Abstract
Recently introduced neural network parsers allow for new approaches to circumvent data sparsity issues by modeling character level information and by exploiting raw data in a semi-supervised setting. Data sparsity is especially prevailing when transferring to non-standard domains. In this setting, lexical normalization has often been used in the past to circumvent data sparsity. In this paper, we investigate whether these new neural approaches provide similar functionality as lexical normalization, or whether they are complementary. We provide experimental results which show that a separate normalization component improves performance of a neural network parser even if it has access to character level information as well as external word embeddings. Further improvements are obtained by a straightforward but novel approach in which the top-N best candidates provided by the normalization component are available to the parser.- Anthology ID:
- D18-1542
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4984–4991
- Language:
- URL:
- https://aclanthology.org/D18-1542
- DOI:
- 10.18653/v1/D18-1542
- Cite (ACL):
- Rob van der Goot and Gertjan van Noord. 2018. Modeling Input Uncertainty in Neural Network Dependency Parsing. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4984–4991, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Modeling Input Uncertainty in Neural Network Dependency Parsing (van der Goot & van Noord, EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/D18-1542.pdf
- Code
- robvanderg/normpar