A Case Study on Learning a Unified Encoder of Relations
Lisheng Fu, Bonan Min, Thien Huu Nguyen, Ralph Grishman
Abstract
Typical relation extraction models are trained on a single corpus annotated with a pre-defined relation schema. An individual corpus is often small, and the models may often be biased or overfitted to the corpus. We hypothesize that we can learn a better representation by combining multiple relation datasets. We attempt to use a shared encoder to learn the unified feature representation and to augment it with regularization by adversarial training. The additional corpora feeding the encoder can help to learn a better feature representation layer even though the relation schemas are different. We use ACE05 and ERE datasets as our case study for experiments. The multi-task model obtains significant improvement on both datasets.- Anthology ID:
- W18-6126
- Volume:
- Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text
- Month:
- November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Venues:
- EMNLP | WNUT | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 202–207
- Language:
- URL:
- https://www.aclweb.org/anthology/W18-6126
- DOI:
- 10.18653/v1/W18-6126
- PDF:
- http://aclanthology.lst.uni-saarland.de/W18-6126.pdf