TY - GEN
T1 - Global attention for name tagging
AU - Zhang, Boliang
AU - Whitehead, Spencer
AU - Huang, Lifu
AU - Ji, Heng
N1 - This work was supported by the U.S. DARPA AIDA Program No. FA8750-18-2-0014, LORELEI Program No. HR0011-15-C-0115, Air Force No. FA8650-17-C-7715, NSF IIS-1523198 and U.S. ARL NS-CTA No. W911NF-09-2-0053. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on.
PY - 2018
Y1 - 2018
N2 - Many name tagging approaches use local contextual information with much success, but 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. We retrieve document-level context from other sentences within the same document and corpus-level context from sentences in other topically related documents. We propose a model that learns to incorporate document-level and corpus-level contextual information alongside local contextual information via global attentions, which dynamically weight their respective contextual information, and gating mechanisms, which determine the influence of this information. Extensive 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.1.
AB - Many name tagging approaches use local contextual information with much success, but 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. We retrieve document-level context from other sentences within the same document and corpus-level context from sentences in other topically related documents. We propose a model that learns to incorporate document-level and corpus-level contextual information alongside local contextual information via global attentions, which dynamically weight their respective contextual information, and gating mechanisms, which determine the influence of this information. Extensive 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.1.
UR - https://www.scopus.com/pages/publications/85072868972
UR - https://www.scopus.com/pages/publications/85072868972#tab=citedBy
U2 - 10.18653/v1/k18-1009
DO - 10.18653/v1/k18-1009
M3 - Conference contribution
AN - SCOPUS:85072868972
T3 - CoNLL 2018 - 22nd Conference on Computational Natural Language Learning, Proceedings
SP - 86
EP - 96
BT - CoNLL 2018 - 22nd Conference on Computational Natural Language Learning, Proceedings
PB - Association for Computational Linguistics (ACL)
T2 - 22nd Conference on Computational Natural Language Learning, CoNLL 2018
Y2 - 31 October 2018 through 1 November 2018
ER -