Human evaluation of a German surface realisation ranker

Details

Event 12th Conference of the European Chapter of the Association of Computational Linguistics

Authors

Forst, Martin
Technical Publications
March 30th 2009
In this paper we present a human-based evaluation of surface realisation alternatives. We examine the relative rankings of naturally occurring corpus sentences and automatically generated strings chosen by statistical models (language model, loglinear model), as well as the naturalness of the strings chosen by the log-linear model. We also investigate to what extent preceding context has an effect on choice. We show that native speakers do accept quite some variation in word order, but there are also clearly factors that make certain realisation alternatives more natural.

Citation

Cahill, A.; Forst, M. Human evaluation of a German surface realisation ranker. 12th Conference of the European Chapter of the Association of Computational Linguistics. 2009 March 30 - April 3; Athens, Greece.

Additional information

Focus Areas

Our work is centered around a series of Focus Areas that we believe are the future of science and technology.

FIND OUT MORE
Licensing & Commercialization Opportunities

We’re continually developing new technologies, many of which are available for Commercialization.

FIND OUT MORE
News

PARC scientists and staffers are active members and contributors to the science and technology communities.

FIND OUT MORE