Natural Language Processing

Faculty

Ralph Grishman   Naomi Sager   Satoshi Sekine

Description

The amount of text which is available in electronic form is growing at an explosive rate. In addition to the web, large quantities of text are being collected for medical, legal, commercial, and scientific applications. But the tools for getting the information we need out of this text are still quite primitive. Our research groups in natural language processing are building systems to to extract specific information from large text collections, and to present it in the user's preferred language.

The Linguistic String Project was one of the pioneers in natural language processing research in the United States. Its current focus is on extracting information from the text in hospital medical records; it has developed systems for English, French, and German.

The Proteus Project focuses on automatically learning the linguistic knowledge needed for information extraction and machine translation. It has developed extraction systems in English and Japanese, and a series of language-independent translation models. It also conducts a wide range of basic research, and develops large-scale dictionaries and other resources for natural language processing.

Research Interests

Ralph Grishman	Founder of the Proteus Project. Acquisition of linguistic knowledge, extraction of information from large corpora, machine translation.
Satoshi Sekine	Information extraction, syntactic parsing, domain-specific language.
Naomi Sager	Director, Linguistic String Project, focusing on extracting information from the text in hospital medical records.

Related Projects

Linguistic String   Proteus