TY - GEN
T1 - Position-aware attention and supervised data improve slot filling
AU - Zhang, Yuhao
AU - Zhong, Victor
AU - Chen, Danqi
AU - Angeli, Gabor
AU - Manning, Christopher D.
N1 - Publisher Copyright:
© 2017 Association for Computational Linguistics.
PY - 2017
Y1 - 2017
N2 - Organized relational knowledge in the form of “knowledge graphs” is important for many applications. However, the ability to populate knowledge bases with facts automatically extracted from documents has improved frustratingly slowly. This paper simultaneously addresses two issues that have held back prior work. We first propose an effective new model, which combines an LSTM sequence model with a form of entity position-aware attention that is better suited to relation extraction. Then we build TACRED, a large (119,474 examples) supervised relation extraction dataset, obtained via crowdsourcing and targeted towards TAC KBP relations. The combination of better supervised data and a more appropriate high-capacity model enables much better relation extraction performance. When the model trained on this new dataset replaces the previous relation extraction component of the best TAC KBP 2015 slot filling system, its F1 score increases markedly from 22.2% to 26.7%.
AB - Organized relational knowledge in the form of “knowledge graphs” is important for many applications. However, the ability to populate knowledge bases with facts automatically extracted from documents has improved frustratingly slowly. This paper simultaneously addresses two issues that have held back prior work. We first propose an effective new model, which combines an LSTM sequence model with a form of entity position-aware attention that is better suited to relation extraction. Then we build TACRED, a large (119,474 examples) supervised relation extraction dataset, obtained via crowdsourcing and targeted towards TAC KBP relations. The combination of better supervised data and a more appropriate high-capacity model enables much better relation extraction performance. When the model trained on this new dataset replaces the previous relation extraction component of the best TAC KBP 2015 slot filling system, its F1 score increases markedly from 22.2% to 26.7%.
UR - http://www.scopus.com/inward/record.url?scp=85048045767&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048045767&partnerID=8YFLogxK
U2 - 10.18653/v1/d17-1004
DO - 10.18653/v1/d17-1004
M3 - Conference contribution
AN - SCOPUS:85048045767
T3 - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
SP - 35
EP - 45
BT - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
PB - Association for Computational Linguistics (ACL)
T2 - 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017
Y2 - 9 September 2017 through 11 September 2017
ER -