Abstract
We present a neural transition-based parser for spinal trees, a dependency representation of constituent trees. The parser uses Stack-LSTMs that compose constituent nodes with dependency-based derivations. In experiments, we show that this model adapts to different styles of dependency relations, but this choice has little effect for predicting constituent structure, suggesting that LSTMs induce useful states by themselves.- Anthology ID:
- W17-6316
- 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:
- 115–121
- Language:
- URL:
- https://aclanthology.org/W17-6316
- DOI:
- Cite (ACL):
- Miguel Ballesteros and Xavier Carreras. 2017. Arc-Standard Spinal Parsing with Stack-LSTMs. In Proceedings of the 15th International Conference on Parsing Technologies, pages 115–121, Pisa, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Arc-Standard Spinal Parsing with Stack-LSTMs (Ballesteros & Carreras, IWPT 2017)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/W17-6316.pdf