Generating Natural Language Sentences Explaining Trends and Relationships of Two Time-Series Data

We propose a method for generating natural language explanations that describe trends and relationships between two time-series data. To address this task, it is essential to analyze the dynamic behavior of both time series and generate textual explanations based on the analytical outcomes. We devel...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of advanced computational intelligence and intelligent informatics Jg. 29; H. 6; S. 1427 - 1442
Hauptverfasser: Nakano, Yukako, Kobayashi, Ichiro
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Tokyo Fuji Technology Press Co. Ltd 20.11.2025
Schlagworte:
Accuracy
Datasets
Natural language
Time series
Trends
ISSN:1343-0130, 1883-8014
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract We propose a method for generating natural language explanations that describe trends and relationships between two time-series data. To address this task, it is essential to analyze the dynamic behavior of both time series and generate textual explanations based on the analytical outcomes. We developed a model that extended the vanilla Transformer architecture to better capture the temporal features relevant to explanation generation. To train the model, we constructed a synthetic, domain-agnostic dataset that simulated time-series patterns and interactions. We conducted two experiments to evaluate the effectiveness of the proposed approach using the synthesized datasets. The first experiment focused on generating explanations for the time-series trends. The results demonstrated that our model could generate accurate and coherent explanations with high accuracy. The second experiment addressed more complex scenarios in which the model was required to answer questions regarding the relationship between two interacting time-series. Although the model initially struggled to achieve high accuracy in this task, we observed that step-by-step training significantly improved its performance. These findings highlight both the potential and current limitations of Transformer-based approaches for interpretable time-series analysis.
AbstractList We propose a method for generating natural language explanations that describe trends and relationships between two time-series data. To address this task, it is essential to analyze the dynamic behavior of both time series and generate textual explanations based on the analytical outcomes. We developed a model that extended the vanilla Transformer architecture to better capture the temporal features relevant to explanation generation. To train the model, we constructed a synthetic, domain-agnostic dataset that simulated time-series patterns and interactions. We conducted two experiments to evaluate the effectiveness of the proposed approach using the synthesized datasets. The first experiment focused on generating explanations for the time-series trends. The results demonstrated that our model could generate accurate and coherent explanations with high accuracy. The second experiment addressed more complex scenarios in which the model was required to answer questions regarding the relationship between two interacting time-series. Although the model initially struggled to achieve high accuracy in this task, we observed that step-by-step training significantly improved its performance. These findings highlight both the potential and current limitations of Transformer-based approaches for interpretable time-series analysis.
Author Kobayashi, Ichiro
Nakano, Yukako
Author_xml – sequence: 1
  givenname: Yukako
  orcidid: 0009-0004-5918-4868
  surname: Nakano
  fullname: Nakano, Yukako
  organization: Graduate School of Humanities and Sciences, Ochanomizu University, 2-1-1 Otsuka, Bunkyo-ku, Tokyo 112-8610, Japan
– sequence: 2
  givenname: Ichiro
  orcidid: 0000-0001-7789-475X
  surname: Kobayashi
  fullname: Kobayashi, Ichiro
  organization: Graduate School of Humanities and Sciences, Ochanomizu University, 2-1-1 Otsuka, Bunkyo-ku, Tokyo 112-8610, Japan
BookMark eNotkFFLwzAUhYNMcM79AZ8CPncmTZqkjzLnFIaCq88hTW9nRpfWpEX993abL_eeC-fcA981mvjWA0K3lCxSkovsfm-sc2480mzRUZ7KCzSlSrFEEcono2acJYQycoXmMe4JGXUqCKdTZNbgIZje-R1-Nf0QTIM3xu8GswO8Bd-DtxDx6qdrjPNHVxHAVxEbX-F3aMZk6-On6yJua1x8t7hwB0i2ENwYezS9uUGXtWkizP_3DH08rYrlc7J5W78sHzaJTTmXibCQMUVLq2TFuRBVTQCYLHmmaD4OK0qiJJciZ5WsOTXKEiOUEEqWhnFgM3R3_tuF9muA2Ot9OwQ_VmqWyjQXOeF8dKVnlw1tjAFq3QV3MOFXU6JPNPWZpj7S1Cea7A_ehmqm
Cites_doi 10.14778/3514061.3514067
10.18653/v1/2021.acl-long.466
10.1002/int.21671
10.18653/v1/2020.inlg-1.21
10.18653/v1/W19-8640
10.18653/v1/D19-5615
10.18653/v1/P17-1126
10.18653/v1/2021.eacl-main.125
10.3115/v1/P15-1142
10.1109/JIOT.2024.3419260
10.18653/v1/2020.inlg-1.20
10.1609/aaai.v33i01.33016786
10.1016/j.fss.2015.06.016
10.18653/v1/2022.acl-long.277
10.18653/v1/2023.emnlp-main.389
10.18653/v1/2021.emnlp-main.55
10.3115/1073083.1073135
10.1016/j.asoc.2022.108612
10.18653/v1/W19-8611
10.1016/j.fss.2015.06.018
10.18653/v1/2023.acl-long.401
ContentType Journal Article
Copyright Copyright © 2025 Fuji Technology Press Ltd.
