We develop a framework for using the Natural Language Toolkit (NLTK) to parse Quranic Arabic sentences. This framework supports the construction of a treebank for the Holy Quran. The proposed model succeeds in parsing different Quranic chapters (Suras) in addition to Modern Standard Arabic (MSA) sentences. The availability of such parser will be useful in various natural language processing app...

In this paper, we describe our approach taken in the MSM2013 IE Challenge, which was aimed at concept extraction from microposts. The goal of the approach was to combine several existing NER tools which use different classification methods and benefit from their combination. Several NER tools have been chosen and individually evaluated on the challenge training set. We observed that some of the...

This deliverable defines the evaluation strategies for the Information Extraction tools that are under development within the Dot.Kom project.

PROTO-INDO-EUROPEAN is the traditional name given to the ancestor language of the Indo-European family that is spread from Iceland to Chinese Turkestan and from Scandinavia to the Near East. A PROTO-LANGUAGE (Gk. prõtos ‘first’) refers to the earliest form of a language family presupposed by all of its descendants. There will forever be major gaps in the reconstruction of proto-languages, but a...

In this paper we introduce an extension of the Probably Approximately Correct (PAC) learning model to study the problem of learning inclusion hierarchies of concepts (sometimes called is-a hierarchies) from random examples. Using only the hypothesis representations output over many different runs of a learning algorithm, we wish to reconstruct the partial order (with respect to generality) amon...