Multi-lingual support for text analytics was a hot topic two weeks ago at the Text Analytics World conference in Boston. It seems like everyone mentioned it at one point or another, and with good reason: not many companies have strong natural language processing software.
Luckily, Lexalytics does. Our Native Language Packs include French, Spanish, Portuguese, and German. We are firm advocates of exclusively using Native Language Packs, as they catch more nuances in translation, and offer more precise sentiment analysis: we like good results.
We also have a Chinese language pack in the works, to be released sometime in early 2013. To ensure top quality, we’ve hired Chinese Language Expert Elizabeth Baran to work closely with our team on this project. Feel free to say hello in the comments, she doesn’t bite.
Elizabeth is fluent in English, French, and Chinese (Mandarin). In addition to having lived in China for 8 months during a Chinese language immersion program, she has published two papers in the domain of Chinese NLP (paper 1, paper 2), which were funded by the National Science Foundation under a Chinese-English Machine Translation grant. She has a Major in Chinese Language, and a double minor in Linguistics and French from Georgetown University.
Her credits include being a member of the Chinese Natural Language Processing Group at Brandeis University (2010-2012), publishing two papers on Chinese NLP, and presenting at the Machine Translation Summit XIII held in Xiamen, China, for research on automatically predicting noun number in Chinese. In addition to providing exceptional services to Lexalytics, she is also completing coursework for a MS in Computational Linguistics at Brandeis University, while writing a thesis on methods for automatically predicting the temporal location of Chinese verbs.
Our Chinese Language Pack will be in good hands.