UoB at ProfNER 2021: data augmentation for classification using machine translation

Frances Adriana Laureano De Leon; Harish Tayyar Madabushi; Mark Lee

doi:10.18653/v1/2021.smm4h-1.23

UoB at ProfNER 2021: data augmentation for classification using machine translation

Frances Adriana Laureano De Leon, Harish Tayyar Madabushi, Mark Lee

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

23 Downloads (Pure)

Abstract

This paper describes the participation of the UoB-NLP team in the ProfNER-ST shared subtask 7a. The task was aimed at detecting the mention of professions in social media text. Our team experimented with two methods of improving the performance of pre-trained models: Specifically, we experimented with data augmentation through translation and the merging of multiple language inputs to meet the objective of the task. While the best performing model on the test data consisted of mBERT fine-tuned on augmented data using back-translation, the improvement is minor possibly because multi-lingual pre-trained models such as mBERT already have access to the kind of information provided through back-translation and bilingual data.

Original language	English
Title of host publication	Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task
Editors	Arjun Magge, Ari Klein, Antonio Miranda-Escalada, Mohammed Ali Al-garadi, Ilseyar Alimova, Zulfat Miftahutdinov, Eulalia Farre-Maduell, Salvador Lima-Lopez, Ivan Flores, Karen O'Connor, Davy Weissenbacher, Elena Tutubalina, Abeed Sarker, Juan M Banda, Martin Krallinger, Graciela Gonzalez-Hernandez
Publisher	Association for Computational Linguistics, ACL
Pages	115–117
Number of pages	3
ISBN (Electronic)	9781954085312
DOIs	https://doi.org/10.18653/v1/2021.smm4h-1.23
Publication status	Published - 10 Jun 2021
Event	Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task - Mexico City, Mexico and Online, Mexico City, Mexico Duration: 10 Jun 2021 → 10 Jun 2021 Conference number: 6th

Publication series

Name	Social Media Mining for Health (SMM4H)

Conference

Conference	Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task
Country/Territory	Mexico
City	Mexico City
Period	10/06/21 → 10/06/21

Bibliographical note

Publisher Copyright:
© 2021 Association for Computational Linguistics.

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Networks and Communications
Hardware and Architecture
Information Systems
Software

Access to Document

10.18653/v1/2021.smm4h-1.23Licence: Creative Commons: Attribution (CC BY)

LaureanoDeLeonFA2021UoBFinal published version, 123 KBLicence: Creative Commons: Attribution (CC BY)

Cite this

Laureano De Leon, F. A., Tayyar Madabushi, H., & Lee, M. (2021). UoB at ProfNER 2021: data augmentation for classification using machine translation. In A. Magge, A. Klein, A. Miranda-Escalada, M. A. Al-garadi, I. Alimova, Z. Miftahutdinov, E. Farre-Maduell, S. Lima-Lopez, I. Flores, K. O'Connor, D. Weissenbacher, E. Tutubalina, A. Sarker, J. M. Banda, M. Krallinger, & G. Gonzalez-Hernandez (Eds.), Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task (pp. 115–117). (Social Media Mining for Health (SMM4H)). Association for Computational Linguistics, ACL. https://doi.org/10.18653/v1/2021.smm4h-1.23

Laureano De Leon, Frances Adriana ; Tayyar Madabushi, Harish ; Lee, Mark. / UoB at ProfNER 2021 : data augmentation for classification using machine translation. Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task. editor / Arjun Magge ; Ari Klein ; Antonio Miranda-Escalada ; Mohammed Ali Al-garadi ; Ilseyar Alimova ; Zulfat Miftahutdinov ; Eulalia Farre-Maduell ; Salvador Lima-Lopez ; Ivan Flores ; Karen O'Connor ; Davy Weissenbacher ; Elena Tutubalina ; Abeed Sarker ; Juan M Banda ; Martin Krallinger ; Graciela Gonzalez-Hernandez. Association for Computational Linguistics, ACL, 2021. pp. 115–117 (Social Media Mining for Health (SMM4H)).

@inproceedings{31e01586ec24450caf503fa153126777,

title = "UoB at ProfNER 2021: data augmentation for classification using machine translation",

abstract = "This paper describes the participation of the UoB-NLP team in the ProfNER-ST shared subtask 7a. The task was aimed at detecting the mention of professions in social media text. Our team experimented with two methods of improving the performance of pre-trained models: Specifically, we experimented with data augmentation through translation and the merging of multiple language inputs to meet the objective of the task. While the best performing model on the test data consisted of mBERT fine-tuned on augmented data using back-translation, the improvement is minor possibly because multi-lingual pre-trained models such as mBERT already have access to the kind of information provided through back-translation and bilingual data.",

author = "{Laureano De Leon}, {Frances Adriana} and {Tayyar Madabushi}, Harish and Mark Lee",

note = "Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics.; Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task ; Conference date: 10-06-2021 Through 10-06-2021",

