Bi-lingual Term Extraction with Big Data
October 10th 2017 12:30 - 12:45
Most current Term Extraction tools are rather weak, uni-lingual or both. Together with the Research Department of the Zurich University of Applied Sciences (ZHAW) we are developing a bi-lingual term extractor that uses a "Big Data" approach. In it's very basic, the tool compares the general occurrence probability of a word with it's relative occurrence in a specific text. The project is still ongoing, but first results are very encouraging. I can explain our approach in more details, compare it with other methods and present the results. This would be a mix of a technology and research spotlight.