Fetching the paper…

Reading the bibliography…

2010

Algorithmic Detection of Computer Generated Text

Lavoie, Allen, Krishnamoorthy, Mukkai

Original
PDF
Post on X

Understand

Computer generated academic papers have been used to expose a lack of thorough human review at several computer science conferences.

We assess the problem of classifying such documents.
After identifying and evaluating several quantifiable features of academic papers, we apply methods from machine learning to build a binary classifier.
In tests with two hundred papers, the resulting classifier correctly labeled papers either as human written or as computer generated with no false classifications of computer generated papers as human and a 2% false classification rate for human papers as computer generated.

Algorithmic Detection of Computer Generated Text · Around

Built on

Nearest neighbor pattern classification
T. Cover and P. Hart · 1967
Earlier work this paper cites.
Data structures and algorithms for nearest neighbor search in general metric spaces
Peter N. Yianilos · 1993
Earlier work this paper cites.
Support-vector networks
Corinna Cortes and Vladimir Vapnik · 1995
Earlier work this paper cites.

Similar

An algorithm to compute semantic metric in the sd-form semantics model
Eiji Kawaguchi, Seiichiro Kamata, Masahiro Wakiyama, and Koichi Nozaki · 1995
Cited alongside, same era.
Nltk: The natural language toolkit
Edward Loper and Steven Bird · 2002
Cited alongside, same era.
http://arxiv.org/
ArXiv e-print archive
Cited in the paper.
Scigen: An automatic cs paper generator
Jeremy Stribling, Max Krohn, and Dan Aguayo
Cited in the paper.

Then

Parallel structurally-symmetric sparse matrix-vector products on multi-core processors
Vicente H. F. Batista, George O. Ainsworth Jr., and Fernando L. B. Ribeiro · 2010
Closest in time.
The Langlands-Kottwitz approach for the modular curve
P. Scholze · 2010
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…