A constraint-based hypergraph partitioning approach to coreference resolution
Emili Sapena Masip
9 Maig 2012
11:00h - Presentació
The objectives of this thesis are focused on research in machine learning for coreference resolution. Coreference resolution is a natural language processing task that consists of determining the expressions in a discourse that mention or refer to the same entity.
The main contributions of this thesis are (i) a new approach to coreference resolution based on constraint satisfaction, using a hypergraph to represent the problem and solving it by relaxation labeling; and (ii) research towards improving coreference resolution performance using world knowledge extracted from Wikipedia.
The developed approach is able to use entity-mention classification model with more expressiveness than the pair-based ones, and overcome weaknesses of previous approaches in the state of the art. Furthermore, the approach allows the incorporation of new information by adding constraints, and a research has been done in order to use world knowledge to improve performances.
RelaxCor, the implementation of the approach, achieved results in the state of the art, and participated in international competitions: SemEval-2010 and CoNLL-2011.