A Deep Learning-Based System for PharmaCoNER

Ying Xiong; Yedan Shen; Yuanhang Huang; Shuai Chen; Buzhou Tang; Xiaolong Wang; Qingcai Chen; Jun Yan; Yi Zhou

doi:10.18653/v1/d19-5706

A Deep Learning-Based System for PharmaCoNER

Ying Xiong
, Yedan Shen
, Yuanhang Huang
, Shuai Chen
, Buzhou Tang^*
, Xiaolong Wang
, Qingcai Chen
, Jun Yan
, Yi Zhou^*

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

11 Citations (Scopus)

1 Downloads (CityUHK Scholars)

Abstract

The Biological Text Mining Unit at BSC and CNIO organized the first shared task on chemical & drug mention recognition from Spanish medical texts called PharmaCoNER (Pharmacological Substances, Compounds and proteins and Named Entity Recognition track) in 2019. The shared task includes two tracks: one for NER offset and entity classification (track 1) and the other one for concept indexing (track 2). We developed a pipeline system based on deep learning methods for this shared task, specifically, a subsystem based on BERT (Bidirectional Encoder Representations from Transformers) for NER offset and entity classification and a subsystem based on Bpool (Bi-LSTM with max/mean pooling) for concept indexing. Evaluation conducted on the shared task data showed that our system achieves a micro-average F1-score of 0.9105 on track 1 and a microaverage F1-score of 0.8391 on track 2. © 2019 Association for Computational Linguistics. © 2019 BioNLP-OST@EMNLP-IJNCLP 2019 - Proceedings of the 5th Workshop on BioNLP Open Shared Tasks. All rights reserved.

Original language	English
Title of host publication	BioNLP-OST@EMNLP-IJNCLP 2019 - Proceedings of the 5th Workshop on BioNLP Open Shared Tasks
Editors	Jin-Dong Kim, Claire Nédellec, Robert Bossy, Louise Deléger
Place of Publication	Stroudsburg, PA
Publisher	Association for Computational Linguistics
Pages	33-37
Number of pages	5
ISBN (Print)	9781950737826
DOIs	https://doi.org/10.18653/v1/d19-5706
Publication status	Published - Nov 2019
Externally published	Yes
Event	5th Workshop on BioNLP Open Shared Tasks (BioNLP-OST 2019) - Hong Kong, China Duration: 4 Nov 2019 → … https://aclanthology.org/volumes/D19-57/

Publication series

Name	BioNLP-OST - EMNLP-IJNCLP - Proceedings of the Workshop on BioNLP

Conference

Conference	5th Workshop on BioNLP Open Shared Tasks (BioNLP-OST 2019)
Place	China
City	Hong Kong
Period	4/11/19 → …
Internet address	https://aclanthology.org/volumes/D19-57/

Funding

This paper is supported in part by grants: NSFCs (National Natural Science Foundations of China) (U1813215, 61876052 and 61573118), Special Foundation for Tecogy hRenescaoPhorlar gofmr Guangdong Province (2015B010131010), Strategic Emerging Industry Development Special Funds of Shenzhen (JCYJ20170307150528934 and JCYJ20180306172232154), Innovation Fund of Harbin Institute of Tecogy hnol (HI.TSNRI.F0217052).

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Access Output

10.18653/v1/d19-5706

335445811.pdfFinal Published version, 259 KBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Xiong, Y., Shen, Y., Huang, Y., Chen, S., Tang, B., Wang, X., Chen, Q., Yan, J., & Zhou, Y. (2019). A Deep Learning-Based System for PharmaCoNER. In J.-D. Kim, C. Nédellec, R. Bossy, & L. Deléger (Eds.), BioNLP-OST@EMNLP-IJNCLP 2019 - Proceedings of the 5th Workshop on BioNLP Open Shared Tasks (pp. 33-37). (BioNLP-OST - EMNLP-IJNCLP - Proceedings of the Workshop on BioNLP). Association for Computational Linguistics. https://doi.org/10.18653/v1/d19-5706

Xiong, Ying ; Shen, Yedan ; Huang, Yuanhang et al. / A Deep Learning-Based System for PharmaCoNER. BioNLP-OST@EMNLP-IJNCLP 2019 - Proceedings of the 5th Workshop on BioNLP Open Shared Tasks. editor / Jin-Dong Kim ; Claire Nédellec ; Robert Bossy ; Louise Deléger. Stroudsburg, PA : Association for Computational Linguistics, 2019. pp. 33-37 (BioNLP-OST - EMNLP-IJNCLP - Proceedings of the Workshop on BioNLP).

