Abstract
We propose a novel approach to semi-supervised learning for information extraction that uses ladder networks (Rasmus et al., 2015). In particular, we focus on the task of named entity classification, defined as identifying the correct label (e.g., person or organization name) of an entity mention in a given context. Our approach is simple, efficient and has the benefit of being robust to semantic drift, a dominant problem in most semi-supervised learning systems. We empirically demonstrate the superior performance of our system compared to the state-of-the-art on two standard datasets for named entity classification. We obtain between 62% and 200% improvement over the state-of-art baseline on these two datasets.- Anthology ID:
- N18-2057
- Volume:
- Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana
- Editors:
- Marilyn Walker, Heng Ji, Amanda Stent
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 352–358
- Language:
- URL:
- https://aclanthology.org/N18-2057
- DOI:
- 10.18653/v1/N18-2057
- Cite (ACL):
- Ajay Nagesh and Mihai Surdeanu. 2018. Keep Your Bearings: Lightly-Supervised Information Extraction with Ladder Networks That Avoids Semantic Drift. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 352–358, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- Keep Your Bearings: Lightly-Supervised Information Extraction with Ladder Networks That Avoids Semantic Drift (Nagesh & Surdeanu, NAACL 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/N18-2057.pdf
- Data
- OntoNotes 5.0