Paper: Unsupervised Morphology Rivals Supervised Morphology for Arabic MT

ACL ID P12-2063
Title Unsupervised Morphology Rivals Supervised Morphology for Arabic MT
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2012
Authors

If unsupervised morphological analyzers could approach the effectiveness of super- vised ones, they would be a very attractive choice for improving MT performance on low-resource inflected languages. In this paper, we compare performance gains for state-of-the-art supervised vs. unsupervised morphological analyzers, using a state-of-the- art Arabic-to-English MT system. We apply maximum marginal decoding to the unsu- pervised analyzer, and show that this yields the best published segmentation accuracy for Arabic, while also making segmentation output more stable. Our approach gives an 18% relative BLEU gain for Levantine dialectal Arabic. Furthermore, it gives higher gains for Modern Standard Arabic (MSA), as measured on NIST MT-08, than does MADA (Habash and Rambow, 2005), a leading super...