TY - GEN
T1 - End-to-end reinforcement learning for automatic taxonomy induction
AU - Mao, Yuning
AU - Ren, Xiang
AU - Shen, Jiaming
AU - Gu, Xiaotao
AU - Han, Jiawei
N1 - Funding Information:
Research was sponsored in part by U.S. Army Research Lab. under Cooperative Agreement No. W911NF-09-2-0053 (NSCTA), DARPA under Agreement No. W911NF-17-C-0099, National Science Foundation IIS 16-18481, IIS 17-04532, and IIS-17-41317, and grant 1U54GM-114838 awarded by NIGMS through funds provided by the trans-NIH Big Data to Knowledge (BD2K) initiative (www.bd2k.nih.gov). The views and conclusions contained in this document are those of the author(s) and should not be interpreted as representing the official policies of the U.S. Army Research Laboratory or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation hereon. We thank Mohit Bansal, Hao Zhang, and anonymous reviewers for valuable feedback.
Publisher Copyright:
© 2018 Association for Computational Linguistics
PY - 2018
Y1 - 2018
N2 - We present a novel end-to-end reinforcement learning approach to automatic taxonomy induction from a set of terms. While prior methods treat the problem as a two-phase task (i.e., detecting hypernymy pairs followed by organizing these pairs into a tree-structured hierarchy), we argue that such two-phase methods may suffer from error propagation, and cannot effectively optimize metrics that capture the holistic structure of a taxonomy. In our approach, the representations of term pairs are learned using multiple sources of information and used to determine which term to select and where to place it on the taxonomy via a policy network. All components are trained in an end-to-end manner with cumulative rewards, measured by a holistic tree metric over the training taxonomies. Experiments on two public datasets of different domains show that our approach outperforms prior state-of-the-art taxonomy induction methods up to 19.6% on ancestor F1.
AB - We present a novel end-to-end reinforcement learning approach to automatic taxonomy induction from a set of terms. While prior methods treat the problem as a two-phase task (i.e., detecting hypernymy pairs followed by organizing these pairs into a tree-structured hierarchy), we argue that such two-phase methods may suffer from error propagation, and cannot effectively optimize metrics that capture the holistic structure of a taxonomy. In our approach, the representations of term pairs are learned using multiple sources of information and used to determine which term to select and where to place it on the taxonomy via a policy network. All components are trained in an end-to-end manner with cumulative rewards, measured by a holistic tree metric over the training taxonomies. Experiments on two public datasets of different domains show that our approach outperforms prior state-of-the-art taxonomy induction methods up to 19.6% on ancestor F1.
UR - http://www.scopus.com/inward/record.url?scp=85051502942&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85051502942&partnerID=8YFLogxK
U2 - 10.18653/v1/p18-1229
DO - 10.18653/v1/p18-1229
M3 - Conference contribution
AN - SCOPUS:85051502942
T3 - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
SP - 2462
EP - 2472
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 -