Julia Trushkina’s research while affiliated with North-West University and other places

This article reports on a project on the development of language resources and linguistic tools for Afrikaans. In the first part of the article, the multilingual parallel corpus that was created in the project is described. The corpus consists of aligned translations of the Bible in three languages, English, Dutch and Afrikaans. The second part of the article discusses one of the applications of a multilingual parallel corpus: induction of linguistic tools for a resource-scarce language.

A wide spectrum of multilingual applications have a ligned parallel corpora as their prerequisite. The aim of the project described in this paper is to build a multilingual corpus where all s entences are aligned at very high precision with a minimal human effort involved. The experiments on a combination of sentence aligners with different underlying algorithms described in th is paper showed that by verifying only those links which were not recognize d by at least two aligners, an error rate can be re duced by 93.76% as compared to the performance of the best aligner. Such manual i nvolvement concerned only a small portion of all da ta (6%). This significantly reduces a load of manual work necessary to achieve nearly 100% accuracy of alignment.

This paper describes design and creation of a multilingual parallel corpus for South African languages. One of the applications of the corpus, namely, the induction of a part-of-speech tagger for Afrikaans from the data, is presented in the paper. Development of the Afrikaans part-of-speech tagger is based on a modified method for induction of linguistic tools from parallel corpora originally proposed by Yarowsky and Ngai (2001). Full Text at Springer, may require registration or fee

This article presents a system designed for automatic detection of errors in second language learner's writing. The system contains two modules, one aimed at detecting and correcting of spelling errors, and a second module providing a broad detection of higher level language errors. The article describes extensions to existing error detection algorithms and introduces a novel method of context-based ranking of spelling correction candidates based on probabilistic context-free grammars. The performance of the system is evaluated on real data with manually marked and classified errors.

Nowadays, text corpora play an important role in language research and all fields involving language study, including theoretical and applied linguistics, language technology, translation studies and CALL (Computer Assisted Language Learning). Multilingual corpora, especially translated corpora, are not always readily available for Dutch. Much depends on the private initiative of individuals, and the data are often restrictedly available. The DPC-project (Dutch Parallel Corpus), which is carried out within the STEVIN program (Odijk et al. 2004), intends to fill the gap for this type of corpora for Dutch. This paper gives an overview of the DPC project. First, an overview and a discussion is given of the main parallel corpora containing Dutch. Then the DPC project is described, focusing on those aspects that make the DPC different from existing parallel corpora. Finally, the choice of an XML based format is explained.

This paper reports on the development of the Dutch Parallel Corpus: a high quality sentence-aligned parallel corpus of 10 million words for the language pairs Dutch-English and Dutch-French. The corpus is composed of different text types. All steps of processing the corpus including alignment and linguistic annotation undergo quality control on different levels. Four categories of potential users of the DPC can be distinguished: developers of HLT-applications, linguists conducting more fundamental research, human translators and language learners. This paper focuses on two types of intended users: MT developers and human translators. The paper describes different characteristics of the corpus relevant for such users, concentrating on corpus design, processing of the corpus data and the exploitation of the corpus.