This user has not added any information to their profile yet.
I am a senior research scientist in the Natural Language Processing group. My research interest lies in Document Understanding. This is the branch of AI interested in the automatic recognition of the structure and content of a document that is only available in a paginated format. Those documents might be born digital, often the case for PDF documents, or obtained by scanning the paper document. Have a look a this blog and demo to get a better idea of what Document Understanding can do for you!
A bit of history...
I graduated from the ENSIMAG, a computer science and applied mathematics engineering school (a so-called French "Grande Ecole") in 1989.
I first worked for the Cap Gemini R&D center, where I was exposed to the emerging domain of business process automation, in the context of a large European research project. The Cap Gemini team proudly came out with one of the first workflow product, called Process Weaver. I was responsible for the design, development of the process engine part and, later on, for its maintenance and support, with one foot on the service side.
I then joined Xerox research in 1995 and worked on the creation of a coordination middleware, with a particular focus on its application to business process support. We later on got quite addicted to looking for ways to stimulate and sustain knowledge sharing in business environments.
I joined the Document Structure group in 2004.
During the period 2012-2015, as a refresher, I led a project involving machine translation and multi-lingual text generation, and then managed the technological transfer to the business services in India.
Publications
All my publications since 1995 are in the publication database.
Patents
- US patents at US Patent Office site.
- US patent applications
- EU patents