Course Description:
Language technologies is the study of computational techniques to process text and speech, including: Information Retrieval, Text Mining, Parsing and Generation, Machine Translation, and Speech Recognition Synthesis. The course will include specific computational technique for each task, such as vector-spaces for IR, Web-spidering for IR and text mining, hidden-markoff-models for speech, chart parsing and so on. There will also be a synthesis task, such as combining parsing, generation and disambiguation for MT. The computational methods range from statistical to knowledge-based, and draw from related areas such as machine learning and linguistics. Students are expected to do hands-on programming and extensions of algorithms, deriving skills useful for further focused study in each area of language technologies as well as for web-based textual and multimedia (e.g. speech) information processing.