Abstract. We present a hybrid machine learning approach for information extraction from unstructured documents by integrating a learned classifier based on the Maximum Entropy Mod...
We improve the quality of paraphrases extracted from parallel corpora by requiring that phrases and their paraphrases be the same syntactic type. This is achieved by parsing the E...
A parsing system returning analyses in the form of sets of grammatical relations can obtain high precision if it hypothesises a particular relation only when it is certain that th...
We report on our work to automatically build a corpus of instructional text annotated with lexical semantics information. We have coupled the parser LCFLEX with a lexicon and onto...
Bootstrapping semantics from text is one of the greatest challenges in natural language learning. We first define a word similarity measure based on the distributional pattern of ...