Annotation Adaptation and Language Adaptation in NLP

Adaptation technologies are always useful in NLP when there is discrepancy between the training scenario and use scenario. They are also effective in alleviating the data scarcity problem. Domain adaptation is the most popular kind of adaptation technologies and is intensively researched. In this talk we will introduce two other kinds of adaptation technologies: annotation adaptation and language adaptation. Annotation adaptation is used to improve the performance of an automatic annotation task by leveraging corpora with different annotation schemas, while language adaptation is used to solve an NLP problem in one language by utilizing the linguistic knowledge which is learnt from solving the same problem in another language. We investigate these technologies mainly for the tasks of word segmentation and parsing, however similar technologies may be developed for other NLP tasks also.