Literary authorship attribution with phrase-structure fragments

Andreas van Cranenburgh

Literary authorship attribution with phrase-structure fragments

Andreas van Cranenburgh^*

^*Corresponding author for this work

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

13 Citations (Scopus)

68 Downloads (Pure)

Abstract

We present a method of authorship attribution and stylometry that exploits hierarchical information in phrase-structures. Contrary to much previous work in stylometry, we focus on content words rather than function words. Texts are parsed to obtain phrase-structures, and compared with texts to be analyzed. An efficient
tree kernel method identifies common tree fragments among data of known authors and unknown texts. These fragments are then used to identify authors and characterize their styles. Our experiments show that the structural information from fragments provides complementary information to the baseline trigram model

Original language	English
Title of host publication	Proceedings of the NAACL-HLT 2012 Workshop on Computational Linguistics for Literature
Place of Publication	Montréal, Canada
Publisher	Association for Computational Linguistics (ACL)
Pages	59-63
Number of pages	5
Publication status	Published - Jun-2012
Externally published	Yes

Access to Document

Literary authorship attribution with phrase-structure fragmentsFinal publisher's version, 124 KBLicence: CC BY-NC-SA

http://aclweb.org/anthology/W12-2508Licence: CC BY-NC-SA

Handle.net

Persistent link

Cite this

@inproceedings{d0830a72bcca4e69bed0ff5bb522eb76,

title = "Literary authorship attribution with phrase-structure fragments",

abstract = "We present a method of authorship attribution and stylometry that exploits hierarchical information in phrase-structures. Contrary to much previous work in stylometry, we focus on content words rather than function words. Texts are parsed to obtain phrase-structures, and compared with texts to be analyzed. An efficienttree kernel method identifies common tree fragments among data of known authors and unknown texts. These fragments are then used to identify authors and characterize their styles. Our experiments show that the structural information from fragments provides complementary information to the baseline trigram model",

author = "{van Cranenburgh}, Andreas",

note = "Revised version: http://andreasvc.github.io/clfl2012.pdf",

year = "2012",

month = jun,

language = "English",

pages = "59--63",

booktitle = "Proceedings of the NAACL-HLT 2012 Workshop on Computational Linguistics for Literature",

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

}

Literary authorship attribution with phrase-structure fragments. / van Cranenburgh, Andreas.
Proceedings of the NAACL-HLT 2012 Workshop on Computational Linguistics for Literature. Montréal, Canada: Association for Computational Linguistics (ACL), 2012. p. 59-63.

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

TY - GEN

T1 - Literary authorship attribution with phrase-structure fragments

AU - van Cranenburgh, Andreas

N1 - Revised version: http://andreasvc.github.io/clfl2012.pdf

PY - 2012/6

Y1 - 2012/6

N2 - We present a method of authorship attribution and stylometry that exploits hierarchical information in phrase-structures. Contrary to much previous work in stylometry, we focus on content words rather than function words. Texts are parsed to obtain phrase-structures, and compared with texts to be analyzed. An efficienttree kernel method identifies common tree fragments among data of known authors and unknown texts. These fragments are then used to identify authors and characterize their styles. Our experiments show that the structural information from fragments provides complementary information to the baseline trigram model

AB - We present a method of authorship attribution and stylometry that exploits hierarchical information in phrase-structures. Contrary to much previous work in stylometry, we focus on content words rather than function words. Texts are parsed to obtain phrase-structures, and compared with texts to be analyzed. An efficienttree kernel method identifies common tree fragments among data of known authors and unknown texts. These fragments are then used to identify authors and characterize their styles. Our experiments show that the structural information from fragments provides complementary information to the baseline trigram model

M3 - Conference contribution

SP - 59

EP - 63

BT - Proceedings of the NAACL-HLT 2012 Workshop on Computational Linguistics for Literature

PB - Association for Computational Linguistics (ACL)

CY - Montréal, Canada

ER -

Literary authorship attribution with phrase-structure fragments

Abstract

Access to Document

Handle.net

Fingerprint

Cite this