Heterogeneous supervision for relation extraction: A representation learning approach

Liyuan Liu, Xiang Ren, Qi Zhu, Huan Gui, Shi Zhi, Heng Ji, Jiawei Han

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

Abstract

Relation extraction is a fundamental task in information extraction. Most existing methods have heavy reliance on annotations labeled by human experts, which are costly and time-consuming. To overcome this drawback, we propose a novel framework, REHESSION, to conduct relation extractor learning using annotations from heterogeneous information source, e.g., knowledge base and domain heuristics. These annotations, referred as heterogeneous supervision, often conflict with each other, which brings a new challenge to the original relation extraction task: how to infer the true label from noisy labels for a given instance. Identifying context information as the backbone of both relation extraction and true label discovery, we adopt embedding techniques to learn the distributed representations of context, which bridges all components with mutual enhancement in an iterative fashion. Extensive experimental results demonstrate the superiority of REHESSION over the state-of-the-art.

Original languageEnglish (US)
Title of host publicationEMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages46-56
Number of pages11
ISBN (Electronic)9781945626838
StatePublished - Jan 1 2017
Event2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017 - Copenhagen, Denmark
Duration: Sep 9 2017Sep 11 2017

Publication series

NameEMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

Conference

Conference2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017
CountryDenmark
CityCopenhagen
Period9/9/179/11/17

Fingerprint

Labels

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Computational Theory and Mathematics

Cite this

Liu, L., Ren, X., Zhu, Q., Gui, H., Zhi, S., Ji, H., & Han, J. (2017). Heterogeneous supervision for relation extraction: A representation learning approach. In EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings (pp. 46-56). (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings). Association for Computational Linguistics (ACL).

Heterogeneous supervision for relation extraction : A representation learning approach. / Liu, Liyuan; Ren, Xiang; Zhu, Qi; Gui, Huan; Zhi, Shi; Ji, Heng; Han, Jiawei.

EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), 2017. p. 46-56 (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings).

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

Liu, L, Ren, X, Zhu, Q, Gui, H, Zhi, S, Ji, H & Han, J 2017, Heterogeneous supervision for relation extraction: A representation learning approach. in EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings, Association for Computational Linguistics (ACL), pp. 46-56, 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, 9/9/17.
Liu L, Ren X, Zhu Q, Gui H, Zhi S, Ji H et al. Heterogeneous supervision for relation extraction: A representation learning approach. In EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL). 2017. p. 46-56. (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings).
Liu, Liyuan ; Ren, Xiang ; Zhu, Qi ; Gui, Huan ; Zhi, Shi ; Ji, Heng ; Han, Jiawei. / Heterogeneous supervision for relation extraction : A representation learning approach. EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), 2017. pp. 46-56 (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings).
@inproceedings{8f65db800d424b55beb0c4b748ac039e,
title = "Heterogeneous supervision for relation extraction: A representation learning approach",
abstract = "Relation extraction is a fundamental task in information extraction. Most existing methods have heavy reliance on annotations labeled by human experts, which are costly and time-consuming. To overcome this drawback, we propose a novel framework, REHESSION, to conduct relation extractor learning using annotations from heterogeneous information source, e.g., knowledge base and domain heuristics. These annotations, referred as heterogeneous supervision, often conflict with each other, which brings a new challenge to the original relation extraction task: how to infer the true label from noisy labels for a given instance. Identifying context information as the backbone of both relation extraction and true label discovery, we adopt embedding techniques to learn the distributed representations of context, which bridges all components with mutual enhancement in an iterative fashion. Extensive experimental results demonstrate the superiority of REHESSION over the state-of-the-art.",
author = "Liyuan Liu and Xiang Ren and Qi Zhu and Huan Gui and Shi Zhi and Heng Ji and Jiawei Han",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
series = "EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "46--56",
booktitle = "EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings",

}

TY - GEN

T1 - Heterogeneous supervision for relation extraction

T2 - A representation learning approach

AU - Liu, Liyuan

AU - Ren, Xiang

AU - Zhu, Qi

AU - Gui, Huan

AU - Zhi, Shi

AU - Ji, Heng

AU - Han, Jiawei

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Relation extraction is a fundamental task in information extraction. Most existing methods have heavy reliance on annotations labeled by human experts, which are costly and time-consuming. To overcome this drawback, we propose a novel framework, REHESSION, to conduct relation extractor learning using annotations from heterogeneous information source, e.g., knowledge base and domain heuristics. These annotations, referred as heterogeneous supervision, often conflict with each other, which brings a new challenge to the original relation extraction task: how to infer the true label from noisy labels for a given instance. Identifying context information as the backbone of both relation extraction and true label discovery, we adopt embedding techniques to learn the distributed representations of context, which bridges all components with mutual enhancement in an iterative fashion. Extensive experimental results demonstrate the superiority of REHESSION over the state-of-the-art.

AB - Relation extraction is a fundamental task in information extraction. Most existing methods have heavy reliance on annotations labeled by human experts, which are costly and time-consuming. To overcome this drawback, we propose a novel framework, REHESSION, to conduct relation extractor learning using annotations from heterogeneous information source, e.g., knowledge base and domain heuristics. These annotations, referred as heterogeneous supervision, often conflict with each other, which brings a new challenge to the original relation extraction task: how to infer the true label from noisy labels for a given instance. Identifying context information as the backbone of both relation extraction and true label discovery, we adopt embedding techniques to learn the distributed representations of context, which bridges all components with mutual enhancement in an iterative fashion. Extensive experimental results demonstrate the superiority of REHESSION over the state-of-the-art.

UR - http://www.scopus.com/inward/record.url?scp=85040545083&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040545083&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85040545083

T3 - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

SP - 46

EP - 56

BT - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

PB - Association for Computational Linguistics (ACL)

ER -