Header

UZH-Logo

Maintenance Infos

A case study in tagging case in german: an assessment of statistical approaches


Clematide, Simon (2013). A case study in tagging case in german: an assessment of statistical approaches. In: Mahlow, Cerstin; Piotrowski, Michael. Systems and Frameworks for Computational Morphology. Heidelberg New York Dordrecht London: Springer, 22-34.

Abstract

In this study, we assess the performance of purely statistical approaches using supervised machine learning for predicting case in German (nominative, accusative, dative, genitive, n/a). We experiment with two different treebanks containing morphological annotations: TIGER and TUEBA. An evaluation with 10-fold cross-validation serves as the basis for systematic comparisons of the optimal parametrizations of different approaches. We test taggers based on Hidden Markov Models (HMM), Decision Trees, and Conditional Random Fields (CRF). The CRF approach based on our hand-crafted feature model achieves an accuracy of about 94%. This outperforms all other approaches and results in an improvement of 11% compared to a baseline HMM trigram tagger and an improvement of 2% compared to a state-of-the-art tagger for rich morphological tagsets. Moreover, we investigate the effect of additional (morphological) categories (gender, number, person, part of speech) in the internal tagset used for the training. Rich internal tagsets improve results for all tested approaches.

Abstract

In this study, we assess the performance of purely statistical approaches using supervised machine learning for predicting case in German (nominative, accusative, dative, genitive, n/a). We experiment with two different treebanks containing morphological annotations: TIGER and TUEBA. An evaluation with 10-fold cross-validation serves as the basis for systematic comparisons of the optimal parametrizations of different approaches. We test taggers based on Hidden Markov Models (HMM), Decision Trees, and Conditional Random Fields (CRF). The CRF approach based on our hand-crafted feature model achieves an accuracy of about 94%. This outperforms all other approaches and results in an improvement of 11% compared to a baseline HMM trigram tagger and an improvement of 2% compared to a state-of-the-art tagger for rich morphological tagsets. Moreover, we investigate the effect of additional (morphological) categories (gender, number, person, part of speech) in the internal tagset used for the training. Rich internal tagsets improve results for all tested approaches.

Statistics

Altmetrics

Additional indexing

Item Type:Book Section, 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
Date:2013
Deposited On:29 Nov 2013 12:57
Last Modified:08 Dec 2017 00:15
Publisher:Springer
Series Name:Communications in Computer and Information Science 380
ISBN:978-3-642-40485-6 (Print) 978-3-642-40486-3 (Online)
Additional Information:Systems and Frameworks for Computational Morphology: Third International Workshop, SFCM 2013, Berlin, Germany, September 6, 2013 Proceedings
Publisher DOI:https://doi.org/10.1007/978-3-642-40486-3_2

Download

Full text not available from this repository.
View at publisher