Recognizing mentions of adverse drug reaction in social media using knowledge-infused recurrent models

Gabriel Stanovsky; Daniel Gruhl; Pablo N. Mendes

doi:10.18653/v1/e17-1014

Recognizing mentions of adverse drug reaction in social media using knowledge-infused recurrent models

Gabriel Stanovsky, Daniel Gruhl, Pablo N. Mendes

Department of Computer Science

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

54 Scopus citations

Abstract

Recognizing mentions of Adverse Drug Reactions (ADR) in social media is challenging: ADR mentions are contextdependent and include long, varied and unconventional descriptions as compared to more formal medical symptom terminology. We use the CADEC corpus to train a recurrent neural network (RNN) transducer, integrated with knowledge graph embeddings of DBpedia, and show the resulting model to be highly accurate (93.4 F1). Furthermore, even when lacking high quality expert annotations, we show that by employing an active learning technique and using purpose built annotation tools, we can train the RNN to perform well (83.9 F1).

Original language	English
Title of host publication	Long Papers
Publisher	Association for Computational Linguistics (ACL)
Pages	142-151
Number of pages	10
ISBN (Electronic)	9781510838604
DOIs	https://doi.org/10.18653/v1/e17-1014
State	Published - 2017
Event	15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Valencia, Spain Duration: 3 Apr 2017 → 7 Apr 2017

Publication series

Name	15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference
Volume	1

Conference

Conference	15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017
Country/Territory	Spain
City	Valencia
Period	3/04/17 → 7/04/17

Bibliographical note

Publisher Copyright:
© 2017 Association for Computational Linguistics.

Access to Document

10.18653/v1/e17-1014

Cite this

Stanovsky, G., Gruhl, D., & Mendes, P. N. (2017). Recognizing mentions of adverse drug reaction in social media using knowledge-infused recurrent models. In Long Papers (pp. 142-151). (15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference; Vol. 1). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/e17-1014

Stanovsky, Gabriel ; Gruhl, Daniel ; Mendes, Pablo N. / Recognizing mentions of adverse drug reaction in social media using knowledge-infused recurrent models. Long Papers. Association for Computational Linguistics (ACL), 2017. pp. 142-151 (15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference).

@inproceedings{4b58e722cc7843249c868d1c67d8bb77,

title = "Recognizing mentions of adverse drug reaction in social media using knowledge-infused recurrent models",

abstract = "Recognizing mentions of Adverse Drug Reactions (ADR) in social media is challenging: ADR mentions are contextdependent and include long, varied and unconventional descriptions as compared to more formal medical symptom terminology. We use the CADEC corpus to train a recurrent neural network (RNN) transducer, integrated with knowledge graph embeddings of DBpedia, and show the resulting model to be highly accurate (93.4 F1). Furthermore, even when lacking high quality expert annotations, we show that by employing an active learning technique and using purpose built annotation tools, we can train the RNN to perform well (83.9 F1).",

author = "Gabriel Stanovsky and Daniel Gruhl and Mendes, {Pablo N.}",

note = "Publisher Copyright: {\textcopyright} 2017 Association for Computational Linguistics.; 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 ; Conference date: 03-04-2017 Through 07-04-2017",

year = "2017",

doi = "10.18653/v1/e17-1014",

language = "אנגלית",

series = "15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference",

publisher = "Association for Computational Linguistics (ACL)",

pages = "142--151",

booktitle = "Long Papers",

address = "ארצות הברית",

}

Stanovsky, G, Gruhl, D & Mendes, PN 2017, Recognizing mentions of adverse drug reaction in social media using knowledge-infused recurrent models. in Long Papers. 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference, vol. 1, Association for Computational Linguistics (ACL), pp. 142-151, 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017, Valencia, Spain, 3/04/17. https://doi.org/10.18653/v1/e17-1014

Recognizing mentions of adverse drug reaction in social media using knowledge-infused recurrent models. / Stanovsky, Gabriel; Gruhl, Daniel; Mendes, Pablo N.
Long Papers. Association for Computational Linguistics (ACL), 2017. p. 142-151 (15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference; Vol. 1).

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

TY - GEN

T1 - Recognizing mentions of adverse drug reaction in social media using knowledge-infused recurrent models

AU - Stanovsky, Gabriel

AU - Gruhl, Daniel

AU - Mendes, Pablo N.

PY - 2017

Y1 - 2017

N2 - Recognizing mentions of Adverse Drug Reactions (ADR) in social media is challenging: ADR mentions are contextdependent and include long, varied and unconventional descriptions as compared to more formal medical symptom terminology. We use the CADEC corpus to train a recurrent neural network (RNN) transducer, integrated with knowledge graph embeddings of DBpedia, and show the resulting model to be highly accurate (93.4 F1). Furthermore, even when lacking high quality expert annotations, we show that by employing an active learning technique and using purpose built annotation tools, we can train the RNN to perform well (83.9 F1).

AB - Recognizing mentions of Adverse Drug Reactions (ADR) in social media is challenging: ADR mentions are contextdependent and include long, varied and unconventional descriptions as compared to more formal medical symptom terminology. We use the CADEC corpus to train a recurrent neural network (RNN) transducer, integrated with knowledge graph embeddings of DBpedia, and show the resulting model to be highly accurate (93.4 F1). Furthermore, even when lacking high quality expert annotations, we show that by employing an active learning technique and using purpose built annotation tools, we can train the RNN to perform well (83.9 F1).

UR - http://www.scopus.com/inward/record.url?scp=85021649640&partnerID=8YFLogxK

U2 - 10.18653/v1/e17-1014

DO - 10.18653/v1/e17-1014

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85021649640

T3 - 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference

SP - 142

EP - 151

BT - Long Papers

PB - Association for Computational Linguistics (ACL)

T2 - 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017

Y2 - 3 April 2017 through 7 April 2017

ER -

Stanovsky G, Gruhl D, Mendes PN. Recognizing mentions of adverse drug reaction in social media using knowledge-infused recurrent models. In Long Papers. Association for Computational Linguistics (ACL). 2017. p. 142-151. (15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference). doi: 10.18653/v1/e17-1014

Recognizing mentions of adverse drug reaction in social media using knowledge-infused recurrent models

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this