The performance of machine learning algorithms can be improved by combining the output of different systems. In this paper we apply this idea to the recognition of noun phrases. W...
We introduce a framework for semantic interpretation in which dependency structures are mapped to conceptual representations based on a parsimonious set of interpretation schemata...
ARBITER is a Prolog program that extracts assertions about macromolecular binding relationships from biomedical text. We describe the domain knowledge and the underspecified lingu...
Thomas C. Rindflesch, Jayant V. Rajan, Lawrence Hu...
We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked on...
Over the past decade or so, a lot of work in computational linguistics has been directed at finding ways to exploit the ever increasing volume of electronic bilingual corpora. The...
Many corpus-based machine translation systems require parallel corpora. In this paper, we present a word-for-word glossing algorithm that requires only a source language corpus. T...