AI & I by Eugene Charniak

Author:Eugene Charniak
Language: eng
Format: epub
Publisher: MIT Press

7

Learning Language (1985–2010)

This chapter is about research into (natural) language processing (NLP). More specifically, it is about the transition within NLP to a learning-based paradigm.

In what was another interesting twist in the AI story, speech recognition work led to the next big change in the foundational ideas of the field. In particular, in 1990, the speech recognition group at IBM, led by Jelinek, published a paper on machine translation (MT)—enabling computers to translate between languages [9]. This paper took the ideas used in speech recognition, most notably the noisy channel model and HMMs, and imported them to the MT problem. This chapter focuses on MT, as it has been a great AI success story. However, at the end of the chapter, we abruptly switch gears and look at syntactic parsing, one of many other aspects of language where probability, graphical models, and learning came to dominate the field.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.