A natural language generation system must generate expressions
that allow a reader to identify the entities to
which they refer. This paper describes the creation of
referring-expression (RE) generation models developed
using a transformation-based learning approach. We
present an evaluation of the learned models and compare
their performance to the performance of a baseline
system, which always generates full noun phrase REs.
When compared to the baseline system, the learned
models produce REs that lead to more coherent natural
language documents and are more accurate and closer
in length to those that people use.
%0 Conference Paper
%1 conf/flairs/NickersonSG06
%A Nickerson, Jill
%A Shieber, Stuart M.
%A Grosz, Barbara J.
%B FLAIRS Conference
%D 2006
%E Sutcliffe, Geoff
%E Goebel, Randy
%I AAAI Press
%K agents ai artificial discourse expression generation intelligence language learning natural transformation
%P 92-97
%T Referring-Expression Generation Using a Transformation-Based Learning Approach.
%U http://www.eecs.harvard.edu/~nickerso/flairs.pdf
%X A natural language generation system must generate expressions
that allow a reader to identify the entities to
which they refer. This paper describes the creation of
referring-expression (RE) generation models developed
using a transformation-based learning approach. We
present an evaluation of the learned models and compare
their performance to the performance of a baseline
system, which always generates full noun phrase REs.
When compared to the baseline system, the learned
models produce REs that lead to more coherent natural
language documents and are more accurate and closer
in length to those that people use.
@inproceedings{conf/flairs/NickersonSG06,
abstract = {A natural language generation system must generate expressions
that allow a reader to identify the entities to
which they refer. This paper describes the creation of
referring-expression (RE) generation models developed
using a transformation-based learning approach. We
present an evaluation of the learned models and compare
their performance to the performance of a baseline
system, which always generates full noun phrase REs.
When compared to the baseline system, the learned
models produce REs that lead to more coherent natural
language documents and are more accurate and closer
in length to those that people use.},
added-at = {2007-05-11T13:10:15.000+0200},
author = {Nickerson, Jill and Shieber, Stuart M. and Grosz, Barbara J.},
biburl = {https://www.bibsonomy.org/bibtex/27653087ee9b33093023675bb86dbcf29/yish},
booktitle = {FLAIRS Conference},
crossref = {conf/flairs/2006},
date = {2007-02-20},
description = {dblp},
editor = {Sutcliffe, Geoff and Goebel, Randy},
interhash = {a09f526691b5f73c5680b858c049599a},
intrahash = {7653087ee9b33093023675bb86dbcf29},
keywords = {agents ai artificial discourse expression generation intelligence language learning natural transformation},
pages = {92-97},
publisher = {AAAI Press},
timestamp = {2007-05-11T13:10:15.000+0200},
title = {Referring-Expression Generation Using a Transformation-Based Learning Approach.},
url = {http://www.eecs.harvard.edu/~nickerso/flairs.pdf},
year = 2006
}