Orthographic Disambiguation Incorporating Transliteration, Typo and Other Similar Phenomena

点击翻译按钮获取中文摘要

Medical records are increasingly written on electronic media instead of on paper, which has radically increased the importance of information processing techniques in medical fields. Nevertheless, the state of usage of information and communication technologies (ICT) in medical fields is said to 10 years behind that in other fields. By processing large amounts of medical records and obtaining knowledge from them, great potential exist in assisting more precise and timely treatments. Such assistance can save lives and provide better quality of life. The goal of this project is to disambiguate medical terms, especially disease names, in medical records. We also handle transliteration, typo and other similar phenomena.