JoLT: Jointly Learned Representations of Language and Time-Series for Clinical Time-Series Interpretation (Student Abstract)
Yifu Cai, Arvind Srinivasan, Mononito Goswami, Arjun Choudhry, Artur Dubrawski
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.
BibTeX
@article{Cai_Srinivasan_Goswami_Choudhry_Dubrawski_2024, title={JoLT: Jointly Learned Representations of Language and Time-Series for Clinical Time-Series Interpretation (Student Abstract)}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30423}, DOI={10.1609/aaai.v38i21.30423}, abstractNote={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.}, number={21}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Cai, Yifu and Srinivasan, Arvind and Goswami, Mononito and Choudhry, Arjun and Dubrawski, Artur}, year={2024}, month={Mar.}, pages={23447-23448} }