Finite State Morphology

By J. Rauff. 2007

353 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.

Finite-state morphological transducers for three Kypchak languages (2014, methodology): “This toolkit has been chosen as it – or the equivalent XFST (Beesley, 2003) – has been widely used for other Turkic languages, such as Turkish (Çöltekin, 2010), Crimean Tatar (Altintas, 2001), Turkmen (Tantuğ et al., 2006), and Kyrgyz (Washington et al., 2012), and is available under a free/open-sou”
Explaining Violation Traces with Finite State Natural Language Generation Models (2014, methodology): “This is based on ﬁnite state techniques as embodied in xfst (Beesley and Karttunen [BK03]) that has already been used extensively in several other areas of language processing such as computational morphology and light parsing. xfst provides a language for the description of complex transducers…”
Arabic Tokenization System (2007, methodology): “One way to allow the tokenizer to handle MWEs is to embed the MWEs in the Tokenizer (Beesley and Karttunen 2003).”
Context-Based Morphological Disambiguation with Random Fields (2005, background): “They are often encoded as ﬁnite-state transducers (Ka-plan and Kay, 1981; Koskenniemi, 1983; Beesley and Karttunen, 2003).”