Collaborative Language Engineering: A Case Study in Efficient Grammar-Based Processing (Lecture Notes)

Following high hopes and subsequent disillusionment in the late 1980s, the past decade of work in language engineering has seen a dramatic increase in the power and sophistication of statistical approaches to natural language processing, along with a growing recognition that these methods alone cannot meet the full range of demands for applications of NLP. While statistical methods, often described as 'shallow' processing techniques, can bring real advantages in robustness and efficiency, they do not provide the precise, reliable representations of meaning which more conventional symbolic grammars can supply for natural language. A consistent, fine-grained mapping between form and meaning is of critical importance in some NLP applications, including machine translation, speech prosthesis, and automated email response. Recent advances in grammar development and processing implementations offer hope of meeting these demands for precision.

This volume provides an update on the state of the art in the development and application of broad-coverage declarative grammars built on sound linguistic foundations - the 'deep' processing paradigm - and presents several aspects of an international research effort to produce comprehensive, re-usable grammars and efficient technology for parsing and generating with such grammars.

Dan Flickinger is project manager of the Linguistic Grammars Online Project at the Center for the Study of Language and Information, Stanford University.
Stephan Oepen is professor in computational linguistics at the University of Oslo and senior researcher at the Center for the Study of Language and Information, Stanford University.

 

 



Dan Flickinger was a senior research associate at the Center for the Study of Language and Information, Stanford University and coeditor of Collected Papers of Martin Kay.