Approaches to Translating Natural Language Queries for use in XML Information Retrieval Systems

XML information retrieval (XML-IR) systems aim to provide users\ud with relevant results that are more specic than documents. To interact\ud with XML-IR systems, users must express both their content and\ud structural requirements in the form of a structured query, using formal\ud languages such as XPath or NEXI. Natural language queries (NLQs)\ud are a more intuitive alternative. Here, we present three approaches\ud that analyse NLQs and translate them into a formal language (NEXI)\ud query. The approaches participated in INEX's 2005 NLP track, where\ud they performed strongly, even outperforming a baseline that consisted\ud of manually constructed NEXI expressions. This suggests that further\ud collaboration between NLP and XML-IR could be mutually benecial