year = "2021",

month = jun,

day = "10",

doi = "10.18653/v1/2021.smm4h-1.23",

language = "English",

series = "Social Media Mining for Health (SMM4H)",

publisher = "Association for Computational Linguistics, ACL",

pages = "115–117",

editor = "Arjun Magge and Ari Klein and Antonio Miranda-Escalada and Al-garadi, {Mohammed Ali } and Ilseyar Alimova and Zulfat Miftahutdinov and Eulalia Farre-Maduell and Salvador Lima-Lopez and Ivan Flores and Karen O'Connor and Davy Weissenbacher and Elena Tutubalina and Abeed Sarker and Banda, {Juan M} and Martin Krallinger and Gonzalez-Hernandez, {Graciela }",

booktitle = "Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task",

}

Laureano De Leon, FA, Tayyar Madabushi, H & Lee, M 2021, UoB at ProfNER 2021: data augmentation for classification using machine translation. in A Magge, A Klein, A Miranda-Escalada, MA Al-garadi, I Alimova, Z Miftahutdinov, E Farre-Maduell, S Lima-Lopez, I Flores, K O'Connor, D Weissenbacher, E Tutubalina, A Sarker, JM Banda, M Krallinger & G Gonzalez-Hernandez (eds), Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task. Social Media Mining for Health (SMM4H), Association for Computational Linguistics, ACL, pp. 115–117, Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task, Mexico City, Mexico, 10/06/21. https://doi.org/10.18653/v1/2021.smm4h-1.23

UoB at ProfNER 2021: data augmentation for classification using machine translation. / Laureano De Leon, Frances Adriana; Tayyar Madabushi, Harish; Lee, Mark.
Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task. ed. / Arjun Magge; Ari Klein; Antonio Miranda-Escalada; Mohammed Ali Al-garadi; Ilseyar Alimova; Zulfat Miftahutdinov; Eulalia Farre-Maduell; Salvador Lima-Lopez; Ivan Flores; Karen O'Connor; Davy Weissenbacher; Elena Tutubalina; Abeed Sarker; Juan M Banda; Martin Krallinger; Graciela Gonzalez-Hernandez. Association for Computational Linguistics, ACL, 2021. p. 115–117 (Social Media Mining for Health (SMM4H)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - UoB at ProfNER 2021

T2 - Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task

AU - Laureano De Leon, Frances Adriana

AU - Tayyar Madabushi, Harish

AU - Lee, Mark

N1 - Conference code: 6th

PY - 2021/6/10

Y1 - 2021/6/10

N2 - This paper describes the participation of the UoB-NLP team in the ProfNER-ST shared subtask 7a. The task was aimed at detecting the mention of professions in social media text. Our team experimented with two methods of improving the performance of pre-trained models: Specifically, we experimented with data augmentation through translation and the merging of multiple language inputs to meet the objective of the task. While the best performing model on the test data consisted of mBERT fine-tuned on augmented data using back-translation, the improvement is minor possibly because multi-lingual pre-trained models such as mBERT already have access to the kind of information provided through back-translation and bilingual data.

AB - This paper describes the participation of the UoB-NLP team in the ProfNER-ST shared subtask 7a. The task was aimed at detecting the mention of professions in social media text. Our team experimented with two methods of improving the performance of pre-trained models: Specifically, we experimented with data augmentation through translation and the merging of multiple language inputs to meet the objective of the task. While the best performing model on the test data consisted of mBERT fine-tuned on augmented data using back-translation, the improvement is minor possibly because multi-lingual pre-trained models such as mBERT already have access to the kind of information provided through back-translation and bilingual data.

UR - http://www.scopus.com/inward/record.url?scp=85138223990&partnerID=8YFLogxK

U2 - 10.18653/v1/2021.smm4h-1.23

DO - 10.18653/v1/2021.smm4h-1.23

M3 - Conference contribution

T3 - Social Media Mining for Health (SMM4H)

SP - 115

EP - 117

BT - Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task

A2 - Magge, Arjun

A2 - Klein, Ari

A2 - Miranda-Escalada, Antonio

A2 - Al-garadi, Mohammed Ali

A2 - Alimova, Ilseyar

A2 - Miftahutdinov, Zulfat

A2 - Farre-Maduell, Eulalia

A2 - Lima-Lopez, Salvador

A2 - Flores, Ivan

A2 - O'Connor, Karen

A2 - Weissenbacher, Davy

A2 - Tutubalina, Elena

A2 - Sarker, Abeed

A2 - Banda, Juan M

A2 - Krallinger, Martin

A2 - Gonzalez-Hernandez, Graciela

PB - Association for Computational Linguistics, ACL

Y2 - 10 June 2021 through 10 June 2021

ER -

Laureano De Leon FA, Tayyar Madabushi H, Lee M. UoB at ProfNER 2021: data augmentation for classification using machine translation. In Magge A, Klein A, Miranda-Escalada A, Al-garadi MA, Alimova I, Miftahutdinov Z, Farre-Maduell E, Lima-Lopez S, Flores I, O'Connor K, Weissenbacher D, Tutubalina E, Sarker A, Banda JM, Krallinger M, Gonzalez-Hernandez G, editors, Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task. Association for Computational Linguistics, ACL. 2021. p. 115–117. (Social Media Mining for Health (SMM4H)). doi: 10.18653/v1/2021.smm4h-1.23

UoB at ProfNER 2021: data augmentation for classification using machine translation

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this