Improved Arabic Base Phrase Chunking with a new enriched POS tag set

Base Phrase Chunking (BPC) or shallow syntactic parsing is proving to be a task of interest to many natural language processing applications. In this paper, A BPC system is introduced that improves over state of the art performance in BPC using a new part of speech tag (POS) set. The new POS tag set, ERTS, reflects some of the morphological features specific to Modern Standard Arabic. ERTS explicitly encodes definiteness, number and gender information increasing the number of tags from 25 in the standard LDC reduced tag set to 75 tags. For the BPC task, we introduce a more language specific set of definitions for the base phrase annotations. We employ a support vector machine approach for both the POS tagging and the BPC processes. The POS tagging performance using this enriched tag set, ERTS, is at 96.13% accuracy. In the BPC experiments, we vary the feature set along two factors: the POS tag set and a set of explicitly encoded morphological features. Using the ERTS POS tagset, BPC achieves the highest overall Fβ=1 of 96.33% on 10 different chunk types outperforming the use of the standard POS tag set even when explicit morphological features are present.