Non-deterministic attribute selection in reference production

Albert Gatt; Roger van Gompel; Emiel Krahmer; Kees van Deemter

Non-deterministic attribute selection in reference production

Albert Gatt, Roger van Gompel, Emiel Krahmer, Kees van Deemter

Computing Science

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

Abstract

In producing identifying descriptions, speakers often
overspecify and manifest preferences for certain at-
tributes. However, current computational models which
incorporate this observation tend not to make precise
predictions about when and how much speakers do this.
The present paper proposes and evaluates two alter-
native models, based on the results of a new experi-
ment. Unlike current models, the new ones are non-
deterministic and seek to make precise quantitative pre-
dictions about the extent to which speakers overspecify.

Original language	English
Title of host publication	Proceedings of the CogSci workshop Production of Referring Expressions
Place of Publication	Boston
Number of pages	7
Publication status	Published - Jul 2011
Event	CogSci 2011 - Boston, MA, United States Duration: 20 Jul 2011 → 23 Jul 2011

Conference

Conference	CogSci 2011
Country	United States
City	Boston, MA
Period	20/07/11 → 23/07/11

Cite this

Gatt, A., van Gompel, R., Krahmer, E., & van Deemter, K. (2011). Non-deterministic attribute selection in reference production. In Proceedings of the CogSci workshop Production of Referring Expressions

@inproceedings{978cc8e6826441339ad4d8f002f73a78,

title = "Non-deterministic attribute selection in reference production",

abstract = "In producing identifying descriptions, speakers often overspecify and manifest preferences for certain at- tributes. However, current computational models which incorporate this observation tend not to make precise predictions about when and how much speakers do this. The present paper proposes and evaluates two alter- native models, based on the results of a new experi- ment. Unlike current models, the new ones are non- deterministic and seek to make precise quantitative pre- dictions about the extent to which speakers overspecify.",

author = "Albert Gatt and {van Gompel}, Roger and Emiel Krahmer and {van Deemter}, Kees",

year = "2011",

month = jul,

language = "English",

booktitle = "Proceedings of the CogSci workshop Production of Referring Expressions",

note = "CogSci 2011 ; Conference date: 20-07-2011 Through 23-07-2011",

}

TY - GEN

T1 - Non-deterministic attribute selection in reference production

AU - Gatt, Albert

AU - van Gompel, Roger

AU - Krahmer, Emiel

AU - van Deemter, Kees

PY - 2011/7

Y1 - 2011/7

N2 - In producing identifying descriptions, speakers often overspecify and manifest preferences for certain at- tributes. However, current computational models which incorporate this observation tend not to make precise predictions about when and how much speakers do this. The present paper proposes and evaluates two alter- native models, based on the results of a new experi- ment. Unlike current models, the new ones are non- deterministic and seek to make precise quantitative pre- dictions about the extent to which speakers overspecify.

AB - In producing identifying descriptions, speakers often overspecify and manifest preferences for certain at- tributes. However, current computational models which incorporate this observation tend not to make precise predictions about when and how much speakers do this. The present paper proposes and evaluates two alter- native models, based on the results of a new experi- ment. Unlike current models, the new ones are non- deterministic and seek to make precise quantitative pre- dictions about the extent to which speakers overspecify.

M3 - Conference contribution

BT - Proceedings of the CogSci workshop Production of Referring Expressions

CY - Boston

T2 - CogSci 2011

Y2 - 20 July 2011 through 23 July 2011

ER -