|Title||Recent advances in the development and sharing of language resources and tools for Latvian|
|Publication Type||Book Chapter|
|Year of Publication||2012|
|Authors||Vasiļjevs, A, Gornostay, T, Skadiņa, I, Deksne, D, Skadiņš, R, Pinnis, M|
|Editor||Vertan, C, v.Hahn, W|
|Book Title||Multilingual Processing in Eastern and Southern EU Languages – Less-resourced Technologies and Translation|
|Publisher||Cambridge Scholars Publishing|
This chapter presents an overview of recent advances in the development and sharing of language resources and tools for Latvian as one of the under-resourced languages. The first section briefly describes linguistic and sociolinguistic characteristics of the Latvian language, the history of language technology for Latvian, as well as national and EU cooperation activities in Latvian language technology. The second section introduces the concept of terminology entry compounding for the identification and unification of matching multilingual entries in terminology databases from different terminological resources. The third section discusses approaches to morphological analysis and tagging for Latvian as a morphologically-rich language. The fourth section focuses on the applied grammar checking methods for the Latvian language. The fifth section reports on recent research in the combination of knowledge-based and data-driven approaches in machine translation, including factored models for statistical machine translation and application of spatial ontologies to improve the translation of toponyms. The final section provides an overview of activities in Latvia to create an infrastructure for distribution and sharing of language resources and tools.