Semi-Automatic Alignment of Multilingual Parts of Speech Tagsets

Abstract

This paper proposes cast the problem of mapping a pair of Parts of Speech (POS) tagsets as a labelled tree mapping problem and present a general-purpose semi-automatic POS tree alignment algorithm to solve the alignment. This algorithm can be used to align two POS tagsets of different languages or the same language. We evaluate its usefulness using POS tagsets of two languages: Tamil and Sinhala. The proposed approach shows that manual effort in prior approaches is drastically reduced due to the proposed algorithm and eliminates the need to create new POS tagsets.