@inproceedings{shim-etal-2021-synthetic,
title = "Synthetic Data Generation and Multi-Task Learning for Extracting Temporal Information from Health-Related Narrative Text",
author = "Shim, Heereen and
Lowet, Dietwig and
Luca, Stijn and
Vanrumste, Bart",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wnut-1.29",
doi = "10.18653/v1/2021.wnut-1.29",
pages = "260--273",
abstract = "Extracting temporal information is critical to process health-related text. Temporal information extraction is a challenging task for language models because it requires processing both texts and numbers. Moreover, the fundamental challenge is how to obtain a large-scale training dataset. To address this, we propose a synthetic data generation algorithm. Also, we propose a novel multi-task temporal information extraction model and investigate whether multi-task learning can contribute to performance improvement by exploiting additional training signals with the existing training data. For experiments, we collected a custom dataset containing unstructured texts with temporal information of sleep-related activities. Experimental results show that utilising synthetic data can improve the performance when the augmentation factor is 3. The results also show that when multi-task learning is used with an appropriate amount of synthetic data, the performance can significantly improve from 82. to 88.6 and from 83.9 to 91.9 regarding micro-and macro-average exact match scores of normalised time prediction, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shim-etal-2021-synthetic">
<titleInfo>
<title>Synthetic Data Generation and Multi-Task Learning for Extracting Temporal Information from Health-Related Narrative Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heereen</namePart>
<namePart type="family">Shim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dietwig</namePart>
<namePart type="family">Lowet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stijn</namePart>
<namePart type="family">Luca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bart</namePart>
<namePart type="family">Vanrumste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Extracting temporal information is critical to process health-related text. Temporal information extraction is a challenging task for language models because it requires processing both texts and numbers. Moreover, the fundamental challenge is how to obtain a large-scale training dataset. To address this, we propose a synthetic data generation algorithm. Also, we propose a novel multi-task temporal information extraction model and investigate whether multi-task learning can contribute to performance improvement by exploiting additional training signals with the existing training data. For experiments, we collected a custom dataset containing unstructured texts with temporal information of sleep-related activities. Experimental results show that utilising synthetic data can improve the performance when the augmentation factor is 3. The results also show that when multi-task learning is used with an appropriate amount of synthetic data, the performance can significantly improve from 82. to 88.6 and from 83.9 to 91.9 regarding micro-and macro-average exact match scores of normalised time prediction, respectively.</abstract>
<identifier type="citekey">shim-etal-2021-synthetic</identifier>
<identifier type="doi">10.18653/v1/2021.wnut-1.29</identifier>
<location>
<url>https://aclanthology.org/2021.wnut-1.29</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>260</start>
<end>273</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Synthetic Data Generation and Multi-Task Learning for Extracting Temporal Information from Health-Related Narrative Text
%A Shim, Heereen
%A Lowet, Dietwig
%A Luca, Stijn
%A Vanrumste, Bart
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F shim-etal-2021-synthetic
%X Extracting temporal information is critical to process health-related text. Temporal information extraction is a challenging task for language models because it requires processing both texts and numbers. Moreover, the fundamental challenge is how to obtain a large-scale training dataset. To address this, we propose a synthetic data generation algorithm. Also, we propose a novel multi-task temporal information extraction model and investigate whether multi-task learning can contribute to performance improvement by exploiting additional training signals with the existing training data. For experiments, we collected a custom dataset containing unstructured texts with temporal information of sleep-related activities. Experimental results show that utilising synthetic data can improve the performance when the augmentation factor is 3. The results also show that when multi-task learning is used with an appropriate amount of synthetic data, the performance can significantly improve from 82. to 88.6 and from 83.9 to 91.9 regarding micro-and macro-average exact match scores of normalised time prediction, respectively.
%R 10.18653/v1/2021.wnut-1.29
%U https://aclanthology.org/2021.wnut-1.29
%U https://doi.org/10.18653/v1/2021.wnut-1.29
%P 260-273
Markdown (Informal)
[Synthetic Data Generation and Multi-Task Learning for Extracting Temporal Information from Health-Related Narrative Text](https://aclanthology.org/2021.wnut-1.29) (Shim et al., WNUT 2021)
ACL