The Pronto QA system at TREC-2007: harvesting hyponyms, using nominalisation patterns, and computing answer cardinality
Johan Bos, Edoardo Guzzetti, James Curran · 2007
The backbone of the Pronto QA system is linguistically-principled: Combinatory Categorial Grammar is used to generate syntactic analyses of questions and potential answer snippets, and Discourse Representation Theory is employed as semantic formalism to match the meanings of questions and answers. The key idea of the Pronto system is to use semantics to prune answer candidates, thereby exploiting lexical resources such as WordNet and NomLex to facilitate the selection of answers. The system performed well at TREC-2007 on factoid-questions with an answer accuracy of 22%, a score higher than the median accuracy score of all participating systems. 1