Kais Dukes

3 paper cards in Mova's library · 2010–2015

Kais Dukes wrote 3 of the papers Mova reads, in 2010–2015, most of them on Treebanks; often with Abdul-Baquee M. Sharaf, Eric Atwell, Nizar Habash.

The profile is the library's match of the name; two people with one name are not always told apart.

Topics: Treebanks 2

Papers

Statistical Parsing by Machine Learning from a Classical Arabic Treebank (2015)
A thesis built on seven papers about annotating and parsing Classical Arabic, with the Quran as the corpus.
Morphological Annotation of Quranic Arabic (2010)
The paper describes how the Quranic Arabic Corpus got its morphological layer: segmentation of each word into stem and affixes, with a part-of-speech tag and inflectional features per segment, following the traditional Arabic grammar tradition.
Syntactic Annotation Guidelines for the Quranic Arabic Dependency Treebank (2010)
The Quranic Arabic Dependency Treebank is part of the Quranic Arabic Corpus. All 77,430 words have manually verified morphology; 11,000 words (about 14%) have syntax, annotated by one part-time expert in three months. The trees follow the traditional i'rab grammar: dependency edges run between morphological segments…