TY - GEN
T1 - Distance-free modeling of multi-predicate interactions in end-to-end Japanese predicate-argument structure analysis
AU - Matsubayashi, Yuichiroh
AU - Inui, Kentaro
N1 - Funding Information:
We are grateful to the anonymous reviewers for their useful comments and suggestions. We thank Hiroki Ouchi for his help in checking our re-implementation. We also thank Shun Kiyono and Kento Watan-abe for valuable discussions. This work was partially supported by JSPS KAKENHI Grant Numbers 15H01702 and 15K16045.
Publisher Copyright:
© 2018 COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings. All rights reserved.
PY - 2018
Y1 - 2018
N2 - Capturing interactions among multiple predicate-argument structures (PASs) is a crucial issue in the task of analyzing PAS in Japanese. In this paper, we propose new Japanese PAS analysis models that integrate the label prediction information of arguments in multiple PASs by extending the input and last layers of a standard deep bidirectional recurrent neural network (bi-RNN) model. In these models, using the mechanisms of pooling and attention, we aim to directly capture the potential interactions among multiple PASs, without being disturbed by the word order and distance. Our experiments show that the proposed models improve the prediction accuracy specifically for cases where the predicate and argument are in an indirect dependency relation and achieve a new state of the art in the overall F1 on a standard benchmark corpus.
AB - Capturing interactions among multiple predicate-argument structures (PASs) is a crucial issue in the task of analyzing PAS in Japanese. In this paper, we propose new Japanese PAS analysis models that integrate the label prediction information of arguments in multiple PASs by extending the input and last layers of a standard deep bidirectional recurrent neural network (bi-RNN) model. In these models, using the mechanisms of pooling and attention, we aim to directly capture the potential interactions among multiple PASs, without being disturbed by the word order and distance. Our experiments show that the proposed models improve the prediction accuracy specifically for cases where the predicate and argument are in an indirect dependency relation and achieve a new state of the art in the overall F1 on a standard benchmark corpus.
UR - http://www.scopus.com/inward/record.url?scp=85085571458&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85085571458&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85085571458
T3 - COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings
SP - 94
EP - 106
BT - COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings
A2 - Bender, Emily M.
A2 - Derczynski, Leon
A2 - Isabelle, Pierre
PB - Association for Computational Linguistics (ACL)
T2 - 27th International Conference on Computational Linguistics, COLING 2018
Y2 - 20 August 2018 through 26 August 2018
ER -