Dr. Frédérique Segond
The USA TODAY article Xerox develops detail-driven search tool said
Xerox researchers say they’ve developed a text-mining tool that’s tuned to the way humans think, speak and ask questions.
Frédérique Segond helped develop an evolutionary search engine that analyzes the meaning of words and contexts and accepts queries in everyday language.
Xerox is “trying to make a computer understand text like a human being,” said Frédérique Segond, parsing and semantics area manager at the company.
Frédérique Segond, Ph.D.
Parsing and Semantics area (ParSem) at XRCE.
She joined the Xerox Research Centre Europe as a research scientist in
1993 and worked on LOCOLEX, an intelligent dictionary lookup (European
Afterwards, within the PARGRAM (Parallel Grammars) project, she was
responsible for the design and the implementation of a French Lexical
Functional Grammar (LFG). She then led the Lexical Sense Disambiguation
LSD project where she worked on the projects EAGLES, ROMANSEVAL and
Frédérique then left the research organization for three years to join the Xerox business development team (NewStarts) where she was in charge of transferring research technologies to the European E-learning marketplace. The result of this is Exills a virtual solution dedicated to language learning that is also realized in an on-going European project Thetis.
She coauthored An experiment in semantic tagging using hidden markov model tagging, Error Driven Word Sense Disambiguation, Local Grammars for the Description of Multi-Word Lexemes and their Automatic Recognition in Texts, Semantic Encoding of Electronic Documents, and An integrated syntactic and semantic system for natural language understanding. Read her full list of publications!
Her patents include Using ranked translation choices to obtain sequences indicating meaning of multi-token expressions, Type-based selection of rules for semantically disambiguating words, Bilingual authoring assistant for the “tip of the tongue” problem, System for learning a language, and Syntactic information tagging support system and method.
Frédérique earned a PhD in Applied Mathematics at the Ecole des Hautes Etudes en Sciences Sociales in Paris where she implemented a categorial French grammar at IBM-France. After a one year post-doc at IBM-Yorktown working on the links between syntax and semantics, she was in charge of starting a research and teaching activity in one of the France Telecom schools.