Multilingual Lexical Resources and Tools
Report on the CLARA researcher training course on Multilingual Lexical Resources and Tools, held in Bergen on 20–23 June 2011.
The course was a cooperation between the CLARA ITN, the Norwegian Research School on Linguistics and Philology and its local branch, the University of Bergen Research School on Linguistics and Philology.
The aims of the course were the following. In recent years, mono- and multilingual lexicons, wordnets and other lexical resources have become more readily available. In such databases, the information provided on words and their relations, both within and across languages, has become richer and more easily exploitable in various applications. WordNets are being used in word sense disambiguation, machine translation, information extraction and information retrieval. Over 60 wordnets have been developed over the world. Typologically different languages have faced challenges in adapting the original model and linking wordnets across languages. Parallel corpora aligned at word level have created possibilities for analyzing translational correspondences and deriving lexical relations within and across languages by means of new computational methods (such as Semantic Mirrors). Furthermore, unstructured texts, such as ordinary web materials, can be mined in different ways by tools such as SketchEngine in order to fully automatically derive overviews of how lexical items behave in context.
The course was held according to plan and offered different training elements. It gave a theoretical overview of lexical relations as related to computational lexicons, wordnets and thesauri and it presented different methods for their construction and exploitation. Standardization of lexical resources in terms of LMF (Lexical Mapping Framework) was explained. The multilingual aspect was founded in a description and classification of translational relations, and their exploration and use were demonstrated and explained. Methods and tools such as Weka, SketchEngine and Semantic Mirrors were demonstrated and hands-on exercises were given.
Program and results
For more details on the training content, see the full course program including suggested readings and slides presented at the course. There was also a joint dinner at Fløien Folkerestaurant (see picture). The time schedule is on the calendar.
Full participation at the course gave 4 credits.