NCUEE at MEDIQA 2019: Medical text inference using ensemble BERT-BiLSTM-attention model

Lung Hao Lee; Yi Lu; Po Han Chen; Po Lei Lee; Kuo Kai Shyu

NCUEE at MEDIQA 2019: Medical text inference using ensemble BERT-BiLSTM-attention model

Lung Hao Lee, Yi Lu, Po Han Chen, Po Lei Lee, Kuo Kai Shyu

電機工程學系

研究成果: 書貢獻/報告類型 › 會議論文篇章 › 同行評審

18 引文斯高帕斯（Scopus）

摘要

This study describes the model design of the NCUEE system for the MEDIQA challenge at the ACL-BioNLP 2019 workshop. We use the BERT (Bidirectional Encoder Representations from Transformers) as the word embedding method to integrate the BiLSTM (Bidirectional Long Short-Term Memory) network with an attention mechanism for medical text inferences. A total of 42 teams participated in natural language inference task at MEDIQA 2019. Our best accuracy score of 0.84 ranked the top-third among all submissions in the leaderboard.

原文	???core.languages.en_GB???
主出版物標題	BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task
發行者	Association for Computational Linguistics (ACL)
頁面	528-532
頁數	5
ISBN（電子）	9781950737284
出版狀態	已出版 - 2019
事件	18th SIGBioMed Workshop on Biomedical Natural Language Processing, BioNLP 2019 - Florence, Italy 持續時間: 1 8月 2019 → …

出版系列

名字	BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	18th SIGBioMed Workshop on Biomedical Natural Language Processing, BioNLP 2019
國家/地區	Italy
城市	Florence
期間	1/08/19 → …

中文醫療健康照護知識庫建置與應用(3/3)
Lee, L.-H. (PI)
1/05/21 → 31/07/22
研究計畫: Research
應用於居家照護之智慧型互動平台－應用於醫療場域及居家照護之智慧型互動平台- 以人工智慧為核心之腦波人機介面開發(2/4)
Shyu, K.-K. (PI)
1/01/19 → 31/12/19
研究計畫: Research

引用此

Lee, L. H., Lu, Y., Chen, P. H., Lee, P. L., & Shyu, K. K. (2019). NCUEE at MEDIQA 2019: Medical text inference using ensemble BERT-BiLSTM-attention model. 於 BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task (頁 528-532). (BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task). Association for Computational Linguistics (ACL).

Lee, Lung Hao ; Lu, Yi ; Chen, Po Han 等. / NCUEE at MEDIQA 2019 : Medical text inference using ensemble BERT-BiLSTM-attention model. BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task. Association for Computational Linguistics (ACL), 2019. 頁 528-532 (BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task).

@inproceedings{5dc0c3d55b524ab7aa9fd1ee1a728ee0,

title = "NCUEE at MEDIQA 2019: Medical text inference using ensemble BERT-BiLSTM-attention model",

abstract = "This study describes the model design of the NCUEE system for the MEDIQA challenge at the ACL-BioNLP 2019 workshop. We use the BERT (Bidirectional Encoder Representations from Transformers) as the word embedding method to integrate the BiLSTM (Bidirectional Long Short-Term Memory) network with an attention mechanism for medical text inferences. A total of 42 teams participated in natural language inference task at MEDIQA 2019. Our best accuracy score of 0.84 ranked the top-third among all submissions in the leaderboard.",

author = "Lee, {Lung Hao} and Yi Lu and Chen, {Po Han} and Lee, {Po Lei} and Shyu, {Kuo Kai}",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computational Linguistics; 18th SIGBioMed Workshop on Biomedical Natural Language Processing, BioNLP 2019 ; Conference date: 01-08-2019",

year = "2019",

language = "???core.languages.en_GB???",

series = "BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task",

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

pages = "528--532",

booktitle = "BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task",

}

Lee, LH, Lu, Y, Chen, PH, Lee, PL & Shyu, KK 2019, NCUEE at MEDIQA 2019: Medical text inference using ensemble BERT-BiLSTM-attention model. 於 BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task. BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task, Association for Computational Linguistics (ACL), 頁 528-532, 18th SIGBioMed Workshop on Biomedical Natural Language Processing, BioNLP 2019, Florence, Italy, 1/08/19.

NCUEE at MEDIQA 2019: Medical text inference using ensemble BERT-BiLSTM-attention model. / Lee, Lung Hao; Lu, Yi; Chen, Po Han 等.
BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task. Association for Computational Linguistics (ACL), 2019. p. 528-532 (BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task).

研究成果: 書貢獻/報告類型 › 會議論文篇章 › 同行評審

TY - GEN

T1 - NCUEE at MEDIQA 2019

T2 - 18th SIGBioMed Workshop on Biomedical Natural Language Processing, BioNLP 2019

AU - Lee, Lung Hao

AU - Lu, Yi

AU - Chen, Po Han

AU - Lee, Po Lei

AU - Shyu, Kuo Kai

PY - 2019

Y1 - 2019

N2 - This study describes the model design of the NCUEE system for the MEDIQA challenge at the ACL-BioNLP 2019 workshop. We use the BERT (Bidirectional Encoder Representations from Transformers) as the word embedding method to integrate the BiLSTM (Bidirectional Long Short-Term Memory) network with an attention mechanism for medical text inferences. A total of 42 teams participated in natural language inference task at MEDIQA 2019. Our best accuracy score of 0.84 ranked the top-third among all submissions in the leaderboard.

AB - This study describes the model design of the NCUEE system for the MEDIQA challenge at the ACL-BioNLP 2019 workshop. We use the BERT (Bidirectional Encoder Representations from Transformers) as the word embedding method to integrate the BiLSTM (Bidirectional Long Short-Term Memory) network with an attention mechanism for medical text inferences. A total of 42 teams participated in natural language inference task at MEDIQA 2019. Our best accuracy score of 0.84 ranked the top-third among all submissions in the leaderboard.

UR - http://www.scopus.com/inward/record.url?scp=85090095778&partnerID=8YFLogxK

M3 - 會議論文篇章

AN - SCOPUS:85090095778

T3 - BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task

SP - 528

EP - 532

BT - BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task

PB - Association for Computational Linguistics (ACL)

Y2 - 1 August 2019

ER -

Lee LH, Lu Y, Chen PH, Lee PL , Shyu KK. NCUEE at MEDIQA 2019: Medical text inference using ensemble BERT-BiLSTM-attention model. 於 BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task. Association for Computational Linguistics (ACL). 2019. p. 528-532. (BioNLP 2019 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 18th BioNLP Workshop and Shared Task).

NCUEE at MEDIQA 2019: Medical text inference using ensemble BERT-BiLSTM-attention model

摘要

出版系列

???event.eventtypes.event.conference???

指紋

專案

中文醫療健康照護知識庫建置與應用(3/3)

應用於居家照護之智慧型互動平台－應用於醫療場域及居家照護之智慧 型互動平台- 以人工智慧為核心之腦波人機介面開發(2/4)

引用此

應用於居家照護之智慧型互動平台－應用於醫療場域及居家照護之智慧型互動平台- 以人工智慧為核心之腦波人機介面開發(2/4)