Evaluating LSTM models for grammatical function labelling

Bich-Ngoc Do, Ines Rehbein


Abstract
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).
Anthology ID:
W17-6318
Volume:
Proceedings of the 15th International Conference on Parsing Technologies
Month:
September
Year:
2017
Address:
Pisa, Italy
Editors:
Yusuke Miyao, Kenji Sagae
Venue:
IWPT
SIG:
SIGPARSE
Publisher:
Association for Computational Linguistics
Note:
Pages:
128–133
Language:
URL:
https://aclanthology.org/W17-6318
DOI:
Bibkey:
Cite (ACL):
Bich-Ngoc Do and Ines Rehbein. 2017. Evaluating LSTM models for grammatical function labelling. In Proceedings of the 15th International Conference on Parsing Technologies, pages 128–133, Pisa, Italy. Association for Computational Linguistics.
Cite (Informal):
Evaluating LSTM models for grammatical function labelling (Do & Rehbein, IWPT 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-6318.pdf