Heiki-Jaan Kaalep

Learn More
The EU Copernicus project Multext-East has created a multi-lingual corpus of text and speech data, covering the six languages of the project: Bulgarian, Czech, Estonian, Hungarian, Romanian, and Slovene. In addition, wordform lexicons for each of the languages were developed. The corpus includes a parallel component consisting of Orwell’s Nineteen(More)
The paper describes a morphological analyser for Estonian and how using a text corpus influenced the process of creating it and the resulting program itself. The influence is not limited with the lexicon only, but is noticeable in the resulting algorithm and implementation too. When work on the analyser started, there was no computational treatment of(More)
The paper describes extraction of Estonian multi-word verbs from text corpora, using a languageand task-specific software tool SENVA, which is based on a statistical language-independent software tool SENTA (Dias et al, 2000). The outcome is a comprehensive list of 16,000 phrasal verbs. We describe the extraction tool, manual post-editing principles, and(More)
Although there are many tools for natural language processing tasks in Estonian, these tools are very loosely interoperable, and it is not easy to build practical applications on top of them. In this paper, we introduce a new Python library for natural language processing in Estonian, which provides a unified programming interface for various NLP(More)
This work introduces amethod and tool for handling overlapping parallel corpora – i.e. corpora that are based on the same source material. The method is insensitive to minor changes in the text, different segmentation levels of the corpora and omitted material from either corpora. The aim is to detect matching sentence pairs and either produce combinations(More)