On Using Classical Poetry Structure for Indian Language Post-Processing

Anoop M. Namboodiri, P. J. Narayanan, C. V. Jawahar

Abstract: Post-processors are critical to the performance of lan- guage recognizers like OCRs, speech recognizers, etc. Dictionary-based post-processing commonly employ either an algorithmic approach or a statistical approach. Other linguistic features are not exploited for this purpose. The language analysis is also largely limited to the prose form. This paper proposes a framework to use the rich metric and formal structure of classical poetic forms in Indian lan- guages for post-processing a recognizer like an OCR en- gine. We show that the structure present in the form of the vrtta and pr¯asa can be efficiently used to disambiguate some cases that may be difficult for an OCR. The approach is efficient, and complementary to other post-processing ap- proaches and can be used in conjunction with them.