Natural Language Processing
A huge amount of information is stored or communicated in the form of natural language. But it is difficult to make use of this information without asking people to read or listen it all.
In our European research centre in Grenoble (France), we teach computers to read, understand and act. Our research in natural language processing (NLP) makes this information accessible, but also comprehensible, integrated, and actionable. Our algorithms and models are used in text analytics applications for healthcare, litigation, automation and finance.
Our research spans from mathematical models that describe better sequences of characters or words (language modeling), vector-based representation of words, to better and more generic methods of transforming text into knowledge, and generate back text. We work in many domains and across many languages. Our research team has leading experts in natural language processing, computational linguistics, knowledge representation, machine learning and text mining.
- AI / data-mining papers so far this year: full papers at UAI, RO-MAN (conversational agents), IJCAI (Q&A), KDD (real-time bidding) and AISTATS (spectral methods).
- Best Full Paper at the 7th International Learning Analytics and Knowledge Conference (LAK'17), 'Reflective Writing Analytics for Actionable Feedback'
- EACL in Valencia: XRCE will present 3 papers and 1 demo
- Xavier Carreras and Ariadna Quattoni are PC & area chair at EMNLP
- We had 4 four papers accepted at ACL + 2 at workshops. Here is the list
- Our entry to the SEMEVAL competition for Sentence-level aspect-based sentiment analysis ranked 1st in polarity detection for English and French. Here is the paper.
- The H2020 project READ started. Learn more about our participation in EC-funded projects here.