@inproceedings{dd00590b0a2442e3aed8c2a6b0dbebdb,

title = "A Deep Learning-Based System for PharmaCoNER",

abstract = "The Biological Text Mining Unit at BSC and CNIO organized the first shared task on chemical \& drug mention recognition from Spanish medical texts called PharmaCoNER (Pharmacological Substances, Compounds and proteins and Named Entity Recognition track) in 2019. The shared task includes two tracks: one for NER offset and entity classification (track 1) and the other one for concept indexing (track 2). We developed a pipeline system based on deep learning methods for this shared task, specifically, a subsystem based on BERT (Bidirectional Encoder Representations from Transformers) for NER offset and entity classification and a subsystem based on Bpool (Bi-LSTM with max/mean pooling) for concept indexing. Evaluation conducted on the shared task data showed that our system achieves a micro-average F1-score of 0.9105 on track 1 and a microaverage F1-score of 0.8391 on track 2. {\textcopyright} 2019 Association for Computational Linguistics. {\textcopyright} 2019 BioNLP-OST@EMNLP-IJNCLP 2019 - Proceedings of the 5th Workshop on BioNLP Open Shared Tasks. All rights reserved.",

author = "Ying Xiong and Yedan Shen and Yuanhang Huang and Shuai Chen and Buzhou Tang and Xiaolong Wang and Qingcai Chen and Jun Yan and Yi Zhou",

year = "2019",

month = nov,

doi = "10.18653/v1/d19-5706",

language = "English",

isbn = "9781950737826",

series = "BioNLP-OST - EMNLP-IJNCLP - Proceedings of the Workshop on BioNLP",

publisher = "Association for Computational Linguistics",

pages = "33--37",

editor = "Jin-Dong Kim and Claire N{\'e}dellec and Robert Bossy and Louise Del{\'e}ger",

booktitle = "BioNLP-OST@EMNLP-IJNCLP 2019 - Proceedings of the 5th Workshop on BioNLP Open Shared Tasks",

address = "United States",

note = "5th Workshop on BioNLP Open Shared Tasks (BioNLP-OST 2019) ; Conference date: 04-11-2019",

url = "https://aclanthology.org/volumes/D19-57/",

}

Xiong, Y, Shen, Y, Huang, Y, Chen, S, Tang, B, Wang, X, Chen, Q, Yan, J & Zhou, Y 2019, A Deep Learning-Based System for PharmaCoNER. in J-D Kim, C Nédellec, R Bossy & L Deléger (eds), BioNLP-OST@EMNLP-IJNCLP 2019 - Proceedings of the 5th Workshop on BioNLP Open Shared Tasks. BioNLP-OST - EMNLP-IJNCLP - Proceedings of the Workshop on BioNLP, Association for Computational Linguistics, Stroudsburg, PA, pp. 33-37, 5th Workshop on BioNLP Open Shared Tasks (BioNLP-OST 2019), Hong Kong, China, 4/11/19. https://doi.org/10.18653/v1/d19-5706

A Deep Learning-Based System for PharmaCoNER. / Xiong, Ying; Shen, Yedan; Huang, Yuanhang et al.
BioNLP-OST@EMNLP-IJNCLP 2019 - Proceedings of the 5th Workshop on BioNLP Open Shared Tasks. ed. / Jin-Dong Kim; Claire Nédellec; Robert Bossy; Louise Deléger. Stroudsburg, PA: Association for Computational Linguistics, 2019. p. 33-37 (BioNLP-OST - EMNLP-IJNCLP - Proceedings of the Workshop on BioNLP).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - A Deep Learning-Based System for PharmaCoNER

