Accepted papers are listed here
Invited Talk: Preslav NAKOV, QCRI, Qatar Foundation. (Title to be announced)
Recent initiatives in language technology have lead to the development of at least minimal language processing kits for all official European languages. This is a big step towards automatic processing and /or extraction of information especially from official documents produced within the European Union.
Apart from those official languages, a large number of dialects or closely related variants are in use, more and more not only as spoken colloquial languages but also in written media.
Building language resources and tools is a cost-expensive operation and one can benefit form similarities among languages to reduce the effort in constructing LRs. One should be, however, aware also of the discrepancies which are often visible not only at the lexical level. Two examples could be different variants of Spanish in Latin America, German spoken in Austria and Switzerland, French – in France and Belgium, Dutch – in the Netherlands and Flemish in Belgium, etc.
Less attention has been paid up to now to the development of LRs for such languages. This has a major impact on promoting language technology at the educational level, using information processing methods in all-day communication, social media, etc.
This workshop intends to draw attention on issues mentioned above by bringing together scientists working with less resourced language variants and producing a roadmap of existing technologies and still existing gaps.
Topics covered by the workshop are:
- Adaptation of monolingual tools for close languages and language variants
- Case studies of using LRs and tools for standard languages on documents in language variants
- Machine translation among closely related languages
- Evaluation of LRs and tools for language variants and close languages
- Linguistic issues in adaptation of LRs and tools (e.g. semantic discrepancies, lexical gaps, false friends)
18 Mar 2013