A Question Answering System for German. Experiments with Morphological Linguistic Resources

Abstract

Question Answering systems are systems that enable the user to ask questions in natural language and to also receive an answer in natural language. Most existing systems, however, are constructed for the English language, and it is not clear in how far these approaches are also applicable to other languages. A richer morphology, greater syntactic variability, and smaller fraction of webpages available in the language are just some issues that complicate the construction of systems for German. In this paper, we present a modular Question Answering System for German which uses several morphological resources to increase recall. Nouns are converted into verbs, verbs into nouns, and the tenses of verbs are modified. We use a web search engine as a back end to allow for open-domain Question Answering. A POS-tagger is employed to identify answer candidates which are then filtered and tiled. The system is shown to achieve a higher recall than other systems for German.

Resources

Details