Heli Uibo

Heli Uibo
Viabix Ltd, Stockholm, Sweden

M. Sc. (Computer Science)

About

16
Publications
2,847
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
54
Citations

Publications

Publications (16)
Conference Paper
Full-text available
This paper describes porting Oahpa, a set of advanced interactive language learning programs, to two new languages both of which spoken in Estonia – Estonian and Võro. Our programs offer a platform where the user can practice vocabulary and the generation of morphologically complex forms both in isolation and within sentential contexts. An overview...
Conference Paper
Full-text available
This paper presents an ICALL system for learning complex inflection systems, based upon finite state transducers (FST). Using a FST has several advantages: it makes it possible to generate a virtually unlimited set of exercises with a relatively small amount of work, and it makes it possible to process both input and output according to a wide rang...
Conference Paper
Full-text available
This paper describes the opportunities that arise from automatic word alignment for bilingual concordances and contrastive language studies. We introduce our parallel corpus of Alpine texts in French and German and our web-based alignment search system. We explain how we have reduced the number of erroneous alignments in the output by distinguishin...
Article
Full-text available
The Constraint Grammar of Estonian presented in the paper is the first attempt in automatic syntactic analysis of Estonian. The grammar consists of 1,240 morphological disambiguation rules, 47 clause boundary detection rules, 180 morphosyntactic mapping rules and 1,118 syn-tactic constraints. The rules have been devised using a training corpus of 2...
Article
Full-text available
14.1 Introduction Koskenniemi's two-level morphology was the first practical general model in the history of computational linguistics for the analysis of morphologically complex languages. In this article we will reconsider one of the key innovations in Koskenniemi (1983), namely the treatment of consonant gra-dation in finite state transducers. W...
Article
Full-text available
The creation of syntactically annotated corpora of Estonian started at the end of 1990s with the training and test corpora for the Constraint Grammar shallow syntactic parser. By now the size of the Estonian Constraint Grammar Corpus is close to 300 000 running words. In 2004 the first attempts have been made to build deep syntactically annotated c...
Article
The research on modeling the Esto- nian morphology by finite state de- vices has been influenced mostly by (Koskenniemi, 1983), (Lauri Karttunen and Zaenen, 1992) and (Beesley and Karttunen, 2000). We have used lex- ical transducer combined with two- level rules as a general model for de- scribing Estonian morphology. As a novel approach we can emp...
Article
Full-text available
The topic of the present study arises from a crucial problem in the field of readability formula application. Most of the formulae include word length as an independent variable to predict text complexity. Advocates of the formulae are convinced that the length of a word indicates its semantic complexity (Klare, 1988). On the other hand, the formul...
Article
Full-text available
The topic of the present study arises from a crucial problem in the field of readability formula application. Most of the formulae include word length as an independent variable to predict text complexity. Advocates of the formulae are convinced that the length of a word indicates its semantic complexity (Klare, 1988). On the other hand, the formul...
Article
Full-text available
The experimental two-level morphology of Estonian is under development at the University of Tartu. The language description, consisting of 45 two-level rules and over 200 lexicons has been implemented and tested using Xerox finite-state tools twolc and lexc. The root lexicons cover 400 most frequent stems at the present stage of development. The so...
Article
Full-text available
The research concentrates on the problems of describing the Estonian morphological system in the two-level formalism, developed by Kimmo Koskenniemi. The complexity of Estonian morphology is illustrated. The outlines of the two-level model are given. The present stage of the experimental Estonian two-level morphology is characterised and the future...
Article
Full-text available
Syntactically annotated corpora are needed 1) to train and test parsers and various language technological products -grammar checkers, information retrievers and extractors, machine translators etc; 2) to check the agreement of existing linguistic theories with the real language usage. The corpora can be annotated on different levels of depth. In s...
Article
Full-text available
The paper is concentrated on modeling the Estonian morphology in the framework of two- level morphology model. The result is a consistent description of Estonian morphology, which consists of a network of lexicons (root lexicons cover 2500 most frequent word roots) and two-level rules. The main rule set contains 45 rules, which describe various ste...

Network

Cited By