id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_cxyxl5vs6zd6xlanudcx46qoqy	Ryan Cotterell	Joint Semantic Synthesis and Morphological Analysis of the Derived Word	2018	16	.pdf	application/pdf	10476	1454	61	Joint Semantic Synthesis and Morphological Analysis of the Derived Word investigate different models of vector composition, showing that recurrent neural networks parts.2 In this work, we propose a novel joint probabilistic model of word formation that captures both • First, we show that jointly modeling continuous representations of the semantics of morphemes and words allows us to improve morphological analysis. • Second, we explore improved models of vector composition for synthesizing word meaning. second body of work, e.g., the unsupervised morphological segmenter MORFESSOR (Creutz and Lagus, 2007), does not deal with semantics and makes While most prior work on morphological segmentation has not explicitly modeled productivity,5 we model's ability to segment words into their canonical morphemes as well as its ability to compositionally derive vectors for new words. Improved transition-based parsing by modeling characters instead of words with LSTMs. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 349–359, models for morpheme segmentation and morphology	./cache/work_cxyxl5vs6zd6xlanudcx46qoqy.pdf	./txt/work_cxyxl5vs6zd6xlanudcx46qoqy.txt