|
Abstract : |
For a variety of reasons NLP has recently spawned a related engineering discipline called language en-gineering (LE), whose orientation is towards the ap-plication of NLP techniques to solving large-scale, real-world language processing problems in a robust and predictable way. Aside from the host of funda-mental theoretical problems that remain to be an-swered in NLP, language engineering faces a variety of problems of its own. First, there is no theory of language which is universally accepted, and no com-putational model of even a part of the process of language understanding which stands uncontested. Second, building intelligent application systems, sys-tems which model or reproduce enough human lan-guage processing capability to be useful, is a large-, |
