This paper discusses our ongoing work on constructing an annotated corpus of children's stories for further studies on the linguistic, computational, and cognitive aspects of...
Many tasks of information extraction or natural language processing have a property that the data naturally consist of several views--disjoint subsets of features. Specifically, a ...
Named entity disambiguation concerns linking a potentially ambiguous mention of named entity in text to an unambiguous identifier in a standard database. One approach to this task...
We present a formal semantics for an objectoriented formalism which allows for the representation of plural objects (such as `Three N', `Most of the N', `Some N',.....
We introduce tiered clustering, a mixture model capable of accounting for varying degrees of shared (context-independent) feature structure, and demonstrate its applicability to i...