The IICS group at the University of Hagen employs multilayered extended semantic networks for the representation of background knowledge, queries, and documents for geographic information retrieval (GIR). This paper describes our work for the participation at the GeoCLEF task of the CLEF 2005 evaluation campaign (Cross Language Evaluation Forum).

Abstract. In this paper, we develop and evaluate methods for decomposing complex questions for a question answering system to less complex questions. This aims at increasing the number of correct answers, especially in (deep) semantic question answering systems. For example, an event that occurs as a temporal restriction of a question can be queried for its date and the resulting answer can be substituted in the original question leading to a simpler, revised question. We present six decomposition classes, which are employed for annotating the 996 different German

Location indicators are text segments from which a geographic scope can be inferred, e.g. adjectives, demonyms (names for inhabitants of a place), geographic codes, orthographic variants, and abbreviations can be mapped to location names in one or more inferential steps. In this paper, the normalization of location indicators and treating morphology of location indicators for geographic information retrieval (GIR) within the system GIRSA (Geographic Information Retrieval by Semantic Annotation) are explored. Several retrieval experiments are performed on the German GeoCLEF 2007 data, including a baseline IR experiment on stemmed text (0.119 mean average precision, MAP). Results for this experiment are compared to results for experiments with normalized location indicators. Additionally, the latter approach was combined with an approach using semantic networks for retrieval (an extension of an experiment performed for GeoCLEF 2005). When using the topic title and description, the best performance was achieved by the combination of approaches (0.196 MAP); adding location names from the narrative part increased MAP to 0.258. Results indicate that 1) employing normalized location indicators improves

The German question answering (QA) system InSicht participated in QA@CLEF for the second time. It relies on complete sentence parsing, inferences, and semantic representation matching. This year, the system was improved in two main directions. First, the background knowledge was extended by large semantic networks and large rule sets. InSicht's query expansion step can produce more alternatives using these resources. A second direction for improvement was to deepen linguistic processing by treating a phenomenon that appears prominently on the level of text semantics: coreference resolution.

The German question answering (QA) system IRSAW (formerly: InSicht) participated in QA@CLEF for the fifth time. IRSAW was introduced in 2007, by integrating the deep answer producer InSicht, several shallow answer producers, and a logical validator. InSicht realizes a deep QA approach: it transforms documents to semantic representations using a parser, draws inferences on semantic representations with rules, and matches semantic representations derived from questions and documents. InSicht was improved for QA@CLEF 2008 mainly in the following areas. The coreference resolver was trained on question series instead of newspaper texts in order to be better applicable for follow-up questions in question series. Questions are decomposed by several methods on the level of semantic representations. On the shallow processing side, the number of answer producers was increased from 2 to 4, by adding FACT and SHASE. The answer validator introduced in the previous year was replaced with the faster RAVE validator designed for logic-based answer validation under time constraints. Using RAVE for merging the results of the answer producers, monolingual German runs and bilingual runs with

Abstract. The LogAnswer project investigates the potential of deep linguistic processing and logical reasoning for question answering. The paragraph selection task of ResPubliQA 2010 offered the opportunity to validate improvements of the LogAnswer QA system that reflect our experience from ResPubliQA 2009. Another objective was to demonstrate the benefit of QA technologies over a pure IR approach. Two runs were produced for ResPubliQA 2010: The first run corresponds to LogAnswer with standard configuration. The accuracy of 0.52 and c@1 score of 0.59 witness that LogAnswer has matured (in 2009, accuracy was 0.40 and

Concepts can be represented as frames, i.e., recursive attribute-value structures. Frames assign unique values to attributes. Concepts can be classified into four groups with respect to both relationality and referential uniqueness: sortal, individual, proper relational, and functional concepts. The paper defines frames as directed graphs with labeled nodes and arcs and it discusses the graph structures of frames for sortal and relational concepts. It aims at a classification of frame graphs that reflects the given concept classification. By giving a new definition of type signatures, the status of attributes in frames is clarified and the connection between functional concepts, their sortal uses, and their associated attributes is explained.

The paper features MAVE, a knowledge-based system for answer validation through deep linguistic processing and logical inference. A relaxation loop is used to determine a robust indicator of logical entailment. The system not only validates answers directly, but also gathers evidence by proving the original question and comparing results with the answer candidate. This method boosts recall by up to 13%. Additional indicators signal false positives. The filter increases precision by up to 14.5 % without compromising recall of the system.

Checking for readability or simplicity of texts is important for many institutional and individual users. Formulas for approximately measuring text readability have a long tradition. Usually, they exploit surface-oriented indicators like sentence length, word length, word frequency, etc. However, in many cases, this information is not adequate to realistically approximate the cognitive difficulties a person can have to understand a text. Therefore we use deep syntactic and semantic indicators in addition. The syntactic information is represented by a dependency tree, the semantic information by a semantic network. Both representations are automatically generated by a deep syntactico-semantic analysis. A global readability score is determined by applying a nearest neighbor algorithm on 3,000 ratings of 300 test persons. The evaluation showed, that the deep syntactic and semantic indicators lead to quite comparable results to most surface-based indicators. Finally, a graphical user interface has been developed which highlights difficult-to-read text passages, depending on the individual indicator values, and displays a global readability score. 1.

Mathematical knowledge contained in scientific digital publications poses a challenge for intelligent retrieval mechanisms. Many current approaches use statistical (e.g. Google) or natural language processing methods to find correlations in texts and annotate texts semantically. However both kinds of approaches face the problem of extracting and processing knowledge from mathematical equations. The presented system is based on natural language processing techniques, and benefits from characteristic linguistic structures defined by the language used in mathematical texts. It accumulates extracted information snippets from texts, symbols, and equations in knowledge bases. These knowledge bases provide the foundation for the information retrieval. This article describes the concepts and the prototypical technical implementation.