Referring-expression generation using a transformation-based learning approach

DSpace/Manakin Repository

Referring-expression generation using a transformation-based learning approach

Citable link to this page

 

 
Title: Referring-expression generation using a transformation-based learning approach
Author: Nickerson, Jill; Shieber, Stuart ORCID  0000-0002-7733-8195 ; Grosz, Barbara

Note: Order does not necessarily reflect citation order of authors.

Citation: Jill Nickerson, Stuart M. Shieber, and Barbara J. Grosz. Referring-expression generation using a transformation-based learning approach. In Proceedings of the 19th International FLAIRS Conference, Melbourne Beach, FL, 11-13 May 2006.
Full Text & Related Files:
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.
Published Version: http://www.aaai.org/Library/FLAIRS/2006/flairs06-016.php
Terms of Use: This article is made available under the terms and conditions applicable to Other Posted Material, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#LAA
Citable link to this page: http://nrs.harvard.edu/urn-3:HUL.InstRepos:2252608
Downloads of this work:

Show full Dublin Core record

This item appears in the following Collection(s)

 
 

Search DASH


Advanced Search
 
 

Submitters