2012 · 20 citations · 24 references
Language StudiesArabicComputer ScienceComputational LinguisticsMorphologyNatural Language ProcessingMorphological AnalysisMorphological ParsingMorphological SegmentationAccuracyMaximum-likelihood DecodingModern Standard ArabicSegmentationUnsupervised Morphological Segmentation
If unsupervised morphological analyzers could approach the effectiveness of supervised 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-theart Arabic-to-English MT system. We apply maximum marginal decoding to the unsupervised 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 supervised MSA segmenter. 1
24
Statistical Significance Tests for Machine Translation Evaluation.
Philipp Koehn · 2004 · 1.5K citations
Philipp Koehn, Hieu Hoang · Edinburgh Research Explorer (University of Edinburgh) · 2007 · 510 citations · Full text