IPhraxtor - A linguistically informed system for extraction of term candidates

Multi-word Term Extraction for Bulgarian

The goal of this paper is to compile a method for multi-word term extraction, taking into account both the linguistic properties of Bulgarian terms and their statistical rates. The method relies on the extraction of term candidates matching given syntactic patterns followed by statistical (by means of Log-likelihood ratio) and linguistically (by means of inflectional clustering) based filtering...

You Can't Beat Frequency (Unless You Use Linguistic Knowledge) - A Qualitative Evaluation of Association Measures for Collocation and Term Extraction

In the past years, a number of lexical association measures have been studied to help extract new scientific terminology or general-language collocations. The implicit assumption of this research was that newly designed term measures involving more sophisticated statistical criteria would outperform simple counts of cooccurrence frequencies. We here explicitly test this assumption. By way of fo...

$YWRPDWVNR OXãþHQMH L]UD]MD L] VORYHQVNR-angleških vzporednih besedil

The paper describes the design and structure of a Slovene-English term extraction system. Although the state-of-the-art systems operate on hybrid approaches using various levels of linguistic analysis, sometimes including semantic information, the aim here was to implement both statistical and linguistically motivated methods for both languages and compare the results. It is shown that some met...

Computational Linguistics in the Translator’s Workflow—Combining Authoring Tools and Translation Memory Systems

In Technical Documentation, Authoring Tools are used to maintain a consistent text quality—especially with regard to the often followed translation of the original documents into several languages using a Translation Memory System. Hitherto these tools have often been used separately one after the other. Additionally Authoring tools often have no linguistic intelligence and thus the quality lev...

Collocation and term extraction using linguistically enhanced statistical methods