LaSTR: Language-Driven Time-Series Segment Retrieval
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910036632010752 |
|---|---|
| author | Dohi, Kota Purohit, Harsh Nishida, Tomoya Endo, Takashi Ohtsubo, Yusuke Yawata, Koichiro Takeshita, Koki Sasaki, Tatsuya Kawaguchi, Yohei |
| author_facet | Dohi, Kota Purohit, Harsh Nishida, Tomoya Endo, Takashi Ohtsubo, Yusuke Yawata, Koichiro Takeshita, Koki Sasaki, Tatsuya Kawaguchi, Yohei |
| contents | Effectively searching time-series data is essential for system analysis, but existing methods often require expert-designed similarity criteria or rely on global, series-level descriptions. We study language-driven segment retrieval: given a natural language query, the goal is to retrieve relevant local segments from large time-series repositories. We build large-scale segment--caption training data by applying TV2-based segmentation to LOTSA windows and generating segment descriptions with GPT-5.2, and then train a Conformer-based contrastive retriever in a shared text--time-series embedding space. On a held-out test split, we evaluate single-positive retrieval together with caption-side consistency (SBERT and VLM-as-a-judge) under multiple candidate pool sizes. Across all settings, LaSTR outperforms random and CLIP baselines, yielding improved ranking quality and stronger semantic agreement between retrieved segments and query intent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00725 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LaSTR: Language-Driven Time-Series Segment Retrieval Dohi, Kota Purohit, Harsh Nishida, Tomoya Endo, Takashi Ohtsubo, Yusuke Yawata, Koichiro Takeshita, Koki Sasaki, Tatsuya Kawaguchi, Yohei Computation and Language Effectively searching time-series data is essential for system analysis, but existing methods often require expert-designed similarity criteria or rely on global, series-level descriptions. We study language-driven segment retrieval: given a natural language query, the goal is to retrieve relevant local segments from large time-series repositories. We build large-scale segment--caption training data by applying TV2-based segmentation to LOTSA windows and generating segment descriptions with GPT-5.2, and then train a Conformer-based contrastive retriever in a shared text--time-series embedding space. On a held-out test split, we evaluate single-positive retrieval together with caption-side consistency (SBERT and VLM-as-a-judge) under multiple candidate pool sizes. Across all settings, LaSTR outperforms random and CLIP baselines, yielding improved ranking quality and stronger semantic agreement between retrieved segments and query intent. |
| title | LaSTR: Language-Driven Time-Series Segment Retrieval |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2603.00725 |