Generating flexible proper name references in text: Data, models and evaluation

Thiago Castro Ferreira; Emiel Krahmer; Sander Wubben

Generating flexible proper name references in text: Data, models and evaluation

Thiago Castro Ferreira
, Emiel Krahmer
, Sander Wubben

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Abstract

This study introduces a statistical model able to generate variations of a proper name, taking into account the person to be mentioned, the discourse context and individual variation. The model relies on the REGnames corpus, a dataset with 53,102 proper name references to 1,000 people in different discourse contexts. We evaluate the versions of our model in the perspective of how human writers produce proper names, and also how human readers process them.

Original language	English
Title of host publication	Proceedings of the European Chapter of the Association for Computational Linguistics
Subtitle of host publication	EACL 2017
Publisher	Association for Computational Linguistics (ACL)
Publication status	Published - 1 Apr 2017
Event	European Chapter of the Association for Computational Linguistics 2017 - Valencia, Spain Duration: 3 Apr 2017 → 7 Apr 2017 Conference number: 15 http://eacl2017.org/

Conference

Conference	European Chapter of the Association for Computational Linguistics 2017
Abbreviated title	EACL 2017
Country/Territory	Spain
City	Valencia
Period	3/04/17 → 7/04/17
Internet address	http://eacl2017.org/

Access to Document

https://www.aclweb.org/anthology/E/E17/E17-1062.pdf

Cite this

@inproceedings{608677e426e0424b8e9d1fcfaa0ea0ed,

title = "Generating flexible proper name references in text: Data, models and evaluation",

abstract = "This study introduces a statistical model able to generate variations of a proper name, taking into account the person to be mentioned, the discourse context and individual variation. The model relies on the REGnames corpus, a dataset with 53,102 proper name references to 1,000 people in different discourse contexts. We evaluate the versions of our model in the perspective of how human writers produce proper names, and also how human readers process them.",

author = "\{Castro Ferreira\}, Thiago and Emiel Krahmer and Sander Wubben",

year = "2017",

month = apr,

day = "1",

language = "English",

booktitle = "Proceedings of the European Chapter of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics (ACL)",

note = "European Chapter of the Association for Computational Linguistics 2017, EACL 2017 ; Conference date: 03-04-2017 Through 07-04-2017",

url = "http://eacl2017.org/",

}

Castro Ferreira, T, Krahmer, E & Wubben, S 2017, Generating flexible proper name references in text: Data, models and evaluation. in Proceedings of the European Chapter of the Association for Computational Linguistics: EACL 2017. Association for Computational Linguistics (ACL), European Chapter of the Association for Computational Linguistics 2017, Valencia, Spain, 3/04/17. <https://www.aclweb.org/anthology/E/E17/E17-1062.pdf>

Generating flexible proper name references in text: Data, models and evaluation. / Castro Ferreira, Thiago; Krahmer, Emiel; Wubben, Sander.
Proceedings of the European Chapter of the Association for Computational Linguistics: EACL 2017. Association for Computational Linguistics (ACL), 2017.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Generating flexible proper name references in text

T2 - European Chapter of the Association for Computational Linguistics 2017

AU - Castro Ferreira, Thiago

AU - Krahmer, Emiel

AU - Wubben, Sander

N1 - Conference code: 15

PY - 2017/4/1

Y1 - 2017/4/1

N2 - This study introduces a statistical model able to generate variations of a proper name, taking into account the person to be mentioned, the discourse context and individual variation. The model relies on the REGnames corpus, a dataset with 53,102 proper name references to 1,000 people in different discourse contexts. We evaluate the versions of our model in the perspective of how human writers produce proper names, and also how human readers process them.

AB - This study introduces a statistical model able to generate variations of a proper name, taking into account the person to be mentioned, the discourse context and individual variation. The model relies on the REGnames corpus, a dataset with 53,102 proper name references to 1,000 people in different discourse contexts. We evaluate the versions of our model in the perspective of how human writers produce proper names, and also how human readers process them.

M3 - Conference contribution

BT - Proceedings of the European Chapter of the Association for Computational Linguistics

PB - Association for Computational Linguistics (ACL)

Y2 - 3 April 2017 through 7 April 2017

ER -

Generating flexible proper name references in text: Data, models and evaluation

Abstract

Conference

Access to Document

Fingerprint

Cite this