Elena Paskaleva

EVTIMA: a system for IE from hospital patient records in Bulgarian

In this article we present a text analysis system designed to extract key information from clinical text in Bulgarian language. Using shallow analysis within an Information Extraction (IE) approach, the system builds structured descriptions of patient status, disease duration, complications and treatments. We discuss some particularities of the medical language of Bulgarian patient records, the architecture and functionality of our current prototype, and evaluation results regarding the IE tasks we tackle at present. The paper also sketches the original aspects of our IE solutions.

A formal procedure for Bulgarian word form generation

The generation procedure proposed aims at the modelling of the process of verbal and nominal inflexion in Bulgarian. As in most of the similar morphological models of inflexional languages the procedure uses a comparatively simple mechar~ism of description a comparatively small number of initial objects among which onl.y one relation (viz. concatenation) is assigned; the transitions generating a separate concrete word form (or class of word forms) are determined.

Robust ending guessing rules with application to Slavonic languages

The paper studies the automatic extraction of diagnostic word endings for Slavonic languages aimed to determine some grammatical, morphological and semantic properties of the underlying word. In particular, ending guessing rules are being learned from a large morphological dictionary of Bulgarian in order to predict POS, gender, number, article and semantics. A simple exact high accuracy algorithm is developed and compared to an approximate one, which uses a scoring function previously proposed by Mikheev for POS guessing. It is shown how the number of rules of the latter can be reduced by a factor of up to 35, without sacrificing performance. The evaluation demonstrates coverage close to 100%, and precision of 97--99% for the approximate algorithm.