JoLT: Jointly Learned Representations of Language and Time-Series for Clinical Time-Series Interpretation (Student Abstract)
Abstract
Time-series and text data are prevalent in healthcare and frequently co-exist, yet they are typically modeled in isolation. Even studies that jointly model time-series and text, do so by converting time-series to images or graphs. We hypothesize that explicitly modeling time-series jointly with text can improve tasks such as summarization and question answering for time-series data, which have received little attention so far. To address this gap, we introduce JoLT to jointly learn desired representations from pre-trained time-series and text models. JoLT utilizes a Querying Transformer (Q-Former) to align the time-series and text representations. Our experiments on a large real-world electrocardiography dataset for medical time-series summarization show that JoLT outperforms state-of-the-art image captioning approaches.
Cite
Text
Cai et al. "JoLT: Jointly Learned Representations of Language and Time-Series for Clinical Time-Series Interpretation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30423Markdown
[Cai et al. "JoLT: Jointly Learned Representations of Language and Time-Series for Clinical Time-Series Interpretation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/cai2024aaai-jolt/) doi:10.1609/AAAI.V38I21.30423BibTeX
@inproceedings{cai2024aaai-jolt,
title = {{JoLT: Jointly Learned Representations of Language and Time-Series for Clinical Time-Series Interpretation (Student Abstract)}},
author = {Cai, Yifu and Srinivasan, Arvind and Goswami, Mononito and Choudhry, Arjun and Dubrawski, Artur},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2024},
pages = {23447-23448},
doi = {10.1609/AAAI.V38I21.30423},
url = {https://mlanthology.org/aaai/2024/cai2024aaai-jolt/}
}