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).
Author: | Bich-Ngoc Do, Ines Rehbein |
---|---|
URN: | urn:nbn:de:bsz:mh39-80010 |
URL: | http://aclweb.org/anthology/W17-6318 |
ISBN: | 978-1-945626-73-9 |
Parent Title (English): | Proceedings of the 15th International Conference on Parsing Technologies, September 20–22, 2017 Pisa, Italy (IWPT 2017) |
Publisher: | The Association for Computational Linguistics |
Place of publication: | Stroudsburg PA, USA |
Document Type: | Conference Proceeding |
Language: | English |
Year of first Publication: | 2017 |
Date of Publication (online): | 2018/09/27 |
Publicationstate: | Veröffentlichungsversion |
Reviewstate: | Peer-Review |
GND Keyword: | Automatische Sprachverarbeitung; Deutsch; Parser; Syntaktische Analyse |
First Page: | 128 |
Last Page: | 133 |
DDC classes: | 400 Sprache / 400 Sprache, Linguistik |
Open Access?: | ja |
Leibniz-Classification: | Sprache, Linguistik |
Linguistics-Classification: | Computerlinguistik |
Program areas: | Digitale Sprachwissenschaft |
Licence (German): | ![]() |