The topic of this project is formal models for uncertain argumentation from natural language text. Based on Dung’s argumentation theory, integrating uncertainty into argumentation is gaining momentum. However, to the best of our knowledge, little attention has been paid to the modelling of uncertain argumentation in which the uncertainty of arguments is obtained mainly from text (e.g. biological papers).The aim of this project is to develop theory and algorithms to formalize and evaluate the uncertain argumentation from natural language text, such that uncertain arguments represented by natural language can be formalized and their status be properly and efficiently evaluated. The prime objectives (challenges) of this project include:(O1) to study how verbal and linguistic uncertainty of arguments can be formally modeled by mapping them to (constraints over) numerical values;(O2) to study how uncertain argumentation is formalized on the basis of O1, by exploiting some existing uncertainty-handling formalisms such as possibility/ranking theory and subjective probability theory, etc.(O3) to study rationality postulates for the uncertain argumentation system formed in O2, and to develop a suitable semantics for it, such that the postulates can be satisfied;(O4) to develop methods to prioritize the evaluation of arguments and their dynamics; (O5) to develop algorithms and implement prototype systems based on methods in O4, and use these systems to empirically validate the methods and theories formulated in O1-O3.The project will be carried out by the cooperation between the Individual and Collective Reasoning (ICR) group at the University of Luxembourg and the group of Beishui Liao of the Center for Study of Language and Cognition (CSLC) at Zhejiang University. The cooperation is founded on complementary researches of the two groups: In Beishui Liao’s group, they have developed a series of innovative theories, algorithms and prototype systems for efficient computation of abstract argumentation semantics (both dynamic and static), while in ICR, we are working in the direction of combining logic and natural language, and have already conducted fundamental research on the topic of combining uncertainty and argumentation. In other words, ICR is good at resolving problems related to the objectives O1- O3, while CSLC has successful experience in realizing the objectives O4 and O5. So, the cooperation of our two groups is not only necessary, but also sufficient to implement the project.