TY - GEN
T1 - Dynamic entity representation with max-pooling improves machine reading
AU - Kobayashi, Sosuke
AU - Den, Zen
AU - Okazaki, Naoaki
AU - Inui, Kentaro
N1 - Funding Information:
This work was supported by CREST, JST and JSPS KAKENHI Grant Number 15H01702 and 15H05318. We would like to thank members of Preferred Infrastructure, Inc. and Preferred Networks, Inc. for useful discussions. We also thank the anonymous reviewers for comments on earlier version of this paper.
Publisher Copyright:
©2016 Association for Computational Linguistics.
PY - 2016
Y1 - 2016
N2 - We propose a novel neural network model for machine reading, DER Network, which explicitly implements a reader building dynamic meaning representations for entities by gathering and accumulating information around the entities as it reads a document. Evaluated on a recent large scale dataset (Hermann et al., 2015), our model exhibits better results than previous research, and we find that max-pooling is suited for modeling the accumulation of information on entities. Further analysis suggests that our model can put together multiple pieces of information encoded in different sentences to answer complicated questions. Our code for the model is available at https://github.com/soskek/der-network.
AB - We propose a novel neural network model for machine reading, DER Network, which explicitly implements a reader building dynamic meaning representations for entities by gathering and accumulating information around the entities as it reads a document. Evaluated on a recent large scale dataset (Hermann et al., 2015), our model exhibits better results than previous research, and we find that max-pooling is suited for modeling the accumulation of information on entities. Further analysis suggests that our model can put together multiple pieces of information encoded in different sentences to answer complicated questions. Our code for the model is available at https://github.com/soskek/der-network.
UR - http://www.scopus.com/inward/record.url?scp=84994145773&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84994145773&partnerID=8YFLogxK
U2 - 10.18653/v1/n16-1099
DO - 10.18653/v1/n16-1099
M3 - Conference contribution
AN - SCOPUS:84994145773
T3 - 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference
SP - 850
EP - 855
BT - 2016 Conference of the North American Chapter of the Association for Computational Linguistics
PB - Association for Computational Linguistics (ACL)
T2 - 15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016
Y2 - 12 June 2016 through 17 June 2016
ER -