The CSLI LinGO Lab is committed to the development of linguistically precise grammars based on the HPSG framework, and general-purpose tools for use in grammar engineering, profiling, parsing and generation. Early work in the CSLI LinGO Lab focused on the construction of a general-purpose grammar of English in the form of the English Resource Grammar (or ERG), and on further development of the LKB grammar engineering system. The LKB was also used at CSLI as the testbed for a number of teaching grammars and smaller-scale grammars for other languages including Japanese and Spanish.
The LinGO Lab is a founding member of the DELPH-IN international research consortium (www.delph-in.net), collaborating over the past 20 years in the development of linguistically grounded grammar and language processing resources.
Since 2008, project work has centered around applications in online education, initially as part of Stanford's Education Program for Gifted Youth (EPGY) with its Language Arts and Writing course, using a modified version of the ERG to automatically detect grammar errors in student writing. Expansion of this course and automated evaluation tools continued after the EPGY courses became part of Redbird Advanced Learning and later McGraw-Hill Education, with an increasing focus on analyzing short essays in addition to single sentence exercises. In 2016, work began in collaboration with the Chinese education publishing company Up366 in Beijing, to use LinGO technology for detecting grammar errors in the writing of Chinese students learning English as a second language. Initially focused on analyzing single sentence translation exercises for middle school and high school students, LinGO work with Up366 has since expanded to now include analysis of short essays, and to accommodate errors typically made by university students, in a three-party collaboration with Up366 and the Polytechnic University in Hong Kong.
In 2020, the lab also began a research and development effort with New York-based Noema Inc. to combine the ERG and related DELPH-IN resources with their system based on a game-theoretic approach to language understanding. Applications being explored at present include spoken language control of household appliances and improved enterprise search tools.
