2-12-1 Hisakata, Tempaku,
NAGOYA 468-8511
JAPAN
Associate Member of the RCLN team, LIPN, Université Paris XIII
|
Postdoctoral Fellow in the COIN team, Toyota Technological Institute 2-12-1 Hisakata, Tempaku, NAGOYA 468-8511 JAPAN Associate Member of the RCLN team, LIPN, Université Paris XIII |
My main interest is the quality of the annotations produced by NLP systems. My PhD thesis puts in evidence that, to date, no NLP system is able to produce automatically perfect annotations. Consequently, it is important to design NLP systems based on inference models dealing with uncertain information. During my PostDoc I worked in close interaction with users from different domains. This was an opportunity to evaluate the usability of current NLP approaches according to the user's point of view. It seems that there is a certain threshold beyond which users will regard the output of an NLP system as reliable, and that current systems have not yet reached that point. This is particularly true for systems which produce semantic information (e.g. Anaphora Resolution or semantic frames extraction). Their use can even be obtrusive if they present noisy and distracting information to the user. I'm currently working on an inference model, based on the belief revision logic, to detect and correct any annotation errors. This may raise the global accuracy of the annotations produced by a given annotation platform.
| 2010-2011 |
|
| 2006-2007 |
|
| 2005-2006 |
|
| 2004-2005 |
|
| 2003-2004 |
|