AU - Xiong, Ying

AU - Shen, Yedan

AU - Huang, Yuanhang

AU - Chen, Shuai

AU - Tang, Buzhou

AU - Wang, Xiaolong

AU - Chen, Qingcai

AU - Yan, Jun

AU - Zhou, Yi

PY - 2019/11

Y1 - 2019/11

N2 - The Biological Text Mining Unit at BSC and CNIO organized the first shared task on chemical & drug mention recognition from Spanish medical texts called PharmaCoNER (Pharmacological Substances, Compounds and proteins and Named Entity Recognition track) in 2019. The shared task includes two tracks: one for NER offset and entity classification (track 1) and the other one for concept indexing (track 2). We developed a pipeline system based on deep learning methods for this shared task, specifically, a subsystem based on BERT (Bidirectional Encoder Representations from Transformers) for NER offset and entity classification and a subsystem based on Bpool (Bi-LSTM with max/mean pooling) for concept indexing. Evaluation conducted on the shared task data showed that our system achieves a micro-average F1-score of 0.9105 on track 1 and a microaverage F1-score of 0.8391 on track 2. © 2019 Association for Computational Linguistics. © 2019 BioNLP-OST@EMNLP-IJNCLP 2019 - Proceedings of the 5th Workshop on BioNLP Open Shared Tasks. All rights reserved.

AB - The Biological Text Mining Unit at BSC and CNIO organized the first shared task on chemical & drug mention recognition from Spanish medical texts called PharmaCoNER (Pharmacological Substances, Compounds and proteins and Named Entity Recognition track) in 2019. The shared task includes two tracks: one for NER offset and entity classification (track 1) and the other one for concept indexing (track 2). We developed a pipeline system based on deep learning methods for this shared task, specifically, a subsystem based on BERT (Bidirectional Encoder Representations from Transformers) for NER offset and entity classification and a subsystem based on Bpool (Bi-LSTM with max/mean pooling) for concept indexing. Evaluation conducted on the shared task data showed that our system achieves a micro-average F1-score of 0.9105 on track 1 and a microaverage F1-score of 0.8391 on track 2. © 2019 Association for Computational Linguistics. © 2019 BioNLP-OST@EMNLP-IJNCLP 2019 - Proceedings of the 5th Workshop on BioNLP Open Shared Tasks. All rights reserved.

UR - https://www.scopus.com/pages/publications/85092232640

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85092232640&origin=recordpage

U2 - 10.18653/v1/d19-5706

DO - 10.18653/v1/d19-5706

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781950737826

T3 - BioNLP-OST - EMNLP-IJNCLP - Proceedings of the Workshop on BioNLP

SP - 33

EP - 37

BT - BioNLP-OST@EMNLP-IJNCLP 2019 - Proceedings of the 5th Workshop on BioNLP Open Shared Tasks

A2 - Kim, Jin-Dong

A2 - Nédellec, Claire

A2 - Bossy, Robert

A2 - Deléger, Louise

PB - Association for Computational Linguistics

CY - Stroudsburg, PA

T2 - 5th Workshop on BioNLP Open Shared Tasks (BioNLP-OST 2019)

Y2 - 4 November 2019

ER -

Xiong Y, Shen Y, Huang Y, Chen S, Tang B, Wang X et al. A Deep Learning-Based System for PharmaCoNER. In Kim JD, Nédellec C, Bossy R, Deléger L, editors, BioNLP-OST@EMNLP-IJNCLP 2019 - Proceedings of the 5th Workshop on BioNLP Open Shared Tasks. Stroudsburg, PA: Association for Computational Linguistics. 2019. p. 33-37. (BioNLP-OST - EMNLP-IJNCLP - Proceedings of the Workshop on BioNLP). doi: 10.18653/v1/d19-5706

A Deep Learning-Based System for PharmaCoNER

Abstract

Publication series

Conference

Funding

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this