id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_ylcltxmpvvdbdmljbf3fmued3q	Karthik Narasimhan	An Unsupervised Method for Uncovering Morphological Chains	2015	12	.pdf	application/pdf	6464	664	63	model for unsupervised morphological analysis that integrates orthographic and semantic views of words. We model word formation in terms of morphological chains, from log-linear models with morpheme and wordlevel features to predict possible parents, including their modifications, for each word. In contrast, earlier approaches that capture semantic similarity in morphological variants operate solely at the word level (Schone and Jurafsky, 2000; Baroni et al., 2002). We evaluate our model on datasets in three languages: Arabic, English and Turkish. Currently, top performing unsupervised morphological analyzers are based on the orthographic properties of sub-word units (Creutz and Lagus, 2005; words (observations) and their segmentations (hidden), using morphemes and their contexts (character n-grams) for the features. We use morphological chains to model words in the where C(w) ⊂Z refers to the set of possible candidates (parents and their types) for the word w ∈W. model for unsupervised morphological segmentation that seamlessly integrates orthographic and semantic properties of words.	./cache/work_ylcltxmpvvdbdmljbf3fmued3q.pdf	./txt/work_ylcltxmpvvdbdmljbf3fmued3q.txt