Copyright_xml – notice: Copyright © 2025 Fuji Technology Press Ltd.
CorporateAuthor Editorial Office
CorporateAuthor_xml – name: Editorial Office
DBID AAYXX
CITATION
7SC
7SP
8FD
8FE
8FG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
GNUQQ
HCIFZ
JQ2
K7-
L7M
L~C
L~D
P5Z
P62
PHGZM
PHGZT
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
DOI 10.20965/jaciii.2025.p1427
DatabaseName CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central UK/Ireland
Advanced Technologies & Aerospace Database‎ (1962 - current)
ProQuest Central Essentials - QC
ProQuest Central
Technology Collection
ProQuest One Community College
ProQuest Central Korea
ProQuest Central Student
SciTech Premium Collection
ProQuest Computer Science Collection
Computer Science Database
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
Proquest Central Premium
ProQuest One Academic
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
DatabaseTitle CrossRef
Computer Science Database
ProQuest Central Student
Technology Collection
Technology Research Database
Computer and Information Systems Abstracts – Academic
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
SciTech Premium Collection
ProQuest One Community College
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Central Korea
ProQuest Central (New)
Advanced Technologies Database with Aerospace
Advanced Technologies & Aerospace Collection
ProQuest One Academic Eastern Edition
Electronics & Communications Abstracts
ProQuest Technology Collection
ProQuest SciTech Collection
Computer and Information Systems Abstracts Professional
Advanced Technologies & Aerospace Database
ProQuest One Academic UKI Edition
ProQuest One Academic
ProQuest One Academic (New)
DatabaseTitleList CrossRef
Computer Science Database
Database_xml – sequence: 1
  dbid: BENPR
  name: AUTh Library subscriptions: ProQuest Central
  url: https://www.proquest.com/central
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1883-8014
EndPage 1442
ExternalDocumentID 10_20965_jaciii_2025_p1427
GroupedDBID AAYXX
AFFHD
AFKRA
ALMA_UNASSIGNED_HOLDINGS
ARAPS
ARCSS
BENPR
BGLVJ
CCPQU
CITATION
GROUPED_DOAJ
HCIFZ
ISHAI
JSI
JSP
K7-
P2P
PHGZM
PHGZT
PQGLB
RJT
RZJ
TUS
7SC
7SP
8FD
8FE
8FG
AZQEC
DWQXO
GNUQQ
JQ2
L7M
L~C
L~D
P62
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
ID FETCH-LOGICAL-c2447-6ce5381bc87d4466df0ee37b45819458c6b08747693d7f41a8c0a686687ba34e3
IEDL.DBID K7-
ISSN 1343-0130
IngestDate Thu Nov 20 00:30:30 EST 2025
Thu Nov 27 00:51:19 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 6
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2447-6ce5381bc87d4466df0ee37b45819458c6b08747693d7f41a8c0a686687ba34e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0001-7789-475X
0009-0004-5918-4868
OpenAccessLink https://doi.org/10.20965/jaciii.2025.p1427
PQID 3272969044
PQPubID 4911628
PageCount 16
ParticipantIDs proquest_journals_3272969044
crossref_primary_10_20965_jaciii_2025_p1427
PublicationCentury 2000
PublicationDate 2025-11-20
PublicationDateYYYYMMDD 2025-11-20
