Abstract. Natural language interfaces offer end-users a familiar and convenient option for querying ontology-based knowledge bases. Several studies have shown that they can achieve high retrieval performance as well as domain independence. This paper focuses on usability and investigates if NLIs are useful from an end-user’s point of view. To that end, we introduce four interfaces each allowing a different query language and present a usability study benchmarking these interfaces. The results of the study reveal a clear preference for full sentences as query language and confirm that NLIs are useful for querying Semantic Web data. 1

Abstract. In this paper we present a model and a corresponding ontology for associating lexical information to entities of a given domain ontology. In particular, we focus on representing subcategorization frames as well as their mapping to ontological structures. The lexicon model and ontology can thus be used to specify the syntax-semantic interface for ontology-based NLP systems which are expected to produce output compliant with a specific domain ontology. Our lexicon ontology itself is formalized in the OWL language, thus allowing the lexica to be published together with the domain ontologies. We also discuss different ways how the creation of appropriate lexica can be supported. 1

In this paper we present interface techniques that support the writing process of machine-oriented controlled natural languages which are well-defined and tractable fragments of English that can be translated unambiguously into a formal target language. Since these languages have grammatical and lexical restrictions, it is important to provide a text editor that assists the writing process by using lookahead information derived from the grammar. We will discuss the requirements to such a lookahead text editor and introduce the semantic wiki AceWiki as an application where this technology plays an important role. We investigate two different approaches how lookahead information can be generated dynamically while a text is written and compare the runtimes and practicality of these approaches in detail. 1

One of the most prominent benefits gained from the emergence of Semantic Web technology is the possibility to access data more efficiently, through the use of ontologies [18]. Querying such data requires using formal languages such as SeRQL [7] or SPARQL [39]. However, the syntax of these formal languages tends to be too

While qualitative analyses of the problems involved in building natural language interfaces (NLIs) have been available, a quantitative grounding in empirical data has been missing. We fill this gap by providing a quantitative analysis on the basis of the Geobase dataset. We hope that this analysis can guide further research in NLIs.

Abstract. We present an approach for computing intensional answers given a set of extensional answers returned as a result of a user query to an information system. Intensional answers are considered as descriptions of the actual answers in terms of properties they share and which can enhance a user’s understanding of the answer itself but also of the underlying knowledge base. In our approach, an intensional answer is represented by a clause and computed based on Inductive Logic Programming (ILP) techniques, in particular bottom-up clause generalization. The approach is evaluated in terms of usefulness and time performance, and its potential for helping to detect flaws in the knowledge base is discussed. While the approach is used in the context of a natural language question answering system in our setting, it clearly has applications beyond. 1

The Semantic Web is about to become a rich source of knowledge whose potential will be squandered if it is not accessible for everyone. Intuitive interfaces like conversational agents are needed to better disseminate this knowledge, either on request or even proactively in a context-aware manner. This paper presents work on extending an existing conversational agent, Max, with abilities to access the Semantic Web via natural language communication. 1.

Abstract. Web search is a key technology of the Web, since it is the primary way to access content on the Web. Current standard Web search is essentially based on a combination of textual keyword search with an importance ranking of the documents depending on the link structure of the Web. For this reason, it has many limitations, and there are a plethora of research activities towards more intelligent forms of search on the Web, called semantic search on the Web, or also Semantic Web search. In this paper, we give a brief overview of existing such approaches, including own ones, and sketch some possible future directions of research.

Workshop chairs Melliyal Annamalai (Oracle, USA) Daniel Olmedilla (Leibniz Universität Hannover, DE)

Abstract. Natural Language Interfaces (NLIs) to structured data allow users to interact with a system using written or spoken language to perform tasks that require knowledge of a formal language. Due to natural language complexity and ambiguity, such interfaces usually support a Controlled Natural Language (CNL): a subset of a natural language that includes certain vocabulary and grammar rules that have to be followed. Building vocabulary differs from one system to another, and the way this is performed significantly affects portability: portable CNLs for querying ontologies are those that can be adapted easily to new domains without sacrificing performance. In this paper we describe the approach for dynamically extending the vocabulary supported by such systems, through a dialog with the user.