A wide-coverage morphemic CCG lexicon for Turkish

Ruket Cakici, Mark Steedman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper we present a method to induce a wide-coverage morpheme-cluster based CCG lexicon from Turkish dependency treebank. We use the sub-word level dependencies in the Turkish dependency treebank, and show that this lexicon performs better than its lexemic counterpart in explaining morphosyntactic behaviour in Turkish. It also aims to solve the data sparseness by allowing better statistics for morphologically decomposed words when compared to fully inflected counterparts.
Original languageEnglish
Title of host publicationParsing with Categorial Grammars Workshop ESSLLI 2009 Bordeaux
Number of pages5
Publication statusPublished - 2009

Fingerprint

Dive into the research topics of 'A wide-coverage morphemic CCG lexicon for Turkish'. Together they form a unique fingerprint.

Cite this