TY - GEN
T1 - A multi-lingual multi-task architecture for low-resource sequence labeling
AU - Lin, Ying
AU - Yang, Shengqi
AU - Stoyanov, Veselin
AU - Ji, Heng
N1 - Funding Information:
This work was supported by the U.S. DARPA LORELEI Program No. HR0011-15-C-0115 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.
Publisher Copyright:
© 2018 Association for Computational Linguistics
PY - 2018
Y1 - 2018
N2 - We propose a multi-lingual multi-task architecture to develop supervised models with a minimal amount of labeled data for sequence labeling. In this new architecture, we combine various transfer models using two layers of parameter sharing. On the first layer, we construct the basis of the architecture to provide universal word representation and feature extraction capability for all models. On the second level, we adopt different parameter sharing strategies for different transfer schemes. This architecture proves to be particularly effective for low-resource settings, when there are less than 200 training sentences for the target task. Using Name Tagging as a target task, our approach achieved 4.3%-50.5% absolute F-score gains compared to the mono-lingual single-task baseline model.1
AB - We propose a multi-lingual multi-task architecture to develop supervised models with a minimal amount of labeled data for sequence labeling. In this new architecture, we combine various transfer models using two layers of parameter sharing. On the first layer, we construct the basis of the architecture to provide universal word representation and feature extraction capability for all models. On the second level, we adopt different parameter sharing strategies for different transfer schemes. This architecture proves to be particularly effective for low-resource settings, when there are less than 200 training sentences for the target task. Using Name Tagging as a target task, our approach achieved 4.3%-50.5% absolute F-score gains compared to the mono-lingual single-task baseline model.1
UR - http://www.scopus.com/inward/record.url?scp=85062364107&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062364107&partnerID=8YFLogxK
U2 - 10.18653/v1/p18-1074
DO - 10.18653/v1/p18-1074
M3 - Conference contribution
AN - SCOPUS:85062364107
T3 - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
SP - 799
EP - 809
BT - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
PB - Association for Computational Linguistics (ACL)
T2 - 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
Y2 - 15 July 2018 through 20 July 2018
ER -