Logo du CNRS, de l EHESS et du Collège de France

Anne Garcia-Fernandez, junior researcher (post doctorate) at CEA-LIST

Question-Answering Systems, Appraisal and Hesitations Expresion (medical domain and the question answering), Text Mining (DEFT 2011, Opinion Mining), Natural Language Generation.

Opinion Mining
I am currently working as a post-doctoral research scientist at CEA-LIST for the WASP project and I am interested in Opinion Mining. Previously, I worked on this topic at LIMSI for the DOXA project in which the LIMSI care of the evaluation campaign.

Automatic Text Datation
Moreover, a participated to the 2011 DEFT Challenge with three colleagues from LIMSI, ILES and TLP groups. We participated to the Diachronic Task.

Appraisal and hesitation expressions
I am also working on appraisal and hesitation expression both on written and speech modality. I am working on two application domains: medical domain and question-answering. On medical domain, we annotated medical problems in clinical reviews (from Akenaton Project). On question-answering, I pursue directly my PhD work annotating and studying hesitation expression on French native speaker answers.

The MACAQ corpus
(Multi-Annotated Corpus of Answers to Question)

During my PhD, I worked on Question-Answering systems and collected a corpus of French native speaker answers to questions. The main characteristics of this corpus are:
- Questions used have a controlled linguistic form_______________- It is both oral and written
- Answers are made for question-answering system use__________- It has been annotated on different level
- It is unique so far! (april 2011)______________________________- It is freely available upon request

For more detail, see the LREC 2010 paper.
The corpus is available upon mail request (only the transcribed version of the oral answers is available).
If you use it please, let me know how and don't forget to cite the LREC 2010 paper :

author = {Anne Garcia-Fernandez, Sophie Rosset, Anne Vilnat},
title = {MACAQ : A Multi Annotated Corpus to study how we adapt Answers to various Questions},
booktitle = {Proceedings of LREC},
year = {2010},

mentions légales - création revaweb