TY - GEN
T1 - Otyper
T2 - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018
AU - Yuan, Zheng
AU - Downey, Douglas C
N1 - Funding Information:
This work was supported in part by NSF Grant IIS-1351029 and the Allen Institute for Artificial Intelligence. We thank Oren Etzioni for suggesting we look at the ONET task. We also thank Mohammed Alam, David Demeter, Jared Fernan-dez, Thanapon Noraset, and Yiben Yang for helpful discussion.
Funding Information:
This work was supported in part by NSF Grant IIS-1351029 and the Allen Institute for Artificial Intelligence. We thank Oren Etzioni for suggesting we look at the ONET task. We also thank Mohammed Alam, David Demeter, Jared Fernandez, Thanapon Noraset, and Yiben Yang for helpful discussion.
Publisher Copyright:
Copyright © 2018, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2018
Y1 - 2018
N2 - Named Entity Typing (NET) is valuable for many natural language processing tasks, such as relation extraction, question answering, knowledge base population, and co-reference resolution. Classical NET targeted a few coarse-grained types, but the task has expanded to sets of hundreds of types in recent years. Existing work in NET assumes that the target types are specified in advance, and that hand-labeled examples of each type are available. In this work, we introduce the task of Open Named Entity Typing (ONET), which is NET when the set of target types is not known in advance. We propose a neural network architecture for ONET, called OTyper, and evaluate its ability to tag entities with types not seen in training. On the benchmark FIGER(GOLD) dataset, OTyper achieves a weighted AUC-ROC score of 0.870 on unseen types, substantially outperforming pattern- and embedding-based baselines.
AB - Named Entity Typing (NET) is valuable for many natural language processing tasks, such as relation extraction, question answering, knowledge base population, and co-reference resolution. Classical NET targeted a few coarse-grained types, but the task has expanded to sets of hundreds of types in recent years. Existing work in NET assumes that the target types are specified in advance, and that hand-labeled examples of each type are available. In this work, we introduce the task of Open Named Entity Typing (ONET), which is NET when the set of target types is not known in advance. We propose a neural network architecture for ONET, called OTyper, and evaluate its ability to tag entities with types not seen in training. On the benchmark FIGER(GOLD) dataset, OTyper achieves a weighted AUC-ROC score of 0.870 on unseen types, substantially outperforming pattern- and embedding-based baselines.
UR - http://www.scopus.com/inward/record.url?scp=85060461185&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85060461185&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85060461185
T3 - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018
SP - 6037
EP - 6044
BT - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018
PB - AAAI Press
Y2 - 2 February 2018 through 7 February 2018
ER -