This prototype demonstrate a novel method for learning to find transliterations of proper nouns on the Web based on query expansion aimed at maximizing the probability of retrieving transliterations from existing search engines. Since the method we used involves learning the morphological relationships between names and their transliterations, we refer to this IR-based approach as morphological...

BACKGROUND In biomedical research, the consent form must comply with regulatory requirements. Checking for compliance typically has been performed on-site and most frequently after a participant's final enrollment. We use a procedure for remote preenrollment checking of consent forms that protects participant identities. This procedure requires a copy of the consent form that partially masks th...

Nouns Proper Names

We investigate the ability to automatically classify previously unseen proper noun phrases as drug names, company names, movie titles, and place names. The classifier relies on learning probabilistic features of each of the categories, the most important being a linearly interpolated 4-gram letter model of the proper nouns. In addition, prior probabilities, suffix probabilities, phrase length, ...

The goal of this paper is to examine the use of definite articleswith proper names, both cross-linguistically and intra-linguistically and provide a morpho-syntactic analysis of it. The first question to consider is whether article absence or article presence is the default case. The second question is when and how the alternative arises. I will presuppose here that names in argument positions ...

The paper presents a tool for the creation of an electronic dictionary of multi-word proper names. Toposław uses graphs for the representation of inflectional and pragmatic variants of names. It cooperates with Morfeusz, a morphological analyser and generator for Polish words, and Multiflex, a cross-language morpho-syntactic generator of multi-word units. Our goal was to create a userfriendly t...

Unknown named entity recognition in inflected languages faces several specific problems – the first and foremost is that the entities themselves are inflected1 (Dvonč et al., 1966) leading to a problem of identifying word forms as belonging to the same lexeme, and also the problem of finding correct lemma. In this article we analyse the distribution of word forms for proper nouns in Slovak and ...