Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks

Chen Lin; Timothy Miller; Dmitriy Dligach; Steven Bethard; Guergana Savova

Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks

Chen Lin, Timothy Miller, Dmitriy Dligach, Steven Bethard, Guergana Savova

Information, School of

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

34 Scopus citations

Abstract

Token sequences are often used as the input for Convolutional Neural Networks (CNNs) in natural language processing. However, they might not be an ideal representation for time expressions, which are long, highly varied, and semantically complex. We describe a method for representing time expressions with single pseudo-tokens for CNNs. With this method, we establish a new state-of-the-art result for a clinical temporal relation extraction task.

Original language	English (US)
Title of host publication	BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop
Publisher	Association for Computational Linguistics (ACL)
Pages	322-327
Number of pages	6
ISBN (Electronic)	9781945626593
State	Published - 2017
Event	16th SIGBioMed Workshop on Biomedical Natural Language Processing, BioNLP 2017 - Vancouver, Canada Duration: Aug 4 2017 → …

Publication series

Name	BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop

Conference

Conference	16th SIGBioMed Workshop on Biomedical Natural Language Processing, BioNLP 2017
Country/Territory	Canada
City	Vancouver
Period	8/4/17 → …

ASJC Scopus subject areas

Language and Linguistics
Computer Science Applications
Information Systems
Software
Biomedical Engineering
Health Informatics

Cite this

Lin, C., Miller, T., Dligach, D., Bethard, S., & Savova, G. (2017). Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks. In BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop (pp. 322-327). (BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop). Association for Computational Linguistics (ACL).

Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks. / Lin, Chen; Miller, Timothy; Dligach, Dmitriy et al.
BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop. Association for Computational Linguistics (ACL), 2017. p. 322-327 (BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop).

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

Lin, C, Miller, T, Dligach, D, Bethard, S & Savova, G 2017, Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks. in BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop. BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop, Association for Computational Linguistics (ACL), pp. 322-327, 16th SIGBioMed Workshop on Biomedical Natural Language Processing, BioNLP 2017, Vancouver, Canada, 8/4/17.

Lin C, Miller T, Dligach D, Bethard S, Savova G. Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks. In BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop. Association for Computational Linguistics (ACL). 2017. p. 322-327. (BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop).

Lin, Chen ; Miller, Timothy ; Dligach, Dmitriy et al. / Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks. BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop. Association for Computational Linguistics (ACL), 2017. pp. 322-327 (BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop).

@inproceedings{c24f0ded0e2d4de09523d42b9afb8de4,

title = "Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks",

abstract = "Token sequences are often used as the input for Convolutional Neural Networks (CNNs) in natural language processing. However, they might not be an ideal representation for time expressions, which are long, highly varied, and semantically complex. We describe a method for representing time expressions with single pseudo-tokens for CNNs. With this method, we establish a new state-of-the-art result for a clinical temporal relation extraction task.",

author = "Chen Lin and Timothy Miller and Dmitriy Dligach and Steven Bethard and Guergana Savova",

note = "Funding Information: The study was funded by R01LM10090 (THYME), R01GM103859 (iPGx), and U24CA184407 (Deep-Phe). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. The Titan X GPU used for this research was donated by the NVIDIA Corporation. Publisher Copyright: {\textcopyright} 2017 Association for Computational Linguistics; 16th SIGBioMed Workshop on Biomedical Natural Language Processing, BioNLP 2017 ; Conference date: 04-08-2017",

year = "2017",

language = "English (US)",

series = "BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop",

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

pages = "322--327",

booktitle = "BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop",

}

TY - GEN

T1 - Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks

AU - Lin, Chen

AU - Miller, Timothy

AU - Dligach, Dmitriy

AU - Bethard, Steven

AU - Savova, Guergana

N1 - Funding Information: The study was funded by R01LM10090 (THYME), R01GM103859 (iPGx), and U24CA184407 (Deep-Phe). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. The Titan X GPU used for this research was donated by the NVIDIA Corporation. Publisher Copyright: © 2017 Association for Computational Linguistics

PY - 2017

Y1 - 2017

N2 - Token sequences are often used as the input for Convolutional Neural Networks (CNNs) in natural language processing. However, they might not be an ideal representation for time expressions, which are long, highly varied, and semantically complex. We describe a method for representing time expressions with single pseudo-tokens for CNNs. With this method, we establish a new state-of-the-art result for a clinical temporal relation extraction task.

AB - Token sequences are often used as the input for Convolutional Neural Networks (CNNs) in natural language processing. However, they might not be an ideal representation for time expressions, which are long, highly varied, and semantically complex. We describe a method for representing time expressions with single pseudo-tokens for CNNs. With this method, we establish a new state-of-the-art result for a clinical temporal relation extraction task.

UR - http://www.scopus.com/inward/record.url?scp=85057221475&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057221475&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85057221475

T3 - BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop

SP - 322

EP - 327

BT - BioNLP 2017 - SIGBioMed Workshop on Biomedical Natural Language Processing, Proceedings of the 16th BioNLP Workshop

PB - Association for Computational Linguistics (ACL)

T2 - 16th SIGBioMed Workshop on Biomedical Natural Language Processing, BioNLP 2017

Y2 - 4 August 2017

ER -

Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks

Abstract

Publication series

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this