Learn More
The choice of natural language technology appropriate for a given language is greatly impacted by density (availability of digitally stored material). More than half of the world speaks medium density languages , yet many of the methods appropriate for high or low density languages yield suboptimal results when applied to the medium density case. In this(More)
The paper provides an overview of the open source Hungarian language resources that the SzóSzablya 'WordSword' project is creating. An extensive crawl of the .hu domain yielded a raw dataset of over 18m web pages. We discuss the methods used to detect and remove duplicates, low quality, foreign, and mixed language documents, and describe the resulting(More)
The ispell family of spellcheckers is perhaps the single most widely ported and deployed open-source language tool. Here we describe how the SzóSzablya 'WordSword' project leverages ispell's Hungarian descendant, HunSpell, to create a whole set of related tools that tackle a wide range of low-level NLP-related tasks such as character set normalization,(More)
Common tasks involving orthographic words include spellchecking, stemming, morphological analysis, and morphological synthesis. To enable significant reuse of the language-specific resources across all such tasks, we have extended the functionality of the open source spellchecker MySpell, yielding a generic word analysis library, the runtime layer of the(More)
Endotoxin challenge leads to septic shock, multi-organ failure and death in mice. Permeability of the blood-brain barrier (BBB) is increased by endotoxemia. Serum amyloid P component (SAP) is a lipopolysaccharide (LPS)-binding protein that can modulate the host reactions during infections. It is controversial whether SAP can protect from LPS toxicity in(More)
CONTEXT Genetic variation in human maternal DNA contributes to the susceptibility for development of gestational diabetes mellitus (GDM). OBJECTIVE We assessed 77 maternal single nucleotide gene polymorphisms (SNPs) for associations with GDM or plasma glucose levels at OGTT in pregnancy. METHODS 960 pregnant women (after dropouts 820: case/control:(More)