A passionate computational linguist solving various natural language processing challenges for European languages, including but not limited to knowledge extraction, opinion mining, and error correction. A member of the BrUK group with 7+ years of experience in NLP in both academia and industry.
Topic: BrUK group for Ukrainian NLP: tools & data
Short Description: For quite a while, Ukrainian NLP was hampered by a lack of (good) data and freely available tools. Fortunately, the situation is changing now. The BrUK group is working on a cornerstone project – a properly annotated corpus for various text processing needs. The Big Electronic Dictionary of Ukrainian (over 200,000 entries and counting) is now available for NLP engineers. LanguageTool for Ukrainian is more than just another spellchecker – it is flexible enough to identify grammar and style errors and is constantly improved. The presentation will discuss these and related projects and tools, highlighting newest developments and the road ahead.