We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
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...
The paper describes a system which uses packed parser output directly to build semantic representations. More specifically, the system takes as input Packed Shared Forests in the ...
This paper describes an approach to using semantic rcprcsentations for learning information extraction (IE) rules by a type-oriented inductire logic programming (ILl)) system. NLP...
We propose a new inference system which operates on underspecified semantic representations of scope and anaphora. This system exploits anaphoric accessibility conditions from dyn...
Spoken language generation for dialogue systems requires a dictionary of mappings between semantic representations of concepts the system wants to express and realizations of thos...
Ryuichiro Higashinaka, Rashmi Prasad, Marilyn A. W...
: Enhancing Wikipedia by means of semantic representations seems to be a promising issue. From a formal or technical point of view there are no major obstacles in the way. Neverthe...
This paper argues for a two-level theory of semantics as opposed to a one-level theory, based on the example of the system of temporal and durationM connectives. Instead of identi...