Attribute Selection for Referring Expression Generation: New Algorithms and Evaluation Methods

  title={Attribute Selection for Referring Expression Generation: New Algorithms and Evaluation Methods},
  author={Albert Gatt and Anja Belz},
Referring expression generation has recently been the subject of the first Shared Task Challenge in NLG. In this paper, we analyse the systems that participated in the Challenge in terms of their algorithmic properties, comparing new techniques to classic ones, based on results from a new human task-performance experiment and from the intrinsic measures that were used in the Challenge. We also consider the relationship between different evaluation methods, showing that extrinsic taskperformance… CONTINUE READING
Highly Cited
This paper has 20 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.
Showing 1-10 of 14 extracted citations

On the Limits of Sentence Compression by Deletion

Empirical Methods in Natural Language Generation • 2010
View 10 Excerpts
Highly Influenced

Generating a variety of expressions from visual information and user-designated viewpoints

2013 International Joint Conference on Awareness Science and Technology & Ubi-Media Computing (iCAST 2013 & UMEDIA 2013) • 2013
View 1 Excerpt


Publications referenced by this paper.
Showing 1-9 of 9 references

The Attribute Selection

A. Belz, A. Gatt
View 3 Excerpts
Highly Influenced

Overspecification in Instructive Texts

A. Arts
Artificial Intelligence, • 2004
View 7 Excerpts
Highly Influenced

Generating Minimal Definite Descriptions

ACL • 2002
View 6 Excerpts
Highly Influenced

Incremental speech

831–836. Thomas Pechmann
View 6 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…