The GRASP project aims at designing new graph-based Machine Learning algorithms that are better tailored to Natural Language Processing structured output problems. Focusing on semi-supervised learning scenarios, we will extend current graph-based learning approaches along two main directions: (i) the use of structured outputs during inference, and (ii) a graph construction mechanism that is more dependent on the task objective and more closely related to label inference. Combined, these two research strands will provide an important step towards delivering more adaptive (to new domains and languages), more accurate, and ultimately more useful language technologies. We will primarily target high-stake semantic and pragmatic tasks such as coreference resolution, temporal chronology prediction, and discourse parsing.
GRASP is funded by ANR, the French National Research Funding Agency, for four and a half year (2016-2021), under the “Jeunes Chercheuses/Jeunes Chercheurs” (“Young Researchers”) scheme (Grant n. ANR-16-CE33-0011-01).