Determining Immediate Constituents of Compounds in GermaNet

Proceedings of Recent Advances in Natural Language Processing, pages 420–426, Hissar, Bulgaria, 12-14 September 2011. Determining Immediate Constituents of Compounds in GermaNet Verena Henrich University of Tübingen verena.henrich@uni- tuebingen.de Erhard Hinrichs University of Tübingen erhard.hinrichs@uni- tuebingen.de Abstract In order to be able to systematically link compounds in GermaNet to their constit- uent parts, compound splitting needs to be applied recursively and has to identify the immediate constituents at each level of analysis. Existing tools for compound splitting for German only offer an analy- sis of all component parts of a compound at once without any grouping of subcon- stituents. Thus, existing tools for splitting compounds were adapted to overcome this issue. Algorithms combining three heterogeneous kinds of compound split- ters are developed to achieve better re- sults. The best overall result with an ac- curacy of 92.42% is achieved by a hybrid combined compound splitter that takes into account all knowledge provided by the individual compound splitters, and in addition some domain knowledge about German derivation morphology and compounding. 1 Introduction The present paper presents a compound splitter for German that is tailored to the needs of sys- tematically enriching the set of lexical relations of GermaNet (Kunze and Lemnitzer, 2002; Hen- rich and Hinrichs, 2010), the German version of the Princeton WordNet for English (Fellbaum, 1998). Compounding is a highly productive word formation process resulting in complex words with two or more constituent parts. Baroni et al. (2002) report that almost half (47%) of the word types in the APA German news corpus are com- pounds. For GermaNet, the numbers are comparable: The morphological analyzer SMOR (Schmid et al., 2004) for German classifies 46.89% of all lexical units contained in release 6.0 of Germa- Net as compounds. Among those, nominal com- pounds make up 95% and are thus by far the largest class of compounds. It is for this reason that we concentrate exclusively on the treatment of nominal compounds in the present study. Given the prevalence of compounds in Germa- Net and its current coverage of 84586 lexical units, a systematic treatment of compounds is badly needed in order to enhance the usability of GermaNet for a wide variety of NLP applica- tions, including machine translation, natural lan- guage generation, information extraction, etc. The size of GermaNet and the high frequency of compounds clearly prohibit a purely manual so- lution and mandate an automatic treatment. The treatment of compounds for GermaNet needs to be systematic along at least three dimensions: (i) it should cover all combinations of word classes present in GermaNet which can enter into noun compounding, (ii) it should apply to all lexical units already entered into GermaNet, and (iii) it should be extendable to all compounds which are candidates for inclusion in GermaNet in future data releases. 2 Nominal Compounds in German Peter Eisenberg (Eisenberg, 2006) defines four major subclasses for compounds, where the rightmost head constituent is a noun. 1. Noun + Noun: Apfelbaum ‘apple tree’. 2. Adjective + Noun: Weißbrot ‘white bread’. 3. …

Content truncated to 500 words