doing in referring expressionalgorithms, and highlight differences betweenwhat is commercially important (at leastto Arria) and the NLG research literature. Arria{\textquoteright}sfocus is on high-quality algorithms fortypes of reference which are important in itssystems. These algorithms need to be parametrisablefor different genres and domains,usable in hybrid systems which include somecanned text, and support variation.",

author = "Reiter, {Ehud Baruch}",

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.; 10th International Natural Language Generation conference ; Conference date: 04-09-2017 Through 07-09-2017",

year = "2017",

doi = "10.18653/v1/W17-3519",

language = "English",

pages = "134--138",

booktitle = "Proceedings of The 10th International Natural Language Generation conference",

publisher = "ACL",

}

TY - GEN

T1 - A Commercial Perspective on Reference

AU - Reiter, Ehud Baruch

N1 - 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.

PY - 2017

Y1 - 2017

N2 - I briefly describe some of the commercial workwhich Arria NLG is doing in referring expressionalgorithms, and highlight differences betweenwhat is commercially important (at leastto Arria) and the NLG research literature. Arria’sfocus is on high-quality algorithms fortypes of reference which are important in itssystems. These algorithms need to be parametrisablefor different genres and domains,usable in hybrid systems which include somecanned text, and support variation.

AB - I briefly describe some of the commercial workwhich Arria NLG is doing in referring expressionalgorithms, and highlight differences betweenwhat is commercially important (at leastto Arria) and the NLG research literature. Arria’sfocus is on high-quality algorithms fortypes of reference which are important in itssystems. These algorithms need to be parametrisablefor different genres and domains,usable in hybrid systems which include somecanned text, and support variation.

U2 - 10.18653/v1/W17-3519

DO - 10.18653/v1/W17-3519

M3 - Published conference contribution

SP - 134

EP - 138

BT - Proceedings of The 10th International Natural Language Generation conference

PB - ACL

T2 - 10th International Natural Language Generation conference

Y2 - 4 September 2017 through 7 September 2017

ER -