CLaSP: Learning Concepts for Time-Series Signals from Natural Language Supervision
This paper proposes a foundation model called "CLaSP" that can search time series signals using natural language that describes the characteristics of the signals as queries. Previous efforts to represent time series signal data in natural language have had challenges in designing a conven...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | Ito, Aoi Dohi, Kota Kawaguchi, Yohei |
description | This paper proposes a foundation model called "CLaSP" that can search time
series signals using natural language that describes the characteristics of the
signals as queries. Previous efforts to represent time series signal data in
natural language have had challenges in designing a conventional class of time
series signal characteristics, formulating their quantification, and creating a
dictionary of synonyms. To overcome these limitations, the proposed method
introduces a neural network based on contrastive learning. This network is
first trained using the datasets TRUCE and SUSHI, which consist of time series
signals and their corresponding natural language descriptions. Previous studies
have proposed vocabularies that data analysts use to describe signal
characteristics, and SUSHI was designed to cover these terms. We believe that a
neural network trained on these datasets will enable data analysts to search
using natural language vocabulary. Furthermore, our method does not require a
dictionary of predefined synonyms, and it leverages common sense knowledge
embedded in a large-scale language model (LLM). Experimental results
demonstrate that CLaSP enables natural language search of time series signal
data and can accurately learn the points at which signal data changes. |
doi_str_mv | 10.48550/arxiv.2411.08397 |
format | Article |
fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2411_08397</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2411_08397</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2411_083973</originalsourceid><addsrcrecordid>eNqFjs0KglAQRu-mRVQP0Kp5AU1TydpK0UIiuu5liPEyoPfK-EO9fRbtW33wceAcpdZh4MdpkgRblCeP_i4OQz9Io8N-ru5Zjvp2hJxQLFsDmbMPavsOKidQcEOeJmHqQLOxWE-_uAau2A-CNeRozYCGQA8tycgdO7tUs2oCafXbhdqcT0V28b72shVuUF7lp6L8VkT_iTcgDzzg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>CLaSP: Learning Concepts for Time-Series Signals from Natural Language Supervision</title><source>arXiv.org</source><creator>Ito, Aoi ; Dohi, Kota ; Kawaguchi, Yohei</creator><creatorcontrib>Ito, Aoi ; Dohi, Kota ; Kawaguchi, Yohei</creatorcontrib><description>This paper proposes a foundation model called "CLaSP" that can search time
series signals using natural language that describes the characteristics of the
signals as queries. Previous efforts to represent time series signal data in
natural language have had challenges in designing a conventional class of time
series signal characteristics, formulating their quantification, and creating a
dictionary of synonyms. To overcome these limitations, the proposed method
introduces a neural network based on contrastive learning. This network is
first trained using the datasets TRUCE and SUSHI, which consist of time series
signals and their corresponding natural language descriptions. Previous studies
have proposed vocabularies that data analysts use to describe signal
characteristics, and SUSHI was designed to cover these terms. We believe that a
neural network trained on these datasets will enable data analysts to search
using natural language vocabulary. Furthermore, our method does not require a
dictionary of predefined synonyms, and it leverages common sense knowledge
embedded in a large-scale language model (LLM). Experimental results
demonstrate that CLaSP enables natural language search of time series signal
data and can accurately learn the points at which signal data changes.</description><identifier>DOI: 10.48550/arxiv.2411.08397</identifier><language>eng</language><subject>Computer Science - Computation and Language ; Computer Science - Learning</subject><creationdate>2024-11</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2411.08397$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2411.08397$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Ito, Aoi</creatorcontrib><creatorcontrib>Dohi, Kota</creatorcontrib><creatorcontrib>Kawaguchi, Yohei</creatorcontrib><title>CLaSP: Learning Concepts for Time-Series Signals from Natural Language Supervision</title><description>This paper proposes a foundation model called "CLaSP" that can search time
