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...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Chapter/Article Conference Paper |
| Language: | English |
| Published: |
September 2017
|
| In: |
15th International Conference on Parsing Technologies - proceedings of the conference
Year: 2017, Pages: 128-133 |
| Online Access: | Verlag, lizenzpflichtig, Volltext: https://aclanthology.org/W17-6318
|
| Author Notes: | Bich-Ngoc Do, Ines Rehbein |
| Summary: | 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). |
|---|---|
| Item Description: | Gesehen am 22.11.2023 |
| Physical Description: | Online Resource |
| ISBN: | 9781945626739 |