Natural Language and Speech Processing

The quantity of text which will come in electronic form keeps growing in an explosive rate. Additionally to the net, large amounts of text are now being collected for medical, legal, commercial, and scientific programs. However the tools to get the data we want using this text continue to be quite primitive. Our research groups in natural language processing are building systems to to extract specific information from large text collections, and also to present it within the user’s preferred language. A carefully related area, speech processing, handles coding, synthesis and extraction of knowledge from speech signals.

Natural language processing includes a lengthy history at NYU. The Linguistic String Project was among the pioneers in natural language processing research within the U. s. States.

The Proteus Project concentrates on instantly understanding the linguistic understanding required for information extraction and machine translation. It’s developed extraction systems in British and Japanese, and a number of language-independent translation models. Additionally, it conducts an array of research, and evolves large-scale dictionaries along with other assets for natural language processing.

Rob Grishman ‘s section of scientific studies are natural language processing, — instantly ‘understanding’ natural language. He creates systems for information extraction, which could take out, from text, details about specific associations or kinds of occasions. For instance, among the systems produced by the audience can process the newspaper text and create a table of recent executive employs and fires, or corporate purchases. A present focus of Rob Grishman’s group is learning information from large text collections. The audience is part of a significant DARPA-funded effort to build up a built-in speech-machine translation-information extraction software lead by SRI worldwide.

Satoshi Sekine is focusing on a number of subjects in natural language processing: on-demand information extraction, understanding discovery from text corpora, to uncover designs, paraphrases, relations and semantic understanding question responding to and summarization, software for Japanese and British text analysis, Japanese and British named entity marking.

Adam Meyers research interests have been in natural language processing and computational linguistics. His primary direction of labor include computational lexicography, predicate argument structure, sentence alignment, coreference and corpus annotation.

Mehryar Mohri’s primary research areas are machine learning, theory and calculations, text and speech processing, and computational biology. Including particularly study regarding the theoretical facets of machine learning, the style of general and accurate learning calculations, as well as their programs to large-scale learning problems for example individuals present in bioinformatics and language processing.