Unsupervised Multilingual Learning for Morphological Segmentation

By Benjamin Snyder, Regina Barzilay. 2008

169 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Linguistic I Ssues in L Anguage Technology Lilt on Achieving and Evaluating Language-independence in Nlp on Achieving and Evaluating Language-independence in Nlp (background): “The very interesting study by Snyder and Barzilay ( 2008 ) on multilingual ap - proaches to morphological segmentation was dicult to classify .”
Linguistically Naïve != Language Independent: Why NLP Needs Linguistic Typology (2009, background): “The very interesting study by Snyder and Barzilay (2008) on multilingual approaches to morphological segmentation was difficult to classify.”
Covariance in Unsupervised Learning of Probabilistic Grammars (2010, background): “Leveraging linguistic information from one language for the task of disambiguating another language has received considerable attention (Dagan, 1991; Yarowsky et al., 2001; Hwa et al., 2005; Smith and Smith, 2004; Snyder and Barzilay, 2008; Burkett and Klein, 2008).”
Posterior Regularization for Structured Latent Variable Models (2010, background): “…(Yarowsky and Ngai, 2001; Rogati et al., 2003; Hwa et al., 2005; Ganchev et al., 2009); discovery of paraphrases (Bannard and Callison-Burch, 2005; Callison-Burch, 2007, 2008); and joint unsupervised POS and parser induction across languages (Snyder and Barzilay, 2008; Snyder et al., 2009).”
Machine Translation without Words through Substring Alignment (2012, background): “…there are other many-to-many alignment meth-ods that have been used for simultaneously discovering morphological boundaries over multiple languages (Snyder and Barzilay, 2008; Naradowsky and Toutanova, 2011), but these have generally been applied to single words or short phrases, and it is not…”
Tuning Phrase-Based Segmented Translation for a Morphologically Complex Target Language (2015, methodology): “…from systems trained with diﬀerent segmentations and marking strategies (De Gispert et al., 2009), using morphology generation instead of segmented translation (Clifton and Sarkar, 2011), and improving the alignment directly in addition to balancing of token counts (Snyder and Barzilay, 2008).”