Towards more variation in text generation: Developing and evaluating variation models for choice of referential form

Thiago Castro Ferreira; Emiel Krahmer; Sander Wubben

Towards more variation in text generation: Developing and evaluating variation models for choice of referential form

Thiago Castro Ferreira, Emiel Krahmer, Sander Wubben

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

Abstract

In this study, we introduce a nondeterministic method for referring expression generation. We describe two models that account for individual variation in the choice of referential form in automatically generated text: a Naive Bayes model and a Recurrent Neural Network. Both are evaluated using the VaREG corpus. Then we select the best performing model to generate referential forms in texts from the GREC-2.0 corpus and conduct an evaluation experiment in which humans judge the coherence and comprehensibility of the generated texts, comparing them both with the original references and those produced by a random baseline model.

Original language	English
Title of host publication	Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics
Place of Publication	Berlin, Germany
Publisher	Association for Computational Linguistics (ACL)
Pages	568-577
Number of pages	10
Publication status	Published - Aug 2016
Event	Annual Meeting of the Association for Computational Linguistics 2016 - Berlin, Germany Duration: 7 Aug 2016 → 12 Aug 2016 Conference number: 54 http://acl2016.org/

Conference

Conference	Annual Meeting of the Association for Computational Linguistics 2016
Abbreviated title	ACL 2016
Country/Territory	Germany
City	Berlin
Period	7/08/16 → 12/08/16
Internet address	http://acl2016.org/

Access to Document

https://www.aclweb.org/anthology/P/P16/P16-1054.pdf

Cite this

Castro Ferreira, T., Krahmer, E., & Wubben, S. (2016). Towards more variation in text generation: Developing and evaluating variation models for choice of referential form. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (pp. 568-577). Association for Computational Linguistics (ACL). https://www.aclweb.org/anthology/P/P16/P16-1054.pdf

@inproceedings{8558338331634897a6ade38477c0589b,

title = "Towards more variation in text generation: Developing and evaluating variation models for choice of referential form",

abstract = "In this study, we introduce a nondeterministic method for referring expression generation. We describe two models that account for individual variation in the choice of referential form in automatically generated text: a Naive Bayes model and a Recurrent Neural Network. Both are evaluated using the VaREG corpus. Then we select the best performing model to generate referential forms in texts from the GREC-2.0 corpus and conduct an evaluation experiment in which humans judge the coherence and comprehensibility of the generated texts, comparing them both with the original references and those produced by a random baseline model.",

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

year = "2016",

month = aug,

language = "English",

pages = "568--577",

booktitle = "Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics",

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

note = "Annual Meeting of the Association for Computational Linguistics 2016, ACL 2016 ; Conference date: 07-08-2016 Through 12-08-2016",

url = "http://acl2016.org/",

}

Castro Ferreira, T, Krahmer, E & Wubben, S 2016, Towards more variation in text generation: Developing and evaluating variation models for choice of referential form. in Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (ACL), Berlin, Germany, pp. 568-577, Annual Meeting of the Association for Computational Linguistics 2016, Berlin, Germany, 7/08/16. <https://www.aclweb.org/anthology/P/P16/P16-1054.pdf>

Towards more variation in text generation: Developing and evaluating variation models for choice of referential form. / Castro Ferreira, Thiago; Krahmer, Emiel; Wubben, Sander.
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Berlin, Germany: Association for Computational Linguistics (ACL), 2016. p. 568-577.

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

TY - GEN

T1 - Towards more variation in text generation

T2 - Annual Meeting of the Association for Computational Linguistics 2016

AU - Castro Ferreira, Thiago

AU - Krahmer, Emiel

AU - Wubben, Sander

N1 - Conference code: 54

PY - 2016/8

Y1 - 2016/8

N2 - In this study, we introduce a nondeterministic method for referring expression generation. We describe two models that account for individual variation in the choice of referential form in automatically generated text: a Naive Bayes model and a Recurrent Neural Network. Both are evaluated using the VaREG corpus. Then we select the best performing model to generate referential forms in texts from the GREC-2.0 corpus and conduct an evaluation experiment in which humans judge the coherence and comprehensibility of the generated texts, comparing them both with the original references and those produced by a random baseline model.

AB - In this study, we introduce a nondeterministic method for referring expression generation. We describe two models that account for individual variation in the choice of referential form in automatically generated text: a Naive Bayes model and a Recurrent Neural Network. Both are evaluated using the VaREG corpus. Then we select the best performing model to generate referential forms in texts from the GREC-2.0 corpus and conduct an evaluation experiment in which humans judge the coherence and comprehensibility of the generated texts, comparing them both with the original references and those produced by a random baseline model.

UR - https://ilk.uvt.nl/~tcastrof/acl2016/

M3 - Conference contribution

SP - 568

EP - 577

BT - Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics

PB - Association for Computational Linguistics (ACL)

CY - Berlin, Germany

Y2 - 7 August 2016 through 12 August 2016

ER -

Towards more variation in text generation: Developing and evaluating variation models for choice of referential form

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this