Konferenzbeitrag
Evaluating LSTM models for grammatical function labelling
To improve grammatical function labelling for German, we augment the labelling component of a neural dependency parser with a decision history. We present different ways to encode the history, using different LSTM architectures, and show that our models yield significant improvements, resulting in a LAS for German that is close to the best result from the SPMRL 2014 shared task (without the reranker).
- Sprache
-
Englisch
- Thema
-
Automatische Sprachverarbeitung
Syntaktische Analyse
Parser
Deutsch
Sprache
- Ereignis
-
Geistige Schöpfung
- (wer)
-
Do, Bich-Ngoc
Rehbein, Ines
- Ereignis
-
Veröffentlichung
- (wer)
-
Stroudsburg PA, USA : The Association for Computational Linguistics
- (wann)
-
2018-09-27
- URN
-
urn:nbn:de:bsz:mh39-80010
- Letzte Aktualisierung
-
06.03.2025, 09:00 MEZ
Datenpartner
Dieses Objekt wird bereitgestellt von:
Leibniz-Institut für Deutsche Sprache - Bibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Leibniz-Institut für Deutsche Sprache - Bibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Objekttyp
- Konferenzbeitrag
Beteiligte
- Do, Bich-Ngoc
- Rehbein, Ines
- Stroudsburg PA, USA : The Association for Computational Linguistics
Entstanden
- 2018-09-27
Ähnliche Objekte (12)
Hard constraints for grammatical function labelling
Hard constraints for grammatical function labelling
Evaluating Evaluation Measures
A new resource and baselines for opinion role labelling in German parliamentary debates
Evaluating LSTM models for grammatical function labelling
Improved opinion role labelling in parliamentary debates
Evaluating the Impact of Coder Errors on Active Learning
Evaluating the Impact of Coder Errors on Active Learning
Treebank-Based Grammar Acquisition for German
Data point selection for self-training
Data point selection for self-training
Der Einfluss der Dependenzgrammatik auf die Computerlinguistik
Hard constraints for grammatical function labelling
Hard constraints for grammatical function labelling
Evaluating Evaluation Measures
A new resource and baselines for opinion role labelling in German parliamentary debates
Evaluating LSTM models for grammatical function labelling
Improved opinion role labelling in parliamentary debates
Evaluating the Impact of Coder Errors on Active Learning
Evaluating the Impact of Coder Errors on Active Learning
Treebank-Based Grammar Acquisition for German
Data point selection for self-training
Data point selection for self-training
Der Einfluss der Dependenzgrammatik auf die Computerlinguistik
Hard constraints for grammatical function labelling
Hard constraints for grammatical function labelling
Evaluating Evaluation Measures
A new resource and baselines for opinion role labelling in German parliamentary debates
Evaluating LSTM models for grammatical function labelling
Improved opinion role labelling in parliamentary debates
Evaluating the Impact of Coder Errors on Active Learning
Evaluating the Impact of Coder Errors on Active Learning
Treebank-Based Grammar Acquisition for German
Data point selection for self-training
Data point selection for self-training