Robust German Noun Chunking With a Probabilistic Context-Free Grammar

We present a noun chunker for German which is based on a head-lexicalised probabilistic contextfree grammar. A manually developed grammar was semi-automatically extended with robustness rules in order to allow parsing of unrestricted text. The model parameters were learned from unlabelled training data by a probabilistic context-free parser. For extracting noun chunks, the parser generates all possible noun chunk analyses, scores them with a novel algorithm which maximizes the best chunk sequence criterion, and chooses the most probable chunk sequence. An evaluation of the chunker on 2,140 hand-annotated noun chunks yielded 92% recall and 93% precision.