TU Darmstadt / ULB / TUbiblio

A Generic Authorship Verification Scheme Based on Equal Error Rates (Notebook for PAN at CLEF 2015)

Halvani, Oren and Winter, Christian
Cappellato, Linda and Ferro, Nicola and Jones, Gareth and Juan, Eric San (eds.) (2015):
A Generic Authorship Verification Scheme Based on Equal Error Rates (Notebook for PAN at CLEF 2015).
In: CLEF2015 Working Notes, Working Notes of CLEF 2015 – Conference and Labs of the Evaluation forum, Toulouse, France, September 8–11, 2015, Sun SITE Central Europe, Toulouse, France, In: CEUR Workshop Proceedings, Vol-1391, [Conference or Workshop Item]

Abstract

We present a generic authorship verification scheme for the PAN-2015 identification task. Our scheme uses a two-step training phase on the training corpora. The first phase learns individual feature category parameters as well as decision thresholds based on equal error rates. The second phase builds feature category ensembles which are used for majority vote decisions because ensembles can outperform single feature categories. All feature categories used in our method are very simple to gain multiple advantages: Our method is entirely independent of any external linguistic resources (even word lists), and hence it can easily be applied to many languages. Moreover, the classification is very fast due to simple features. Additionally, we make use of parallelization. The evaluation of our scheme on a 40% split (which we did not use for training) of the official PAN-2015 training corpus led to an average corpus accuracy of 68.12%; in detail 60% for the Dutch, 67.5% for the English, 60% for the Greek and 85% for the Spanish subcorpus. The overall computation runtime was approximately 27 seconds.

Item Type: Conference or Workshop Item
Erschienen: 2015
Editors: Cappellato, Linda and Ferro, Nicola and Jones, Gareth and Juan, Eric San
Creators: Halvani, Oren and Winter, Christian
Title: A Generic Authorship Verification Scheme Based on Equal Error Rates (Notebook for PAN at CLEF 2015)
Language: ["languages_typename_1" not defined]
Abstract:

We present a generic authorship verification scheme for the PAN-2015 identification task. Our scheme uses a two-step training phase on the training corpora. The first phase learns individual feature category parameters as well as decision thresholds based on equal error rates. The second phase builds feature category ensembles which are used for majority vote decisions because ensembles can outperform single feature categories. All feature categories used in our method are very simple to gain multiple advantages: Our method is entirely independent of any external linguistic resources (even word lists), and hence it can easily be applied to many languages. Moreover, the classification is very fast due to simple features. Additionally, we make use of parallelization. The evaluation of our scheme on a 40% split (which we did not use for training) of the official PAN-2015 training corpus led to an average corpus accuracy of 68.12%; in detail 60% for the Dutch, 67.5% for the English, 60% for the Greek and 85% for the Spanish subcorpus. The overall computation runtime was approximately 27 seconds.

Title of Book: CLEF2015 Working Notes, Working Notes of CLEF 2015 – Conference and Labs of the Evaluation forum, Toulouse, France, September 8–11, 2015
Series Name: CEUR Workshop Proceedings
Volume: Vol-1391
Publisher: Sun SITE Central Europe
Uncontrolled Keywords: Secure Data;authorship verification, equal error rates, intrinsic
Divisions: LOEWE > LOEWE-Zentren > CASED – Center for Advanced Security Research Darmstadt
LOEWE > LOEWE-Zentren
LOEWE
Event Location: Toulouse, France
Date Deposited: 30 Dec 2016 20:23
Identification Number: TUD-CS-2015-12073
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item