Header

UZH-Logo

Maintenance Infos

Incremental morphosyntactic disambiguation of nouns in German-language law texts


Sugisaki, Kyoko; Höfler, Stefan (2013). Incremental morphosyntactic disambiguation of nouns in German-language law texts. In: ESSLLI-13 Workshop on Extrinsic Parse Improvement (EPI) , Düsseldorf, 12 August 2013 - 16 August 2013.

Abstract

Morphosyntactic disambiguation is a crucial pre-processing step for the recognition of grammatical functions in morphologically rich languages like German and heavily nominalized domains like law texts. This paper explores how far linguistically motivated hard rules can contribute to morphosyntactic disambiguation. It introduces an incremental system that is capable of reducing the rate of morphosyntactically ambiguous nouns in sentences from German-language law texts from 91.12% to 32.31%. The evaluation indicates that disambiguation rules based on feature unification within complex sub-clausal structures such as noun phrase coordinations and participle phrases have the most impact on the reduction of morphosyntactic ambiguity.

Abstract

Morphosyntactic disambiguation is a crucial pre-processing step for the recognition of grammatical functions in morphologically rich languages like German and heavily nominalized domains like law texts. This paper explores how far linguistically motivated hard rules can contribute to morphosyntactic disambiguation. It introduces an incremental system that is capable of reducing the rate of morphosyntactically ambiguous nouns in sentences from German-language law texts from 91.12% to 32.31%. The evaluation indicates that disambiguation rules based on feature unification within complex sub-clausal structures such as noun phrase coordinations and participle phrases have the most impact on the reduction of morphosyntactic ambiguity.

Statistics

Downloads

132 downloads since deposited on 22 Aug 2013
79 downloads 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:16 August 2013
Deposited On:22 Aug 2013 06:22
Last Modified:06 Apr 2017 13:51
Funders:Swiss National Science Foundation
Free access at:Official URL. An embargo period may apply.
Official URL:http://cl.indiana.edu/epi/papers/sugisaki-hoefler.pdf
Related URLs:http://cl.indiana.edu/epi/ (Organisation)

Download

Preview Icon on Download
Preview
Content: Published Version
Language: English
Filetype: PDF
Size: 99kB

TrendTerms

TrendTerms displays relevant terms of the abstract of this publication and related documents on a map. The terms and their relations were extracted from ZORA using word statistics. Their timelines are taken from ZORA as well. The bubble size of a term is proportional to the number of documents where the term occurs. Red, orange, yellow and green colors are used for terms that occur in the current document; red indicates high interlinkedness of a term with other terms, orange, yellow and green decreasing interlinkedness. Blue is used for terms that have a relation with the terms in this document, but occur in other documents.
You can navigate and zoom the map. Mouse-hovering a term displays its timeline, clicking it yields the associated documents.

Author Collaborations