Konferenzbeitrag
Hard constraints for grammatical function labelling
For languages with (semi-) free word order (such as German), labelling grammatical functions on top of phrase-structural constituent analyses is crucial for making them interpretable. Unfortunately, most statistical classifiers consider only local information for function labelling and fail to capture important restrictions on the distribution of core argument functions such as subject, object etc., namely that there is at most one subject (etc.) per clause. We augment a statistical classifier with an integer linear program imposing hard linguistic constraints on the solution space output by the classifier, capturing global distributional restrictions. We show that this improves labelling quality, in particular for argument grammatical functions, in an intrinsic evaluation, and, importantly, grammar coverage for treebankbased (Lexical-Functional) grammar acquisition and parsing, in an extrinsic evaluation.
- Language
-
Englisch
- Subject
-
Phrasenstruktur
Automatische Sprachanalyse
Sprache
- Event
-
Geistige Schöpfung
- (who)
-
Seeker, Wolfgang
Rehbein, Ines
Kuhn, Joans
van Genabith, Josef
- Event
-
Veröffentlichung
- (who)
-
Stroudsburg, PA : Association for Computational Linguistics
- (when)
-
2016-11-21
- URN
-
urn:nbn:de:bsz:mh39-56059
- Last update
-
06.03.2025, 9:00 AM CET
Data provider
Leibniz-Institut für Deutsche Sprache - Bibliothek. If you have any questions about the object, please contact the data provider.
Object type
- Konferenzbeitrag
Associated
- Seeker, Wolfgang
- Rehbein, Ines
- Kuhn, Joans
- van Genabith, Josef
- Stroudsburg, PA : Association for Computational Linguistics
Time of origin
- 2016-11-21
Other Objects (12)
Hard constraints for grammatical function labelling
Evaluating LSTM models for grammatical function labelling
A new resource and baselines for opinion role labelling in German parliamentary debates
Improved opinion role labelling in parliamentary debates
Data point selection for self-training
Treebank-Based Grammar Acquisition for German
Der Einfluss der Dependenzgrammatik auf die Computerlinguistik
POS error detection in automatically annotated corpora
Data point selection for self-training
Der Einfluss der Dependenzgrammatik auf die Computerlinguistik
A testsuite for testing parser performance on complex German grammatical constructions [TePaCoC - a corpus for testing parser performance on complex German grammatical constructions]
TePaCoC - A Testsuite for Testing Parser Performance on Complex German Grammatical Constructions
Hard constraints for grammatical function labelling
Evaluating LSTM models for grammatical function labelling
A new resource and baselines for opinion role labelling in German parliamentary debates
Improved opinion role labelling in parliamentary debates
Data point selection for self-training
Treebank-Based Grammar Acquisition for German
Der Einfluss der Dependenzgrammatik auf die Computerlinguistik
POS error detection in automatically annotated corpora
Data point selection for self-training
Der Einfluss der Dependenzgrammatik auf die Computerlinguistik
A testsuite for testing parser performance on complex German grammatical constructions [TePaCoC - a corpus for testing parser performance on complex German grammatical constructions]
TePaCoC - A Testsuite for Testing Parser Performance on Complex German Grammatical Constructions
Hard constraints for grammatical function labelling
Evaluating LSTM models for grammatical function labelling
A new resource and baselines for opinion role labelling in German parliamentary debates
Improved opinion role labelling in parliamentary debates
Data point selection for self-training
Treebank-Based Grammar Acquisition for German
Der Einfluss der Dependenzgrammatik auf die Computerlinguistik
POS error detection in automatically annotated corpora
Data point selection for self-training
Der Einfluss der Dependenzgrammatik auf die Computerlinguistik
A testsuite for testing parser performance on complex German grammatical constructions [TePaCoC - a corpus for testing parser performance on complex German grammatical constructions]