Home

Automatic Identification of Errors in Arabic Handwriting Recognition

Nizar Y. Habash; Ryan M. Roth

Title:
Automatic Identification of Errors in Arabic Handwriting Recognition
Author(s):
Habash, Nizar Y.
Roth, Ryan M.
Date:
Type:
Technical reports
Department:
Center for Computational Learning Systems
Permanent URL:
Series:
CCLS Technical Report
Part Number:
CCLS-10-02
Publisher:
Center for Computational Learning Systems, Columbia University
Publisher Location:
New York
Abstract:
Arabic handwriting recognition (HR) is a challenging problem due to Arabic's connected letter forms, consonantal diacritics and rich morphology. In this paper we isolate the task of identification of erroneous words in HR from the task of producing corrections for these words. We consider a variety of linguistic (morphological and syntactic) and non-linguistic features to automatically identify these errors. We also consider a learning curve varying in two dimensions: number of segments and number of n-best hypotheses to train on. We additionally evaluate the performance on different test sets with different degrees of errors in them. Our best approach achieves a roughly ~20% absolute increase in F-score over a simple but reasonable baseline. A detailed error analysis shows that linguistic features, such as lemma models, help improve HR-error detection precisely where we expect them to: semantically inconsistent error words.
Subject(s):
Computer science
Artificial intelligence
Item views:
439
Metadata:
text | xml

In Partnership with the Center for Digital Research and Scholarship at Columbia University Libraries/Information Services | Terms of Use