Jointly embedding relations and mentions for knowledge population

Miao Fan, Kai Cao, Yifan He, Ralph Grishman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper contributes a joint embedding model for predicting relations between a pair of entities in the scenario of relation inference. It differs from most standalone approaches which separately operate on either knowledge bases or free texts. The proposed model simultaneously learns low-dimensional vector representations for both triplets in knowledge repositories and the mentions of relations in free texts, so that we can leverage the evidence both resources to make more accurate predictions. We use NELL to evaluate the performance of our approach, compared with cutting-edge methods. Results of extensive experiments show that our model achieves significant improvement on relation extraction.

Original languageEnglish (US)
Title of host publicationInternational Conference Recent Advances in Natural Language Processing, RANLP
PublisherAssociation for Computational Linguistics (ACL)
Pages186-191
Number of pages6
Volume2015-January
StatePublished - 2015
Event10th International Conference on Recent Advances in Natural Language Processing, RANLP 2015 - Hissar, Bulgaria
Duration: Sep 7 2015Sep 9 2015

Other

Other10th International Conference on Recent Advances in Natural Language Processing, RANLP 2015
CountryBulgaria
CityHissar
Period9/7/159/9/15

Fingerprint

Experiments

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Software
  • Electrical and Electronic Engineering

Cite this

Fan, M., Cao, K., He, Y., & Grishman, R. (2015). Jointly embedding relations and mentions for knowledge population. In International Conference Recent Advances in Natural Language Processing, RANLP (Vol. 2015-January, pp. 186-191). Association for Computational Linguistics (ACL).

Jointly embedding relations and mentions for knowledge population. / Fan, Miao; Cao, Kai; He, Yifan; Grishman, Ralph.

International Conference Recent Advances in Natural Language Processing, RANLP. Vol. 2015-January Association for Computational Linguistics (ACL), 2015. p. 186-191.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Fan, M, Cao, K, He, Y & Grishman, R 2015, Jointly embedding relations and mentions for knowledge population. in International Conference Recent Advances in Natural Language Processing, RANLP. vol. 2015-January, Association for Computational Linguistics (ACL), pp. 186-191, 10th International Conference on Recent Advances in Natural Language Processing, RANLP 2015, Hissar, Bulgaria, 9/7/15.
Fan M, Cao K, He Y, Grishman R. Jointly embedding relations and mentions for knowledge population. In International Conference Recent Advances in Natural Language Processing, RANLP. Vol. 2015-January. Association for Computational Linguistics (ACL). 2015. p. 186-191
Fan, Miao ; Cao, Kai ; He, Yifan ; Grishman, Ralph. / Jointly embedding relations and mentions for knowledge population. International Conference Recent Advances in Natural Language Processing, RANLP. Vol. 2015-January Association for Computational Linguistics (ACL), 2015. pp. 186-191
@inproceedings{df9453236bcb49bf9c45f49d6b19d13d,
title = "Jointly embedding relations and mentions for knowledge population",
abstract = "This paper contributes a joint embedding model for predicting relations between a pair of entities in the scenario of relation inference. It differs from most standalone approaches which separately operate on either knowledge bases or free texts. The proposed model simultaneously learns low-dimensional vector representations for both triplets in knowledge repositories and the mentions of relations in free texts, so that we can leverage the evidence both resources to make more accurate predictions. We use NELL to evaluate the performance of our approach, compared with cutting-edge methods. Results of extensive experiments show that our model achieves significant improvement on relation extraction.",
author = "Miao Fan and Kai Cao and Yifan He and Ralph Grishman",
year = "2015",
language = "English (US)",
volume = "2015-January",
pages = "186--191",
booktitle = "International Conference Recent Advances in Natural Language Processing, RANLP",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Jointly embedding relations and mentions for knowledge population

AU - Fan, Miao

AU - Cao, Kai

AU - He, Yifan

AU - Grishman, Ralph

PY - 2015

Y1 - 2015

N2 - This paper contributes a joint embedding model for predicting relations between a pair of entities in the scenario of relation inference. It differs from most standalone approaches which separately operate on either knowledge bases or free texts. The proposed model simultaneously learns low-dimensional vector representations for both triplets in knowledge repositories and the mentions of relations in free texts, so that we can leverage the evidence both resources to make more accurate predictions. We use NELL to evaluate the performance of our approach, compared with cutting-edge methods. Results of extensive experiments show that our model achieves significant improvement on relation extraction.

AB - This paper contributes a joint embedding model for predicting relations between a pair of entities in the scenario of relation inference. It differs from most standalone approaches which separately operate on either knowledge bases or free texts. The proposed model simultaneously learns low-dimensional vector representations for both triplets in knowledge repositories and the mentions of relations in free texts, so that we can leverage the evidence both resources to make more accurate predictions. We use NELL to evaluate the performance of our approach, compared with cutting-edge methods. Results of extensive experiments show that our model achieves significant improvement on relation extraction.

UR - http://www.scopus.com/inward/record.url?scp=84949745124&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949745124&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2015-January

SP - 186

EP - 191

BT - International Conference Recent Advances in Natural Language Processing, RANLP

PB - Association for Computational Linguistics (ACL)

ER -