series signals using natural language that describes the characteristics of the
signals as queries. Previous efforts to represent time series signal data in
natural language have had challenges in designing a conventional class of time
series signal characteristics, formulating their quantification, and creating a
dictionary of synonyms. To overcome these limitations, the proposed method
introduces a neural network based on contrastive learning. This network is
first trained using the datasets TRUCE and SUSHI, which consist of time series
signals and their corresponding natural language descriptions. Previous studies
have proposed vocabularies that data analysts use to describe signal
characteristics, and SUSHI was designed to cover these terms. We believe that a
neural network trained on these datasets will enable data analysts to search
using natural language vocabulary. Furthermore, our method does not require a
dictionary of predefined synonyms, and it leverages common sense knowledge
embedded in a large-scale language model (LLM). Experimental results
demonstrate that CLaSP enables natural language search of time series signal
data and can accurately learn the points at which signal data changes.</description><subject>Computer Science - Computation and Language</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNqFjs0KglAQRu-mRVQP0Kp5AU1TydpK0UIiuu5liPEyoPfK-EO9fRbtW33wceAcpdZh4MdpkgRblCeP_i4OQz9Io8N-ru5Zjvp2hJxQLFsDmbMPavsOKidQcEOeJmHqQLOxWE-_uAau2A-CNeRozYCGQA8tycgdO7tUs2oCafXbhdqcT0V28b72shVuUF7lp6L8VkT_iTcgDzzg</recordid><startdate>20241113</startdate><enddate>20241113</enddate><creator>Ito, Aoi</creator><creator>Dohi, Kota</creator><creator>Kawaguchi, Yohei</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20241113</creationdate><title>CLaSP: Learning Concepts for Time-Series Signals from Natural Language Supervision</title><author>Ito, Aoi ; Dohi, Kota ; Kawaguchi, Yohei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2411_083973</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Computation and Language</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Ito, Aoi</creatorcontrib><creatorcontrib>Dohi, Kota</creatorcontrib><creatorcontrib>Kawaguchi, Yohei</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ito, Aoi</au><au>Dohi, Kota</au><au>Kawaguchi, Yohei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>CLaSP: Learning Concepts for Time-Series Signals from Natural Language Supervision</atitle><date>2024-11-13</date><risdate>2024</risdate><abstract>This paper proposes a foundation model called "CLaSP" that can search time
series signals using natural language that describes the characteristics of the
signals as queries. Previous efforts to represent time series signal data in
natural language have had challenges in designing a conventional class of time
series signal characteristics, formulating their quantification, and creating a
dictionary of synonyms. To overcome these limitations, the proposed method
introduces a neural network based on contrastive learning. This network is
first trained using the datasets TRUCE and SUSHI, which consist of time series
signals and their corresponding natural language descriptions. Previous studies
have proposed vocabularies that data analysts use to describe signal
characteristics, and SUSHI was designed to cover these terms. We believe that a
neural network trained on these datasets will enable data analysts to search
using natural language vocabulary. Furthermore, our method does not require a
dictionary of predefined synonyms, and it leverages common sense knowledge
embedded in a large-scale language model (LLM). Experimental results
demonstrate that CLaSP enables natural language search of time series signal
data and can accurately learn the points at which signal data changes.</abstract><doi>10.48550/arxiv.2411.08397</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.48550/arxiv.2411.08397 |
ispartof | |
issn | |
language | eng |
recordid | cdi_arxiv_primary_2411_08397 |
source | arXiv.org |
subjects | Computer Science - Computation and Language Computer Science - Learning |
title | CLaSP: Learning Concepts for Time-Series Signals from Natural Language Supervision |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T20%3A24%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=CLaSP:%20Learning%20Concepts%20for%20Time-Series%20Signals%20from%20Natural%20Language%20Supervision&rft.au=Ito,%20Aoi&rft.date=2024-11-13&rft_id=info:doi/10.48550/arxiv.2411.08397&rft_dat=%3Carxiv_GOX%3E2411_08397%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |