The basic aim of the model proposed here is to automatically build semantic metatext structure for texts that would allow us to search and extract discourse and semantic informati...
Representing documents by vectors that are independent of language enhances machine translation and multilingual text categorization. We use discriminative training to create a pr...
This paper reports a research effort in scenario recognition task in information extraction. The presented approach uses partial semantic analysis based on logical form representa...
Svetla Boytcheva, Milena Yankova, Albena Strupchan...
Knowledge representation is essential for semantics modeling and intelligent information processing. For decades researchers have proposed many knowledge representation techniques...
We argue that groups of unannotated texts with overlapping and non-contradictory semantics represent a valuable source of information for learning semantic representations. A simp...