Domain-Independent Automatic Generation of Descriptive Texts for Time-Series Data
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912519119962112 |
|---|---|
| author | Dohi, Kota Ito, Aoi Purohit, Harsh Nishida, Tomoya Endo, Takashi Kawaguchi, Yohei |
| author_facet | Dohi, Kota Ito, Aoi Purohit, Harsh Nishida, Tomoya Endo, Takashi Kawaguchi, Yohei |
| contents | Due to scarcity of time-series data annotated with descriptive texts, training a model to generate descriptive texts for time-series data is challenging. In this study, we propose a method to systematically generate domain-independent descriptive texts from time-series data. We identify two distinct approaches for creating pairs of time-series data and descriptive texts: the forward approach and the backward approach. By implementing the novel backward approach, we create the Temporal Automated Captions for Observations (TACO) dataset. Experimental results demonstrate that a contrastive learning based model trained using the TACO dataset is capable of generating descriptive texts for time-series data in novel domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_16647 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Domain-Independent Automatic Generation of Descriptive Texts for Time-Series Data Dohi, Kota Ito, Aoi Purohit, Harsh Nishida, Tomoya Endo, Takashi Kawaguchi, Yohei Computation and Language Machine Learning Due to scarcity of time-series data annotated with descriptive texts, training a model to generate descriptive texts for time-series data is challenging. In this study, we propose a method to systematically generate domain-independent descriptive texts from time-series data. We identify two distinct approaches for creating pairs of time-series data and descriptive texts: the forward approach and the backward approach. By implementing the novel backward approach, we create the Temporal Automated Captions for Observations (TACO) dataset. Experimental results demonstrate that a contrastive learning based model trained using the TACO dataset is capable of generating descriptive texts for time-series data in novel domains. |
| title | Domain-Independent Automatic Generation of Descriptive Texts for Time-Series Data |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2409.16647 |