The Natural Language Processing Research Group at Institute of Computing Technology, Chinese Academy of Sciences
conducts research on algorithms that allow computers to process and understand human languages. Our work covers a broad range of topics in natural language processing including machine translation, parsing, word segmentation and POS tagging, information retrieval, and information extraction.
A particular focus of our group is on building statistical machine translation systems that translate human languages automatically. We are pursuing a data-driven approach that all translation knowledge is learned from real-world parallel text. Our translation systems have resulted in leading performance for many natural languages such as Chinese, English, Korean, Mongolian, Uyghur, and Tibetan.