Graph convolutional networks for exploring authorship hypotheses

Tom Lippincott


Abstract
This work considers a task from traditional literary criticism: annotating a structured, composite document with information about its sources. We take the Documentary Hypothesis, a prominent theory regarding the composition of the first five books of the Hebrew bible, extract stylistic features designed to avoid bias or overfitting, and train several classification models. Our main result is that the recently-introduced graph convolutional network architecture outperforms structurally-uninformed models. We also find that including information about the granularity of text spans is a crucial ingredient when employing hidden layers, in contrast to simple logistic regression. We perform error analysis at several levels, noting how some characteristic limitations of the models and simple features lead to misclassifications, and conclude with an overview of future work.
Anthology ID:
W19-2510
Volume:
Proceedings of the 3rd Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature
Month:
June
Year:
2019
Address:
Minneapolis, USA
Editors:
Beatrice Alex, Stefania Degaetano-Ortlieb, Anna Kazantseva, Nils Reiter, Stan Szpakowicz
Venue:
LaTeCH
SIG:
SIGHUM
Publisher:
Association for Computational Linguistics
Note:
Pages:
76–81
Language:
URL:
https://aclanthology.org/W19-2510
DOI:
10.18653/v1/W19-2510
Bibkey:
Cite (ACL):
Tom Lippincott. 2019. Graph convolutional networks for exploring authorship hypotheses. In Proceedings of the 3rd Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pages 76–81, Minneapolis, USA. Association for Computational Linguistics.
Cite (Informal):
Graph convolutional networks for exploring authorship hypotheses (Lippincott, LaTeCH 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-2510.pdf