Derivational models are still an under-researched area in computational morphology. Even for German, a rather resource-rich language, there is a lack of large-coverage derivational knowledge. This paper describes a rule-based framework for inducing derivational families (i.e., clusters of lemmas in derivational relationships) and its application to create a high-coverage German resource, DERIVBASE, mapping over 280k lemmas into more than 17k non-singleton clusters. We focus on the rule component and a qualitative and quantitative evaluation. Our approach achieves up to 93\% precision and 71\% recall. We attribute the high precision to the fact that our rules are based on information from grammar books.
%0 Conference Paper
%1 zeller:2013
%A Zeller, Britta D.
%A Snajder, Jan
%A Padó, Sebastian
%B Proceedings of ACL
%C Sofia, Bulgaria
%D 2013
%K conference myown
%P 1201--1211
%T DErivBase: Inducing and Evaluating a Derivational
Morphology Resource for German
%U http://www.aclweb.org/anthology/P13-1118.pdf
%X Derivational models are still an under-researched area in computational morphology. Even for German, a rather resource-rich language, there is a lack of large-coverage derivational knowledge. This paper describes a rule-based framework for inducing derivational families (i.e., clusters of lemmas in derivational relationships) and its application to create a high-coverage German resource, DERIVBASE, mapping over 280k lemmas into more than 17k non-singleton clusters. We focus on the rule component and a qualitative and quantitative evaluation. Our approach achieves up to 93\% precision and 71\% recall. We attribute the high precision to the fact that our rules are based on information from grammar books.
@inproceedings{zeller:2013,
abstract = {Derivational models are still an under-researched area in computational morphology. Even for German, a rather resource-rich language, there is a lack of large-coverage derivational knowledge. This paper describes a rule-based framework for inducing derivational families (i.e., clusters of lemmas in derivational relationships) and its application to create a high-coverage German resource, DERIVBASE, mapping over 280k lemmas into more than 17k non-singleton clusters. We focus on the rule component and a qualitative and quantitative evaluation. Our approach achieves up to 93\% precision and 71\% recall. We attribute the high precision to the fact that our rules are based on information from grammar books.},
added-at = {2017-04-03T19:28:28.000+0200},
address = {Sofia, Bulgaria},
author = {Zeller, Britta D. and \v{S}najder, Jan and Pad{\'o}, Sebastian},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2cf864dcc94fe3d18d93309af2d8f2cfa/sp},
booktitle = {Proceedings of ACL},
interhash = {45746e3b846ceee5060bf5d7aedfd2c6},
intrahash = {cf864dcc94fe3d18d93309af2d8f2cfa},
keywords = {conference myown},
pages = {1201--1211},
timestamp = {2024-02-22T12:36:39.000+0100},
title = {{DErivBase}: Inducing and Evaluating a Derivational
Morphology Resource for {G}erman},
url = {http://www.aclweb.org/anthology/P13-1118.pdf},
year = 2013
}