Home > Research > Publications & Outputs > Learning with noise

Research

Associated organisational units

Electronic data

  • acl2017

    Accepted author manuscript, 3.28 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Learning with noise: enhance distantly supervised relation extraction with dynamic transition matrix

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Learning with noise: enhance distantly supervised relation extraction with dynamic transition matrix. / Luo, Binfeng; Feng, Yansong; Wang, Zheng et al.
The 55th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 1 (Long Papers). Stroudsburg, Pa.: Association for Computational Linguistics, 2017. P-17 1040.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Luo, B, Feng, Y, Wang, Z, Zhu, Z, Huang, S, Yan, R & Zhao, D 2017, Learning with noise: enhance distantly supervised relation extraction with dynamic transition matrix. in The 55th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 1 (Long Papers)., P-17 1040, Association for Computational Linguistics, Stroudsburg, Pa., Annual Meeting of the Association for Computational Linguistics, Vancouver, Canada, 30/07/17. https://doi.org/10.18653/v1/P17-1040

APA

Luo, B., Feng, Y., Wang, Z., Zhu, Z., Huang, S., Yan, R., & Zhao, D. (2017). Learning with noise: enhance distantly supervised relation extraction with dynamic transition matrix. In The 55th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 1 (Long Papers) Article P-17 1040 Association for Computational Linguistics. https://doi.org/10.18653/v1/P17-1040

Vancouver

Luo B, Feng Y, Wang Z, Zhu Z, Huang S, Yan R et al. Learning with noise: enhance distantly supervised relation extraction with dynamic transition matrix. In The 55th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 1 (Long Papers). Stroudsburg, Pa.: Association for Computational Linguistics. 2017. P-17 1040 doi: 10.18653/v1/P17-1040

Author

Luo, Binfeng ; Feng, Yansong ; Wang, Zheng et al. / Learning with noise : enhance distantly supervised relation extraction with dynamic transition matrix. The 55th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 1 (Long Papers). Stroudsburg, Pa. : Association for Computational Linguistics, 2017.

Bibtex

@inproceedings{b9ee1b4f4f9e4028941019ec93056ab6,
title = "Learning with noise: enhance distantly supervised relation extraction with dynamic transition matrix",
abstract = "Distant supervision significantly reduces human efforts in building training data for many classification tasks. While promising, this technique often introduces noise to the generated training data, which can severely affect the model performance. In this paper, we take a deep look at the application of distant supervision in relation extraction.We show that the dynamic transition matrix can effectively characterize the noise in the training data built by distant supervision. The transition matrix can be effectively trained using a novel curriculum learning based method without any direct supervision about the noise. We thoroughly evaluate our approach under a wide range of extraction scenarios. Experimental results show that our approach consistently improves the extraction results and outperforms the state-of-the-art in various evaluation scenarios.",
author = "Binfeng Luo and Yansong Feng and Zheng Wang and Zhanxing Zhu and Songfang Huang and Rui Yan and Dongyan Zhao",
year = "2017",
month = jul,
day = "30",
doi = "10.18653/v1/P17-1040",
language = "English",
isbn = "9781945626753",
booktitle = "The 55th Annual Meeting of the Association for Computational Linguistics",
publisher = "Association for Computational Linguistics",
note = "Annual Meeting of the Association for Computational Linguistics, ACL 2017 ; Conference date: 30-07-2017 Through 04-08-2017",
url = "http://acl2017.org/",

}

RIS

TY - GEN

T1 - Learning with noise

T2 - Annual Meeting of the Association for Computational Linguistics

AU - Luo, Binfeng

AU - Feng, Yansong

AU - Wang, Zheng

AU - Zhu, Zhanxing

AU - Huang, Songfang

AU - Yan, Rui

AU - Zhao, Dongyan

PY - 2017/7/30

Y1 - 2017/7/30

N2 - Distant supervision significantly reduces human efforts in building training data for many classification tasks. While promising, this technique often introduces noise to the generated training data, which can severely affect the model performance. In this paper, we take a deep look at the application of distant supervision in relation extraction.We show that the dynamic transition matrix can effectively characterize the noise in the training data built by distant supervision. The transition matrix can be effectively trained using a novel curriculum learning based method without any direct supervision about the noise. We thoroughly evaluate our approach under a wide range of extraction scenarios. Experimental results show that our approach consistently improves the extraction results and outperforms the state-of-the-art in various evaluation scenarios.

AB - Distant supervision significantly reduces human efforts in building training data for many classification tasks. While promising, this technique often introduces noise to the generated training data, which can severely affect the model performance. In this paper, we take a deep look at the application of distant supervision in relation extraction.We show that the dynamic transition matrix can effectively characterize the noise in the training data built by distant supervision. The transition matrix can be effectively trained using a novel curriculum learning based method without any direct supervision about the noise. We thoroughly evaluate our approach under a wide range of extraction scenarios. Experimental results show that our approach consistently improves the extraction results and outperforms the state-of-the-art in various evaluation scenarios.

U2 - 10.18653/v1/P17-1040

DO - 10.18653/v1/P17-1040

M3 - Conference contribution/Paper

SN - 9781945626753

BT - The 55th Annual Meeting of the Association for Computational Linguistics

PB - Association for Computational Linguistics

CY - Stroudsburg, Pa.

Y2 - 30 July 2017 through 4 August 2017

ER -