Preface: 17th International conference on Applications of Natural Language to Information Systems (NLDB 2012)

This special issue consists of four revised and extended papers selected from the 17th International conference on Applications of Natural Language to Information Systems (NLDB 2012), which was organized in June 2012 in Groningen, the Netherlands. The NLDB conferences bring together researchers interested in the use of natural language processing techniques in applications such as database querying, information systems architecture, software development, and more recently, various applications dealing with automatic enrichment of and advanced search in large volumes of web content. Authors of a selected number of contributions to the conference (12 full papers, 24 short papers, and 17 poster presentations) were asked to develop their paper into a journal article. After additional reviewing, 4 papers were selected for this special issue. ‘A semi supervised learning model for mapping sentences to logical forms with ambiguous supervision’ by Minh Le Nguyen and Akira Shimazu proposes a novel method for bootstrapping a semantic parser from a combination of semantically annotated, but not disambiguated, data and unlabeled data. ‘Wikimantic: Toward effective disambiguation and expansion of queries’ byChristopher Boston, Hui Fang, Sandra Carberry, Hao Wu, and Xitong Liu is concerned with microblog (tweet) retrieval, and shows that a query disambiguation and expansion method which uses Wikipedia as knowledge resource improves retrieval performance. ‘Inducing the contextual and prior polarity of nouns from the induced polarity preference of verbs’ by Manfred Klenner and Stefanos Petrakis presents a new method for learning the prior negative or positive sentiment of a noun, based on statistics obtained from a large corpus annotated with syntactic dependency relations. ‘Multidimensional topic analysis in political texts’ by Cäcilia Zirn and Heiner Stuckenschmidt addresses the issue of automatic content analysis in the social sciences. In particular, it shows that a technique for creating topic models based on party manifestos and coalition contracts is able to predict which party was primarily responsible for the text of which ministry. On behalf of the authors of the selected papers, we would like to thank all reviewers for their detailed and constructive comments on the submitted manuscripts.