Header

UZH-Logo

Maintenance Infos

Reconstructing Complete Lemmas for Incomplete German Compounds


Aepli, Noëmi; Volk, Martin (2013). Reconstructing Complete Lemmas for Incomplete German Compounds. In: International Conference of the German Society for Computational Linguistics and Language Technology (GSCL), Darmstadt, 25 September 2013 - 27 September 2013, 1-13.

Abstract

This paper discusses elliptical compounds, which are frequently used in German in order to avoid repetitions. This phenomenon involves truncated words, mostly truncated compounds. These words pose a challenge in PoS tagging and lemmatization, which often leads to unknown or incomplete lemmas. We present an approach to reconstruct complete lemmas of truncated compounds in order to improve subsequent language technology or corpus linguistic applications. Results show an f-measure of 95.6% for the detection of elliptical compound patterns and 86.4% for the correction of compound lemmas.

Abstract

This paper discusses elliptical compounds, which are frequently used in German in order to avoid repetitions. This phenomenon involves truncated words, mostly truncated compounds. These words pose a challenge in PoS tagging and lemmatization, which often leads to unknown or incomplete lemmas. We present an approach to reconstruct complete lemmas of truncated compounds in order to improve subsequent language technology or corpus linguistic applications. Results show an f-measure of 95.6% for the detection of elliptical compound patterns and 86.4% for the correction of compound lemmas.

Statistics

Downloads

3 downloads since deposited on 22 Nov 2013
1 download since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Language:English
Event End Date:27 September 2013
Deposited On:22 Nov 2013 10:17
Last Modified:28 Aug 2017 15:30
Official URL:http://link.springer.com/chapter/10.1007/978-3-642-40722-2_1

Download