Synthetic Data Generation and Multi-Task Learning for Extracting Temporal Information from Health-Related Narrative Text

Heereen Shim, Dietwig Lowet, Stijn Luca, Bart Vanrumste

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.
Anthology ID:
2021.wnut-1.29
Volume:
Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)
Month:
November
Year:
2021
Address:
Online
Editors:
Wei Xu, Alan Ritter, Tim Baldwin, Afshin Rahimi
Venue:
WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
260–273
Language:
URL:
https://aclanthology.org/2021.wnut-1.29
DOI:
10.18653/v1/2021.wnut-1.29
Bibkey:
Cite (ACL):
Heereen Shim, Dietwig Lowet, Stijn Luca, and Bart Vanrumste. 2021. Synthetic Data Generation and Multi-Task Learning for Extracting Temporal Information from Health-Related Narrative Text. In Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021), pages 260–273, Online. Association for Computational Linguistics.
Cite (Informal):
Synthetic Data Generation and Multi-Task Learning for Extracting Temporal Information from Health-Related Narrative Text (Shim et al., WNUT 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2021.wnut-1.29.pdf
PDF Search