In this paper, we investigate the semantic meaning of the messages passed in the Hugin architecture for probabilistic inference. By utilizing this information, one can avoid passi...
Context-free grammars cannot be identified in the limit from positive examples (Gold, 1967), yet natural language grammars are more powerful than context-free grammars and humans ...
Tim Oates, Tom Armstrong, Justin Harris, Mark Nejm...
We propose a methodology for investigating how well NLP systems handle meaning preserving syntactic variations. We start by presenting a method for the semi automated creation of ...
Full hierarchical dependencies (FHDs) constitute a large class of relational dependencies. A relation exhibits an FHD precisely when it can be decomposed into at least two of its ...
Semantic entailment is the problem of determining if the meaning of a given sentence entails that of another. This is a fundamental problem in natural language understanding that ...
Rodrigo de Salvo Braz, Roxana Girju, Vasin Punyaka...