A Corpus-based Approach to the Interpretation of Unknown Words with an Application to German

Abstract Usually a high portion of the different word forms in a corpus receive no reading by the lexical and/or morphological analysis. These unknown words constitute a huge problem for NLP analysis tasks like POS-tagging or syntactic parsing. We present a parameterizable (in principle language-independent) corpus-based approach for the interpretation of unknown words that only needs a tokenized corpus and can be used in both offline and online applications. In combination with a few linguistic (language-dependent) rules unknown verbs, adjectives, nouns, multiword units etc. are identified. Depending on the recognized word class(es), more detailed morphosyntactic and semantic information is additionally identified in opposite to the majority of other unknown word guessing methods, which only uses a very narrow decision window to assign an unknown word its correct reading respective Part-of-Speech tag in a given text. We tested our approach by experiments with German data and received very promising results.