Abstract
Many name tagging approaches use local contextual information with much success, but can fail when the local context is ambiguous or limited. We present a new framework to improve name tagging by utilizing local, document-level, and corpus-level contextual information. For each word, we retrieve document-level context from other sentences within the same document and corpus-level context from sentences in other documents. We propose a model that learns to incorporate document-level and corpus-level contextual information alongside local contextual information via document-level and corpus-level attentions, which dynamically weight their respective contextual information and determines the influence of this information through gating mechanisms. Experiments on benchmark datasets show the effectiveness of our approach, which achieves state-of-the-art results for Dutch, German, and Spanish on the CoNLL-2002 and CoNLL-2003 datasets. We will make our code and pre-trained models publicly available for research purposes.- Anthology ID:
- K18-1009
- Volume:
- Proceedings of the 22nd Conference on Computational Natural Language Learning
- Month:
- October
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Anna Korhonen, Ivan Titov
- Venue:
- CoNLL
- SIG:
- SIGNLL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 86–96
- Language:
- URL:
- https://aclanthology.org/K18-1009
- DOI:
- 10.18653/v1/K18-1009
- Cite (ACL):
- Boliang Zhang, Spencer Whitehead, Lifu Huang, and Heng Ji. 2018. Global Attention for Name Tagging. In Proceedings of the 22nd Conference on Computational Natural Language Learning, pages 86–96, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Global Attention for Name Tagging (Zhang et al., CoNLL 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/K18-1009.pdf
- Data
- CoNLL 2003