|
|
|
| e-Pub |
Previous | 
Home
Section: Overall Objectives
Highlights of the Year
Nomination at the Institut Universitaire de France
Laurence Danlos is a Senior Member of the Institut Universitaire de France since October 2013
Statistical Parsing of Morphologically Rich Languages
Since several years, Djamé Seddah, together with Marie-Hélène Candito and more generally the whole Alpage team, has played a major role in setting up and animating an international network of researchers focusing on parsing morphologically rich languages (MRLs).
This year, Djamé Seddah has led the organization of the first shared task on parsing MRLs, hosted by the fourth SPMRL workshop [29] . Its primary goal was to bring forward work on parsing morphologically ambiguous input in both dependency and constituency parsing, and to show the state of the art for MRLs. We compiled data for as many as 9 languages, which represents an immense scientific and technical challenge.
Alpage participated to this shared task with two systems. The first one, applied to French only, belongs to the Bonsai series of parsers, adapted in collaboration with the LIGM in order to better deal with multi-word units [19] . It was ranked first, and is therefore the best known parser for French to date.
The other Alpage system which took part to this shared task is Éric Villemonte De La Clergerie's new DyALog-based shift-reduced parser [30] , which was applied to all 9 languages. It is the second best system overall.