Abstract: In this paper we describe a flexible, portable and languageindependent infrastructure for setting up large monolingual language corpora. The approach is based on collecti...
Christian Biemann, Stefan Bordag, Gerhard Heyer, U...
Corpus-based stochastic language models have achieved significant success in speech recognition, but construction of a corpus pertaining to a specific application is a difficult ta...
The application of statistical methods to natural language processing has been remarkably successful over the past two decades. But, to deal with recent problems arising in this ...
Abstract. Controlled languages (CLs) are ambiguity-free subsets of natural languages such as English offering a good trade-off between the formal rigor of ontology and query langua...
We present a method of grounded word learning that is powerful enough to learn the meanings of first and second person pronouns. The model uses the understood words in an utteran...