@incollection{SteinerRuppenhofer2018, author = {Petra Steiner and Josef Ruppenhofer}, title = {Building a morphological treebank for German from a linguistic database}, series = {Proceedings of the eleventh international conference on language resources and evaluation (LREC 2018), 7-12 May 2018, Miyazaki, Japan}, editor = {Nicoletta Calzolari and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and H{\´e}l{\`e}ne Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga}, publisher = {European language resources association (ELRA)}, address = {Paris, France}, isbn = {979-10-95546-00-9}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-74958}, pages = {3882 -- 3889}, year = {2018}, abstract = {German is a language with complex morphological processes. Its long and often ambiguous word forms present a bottleneck problem in natural language processing. As a step towards morphological analyses of high quality, this paper introduces a morphological treebank for German. It is derived from the linguistic database CELEX which is a standard resource for German morphology. We build on its refurbished, modernized and partially revised version. The derivation of the morphological trees is not trivial, especially for such cases of conversions which are morpho-semantically opaque and merely of diachronic interest. We develop solutions and present exemplary analyses. The resulting database comprises about 40,000 morphological trees of a German base vocabulary whose format and grade of detail can be chosen according to the requirements of the applications. The Perl scripts for the generation of the treebank are publicly available on github. In our discussion, we show some future directions for morphological treebanks. In particular, we aim at the combination with other reliable lexical resources such as GermaNet.}, language = {en} }