PublicationDate_xml – month: 11
  year: 2025
  text: 2025-11-20
  day: 20
PublicationDecade 2020
PublicationPlace Tokyo
PublicationPlace_xml – name: Tokyo
PublicationTitle Journal of advanced computational intelligence and intelligent informatics
PublicationYear 2025
Publisher Fuji Technology Press Co. Ltd
Publisher_xml – name: Fuji Technology Press Co. Ltd
References key-10.20965/jaciii.2025.p1427-13
key-10.20965/jaciii.2025.p1427-12
key-10.20965/jaciii.2025.p1427-15
key-10.20965/jaciii.2025.p1427-14
key-10.20965/jaciii.2025.p1427-17
key-10.20965/jaciii.2025.p1427-16
key-10.20965/jaciii.2025.p1427-19
key-10.20965/jaciii.2025.p1427-18
key-10.20965/jaciii.2025.p1427-9
key-10.20965/jaciii.2025.p1427-7
key-10.20965/jaciii.2025.p1427-8
key-10.20965/jaciii.2025.p1427-31
key-10.20965/jaciii.2025.p1427-30
key-10.20965/jaciii.2025.p1427-11
key-10.20965/jaciii.2025.p1427-10
key-10.20965/jaciii.2025.p1427-1
key-10.20965/jaciii.2025.p1427-2
key-10.20965/jaciii.2025.p1427-5
key-10.20965/jaciii.2025.p1427-6
key-10.20965/jaciii.2025.p1427-3
key-10.20965/jaciii.2025.p1427-4
key-10.20965/jaciii.2025.p1427-24
key-10.20965/jaciii.2025.p1427-23
key-10.20965/jaciii.2025.p1427-26
key-10.20965/jaciii.2025.p1427-25
key-10.20965/jaciii.2025.p1427-28
key-10.20965/jaciii.2025.p1427-27
key-10.20965/jaciii.2025.p1427-29
key-10.20965/jaciii.2025.p1427-20
key-10.20965/jaciii.2025.p1427-22
key-10.20965/jaciii.2025.p1427-21
References_xml – ident: key-10.20965/jaciii.2025.p1427-25
  doi: 10.14778/3514061.3514067
– ident: key-10.20965/jaciii.2025.p1427-10
  doi: 10.18653/v1/2021.acl-long.466
– ident: key-10.20965/jaciii.2025.p1427-20
  doi: 10.1002/int.21671
– ident: key-10.20965/jaciii.2025.p1427-24
  doi: 10.18653/v1/2020.inlg-1.21
– ident: key-10.20965/jaciii.2025.p1427-7
  doi: 10.18653/v1/W19-8640
– ident: key-10.20965/jaciii.2025.p1427-9
  doi: 10.18653/v1/D19-5615
– ident: key-10.20965/jaciii.2025.p1427-18
– ident: key-10.20965/jaciii.2025.p1427-26
– ident: key-10.20965/jaciii.2025.p1427-6
  doi: 10.18653/v1/P17-1126
– ident: key-10.20965/jaciii.2025.p1427-28
– ident: key-10.20965/jaciii.2025.p1427-31
– ident: key-10.20965/jaciii.2025.p1427-12
  doi: 10.18653/v1/2021.eacl-main.125
– ident: key-10.20965/jaciii.2025.p1427-16
  doi: 10.3115/v1/P15-1142
– ident: key-10.20965/jaciii.2025.p1427-22
  doi: 10.1109/JIOT.2024.3419260
– ident: key-10.20965/jaciii.2025.p1427-3
  doi: 10.18653/v1/2020.inlg-1.20
– ident: key-10.20965/jaciii.2025.p1427-15
  doi: 10.1609/aaai.v33i01.33016786
– ident: key-10.20965/jaciii.2025.p1427-13
– ident: key-10.20965/jaciii.2025.p1427-11
– ident: key-10.20965/jaciii.2025.p1427-17
– ident: key-10.20965/jaciii.2025.p1427-19
  doi: 10.1016/j.fss.2015.06.016
– ident: key-10.20965/jaciii.2025.p1427-4
  doi: 10.18653/v1/2022.acl-long.277
– ident: key-10.20965/jaciii.2025.p1427-8
– ident: key-10.20965/jaciii.2025.p1427-1
  doi: 10.18653/v1/2023.emnlp-main.389
– ident: key-10.20965/jaciii.2025.p1427-5
  doi: 10.18653/v1/2021.emnlp-main.55
– ident: key-10.20965/jaciii.2025.p1427-30
– ident: key-10.20965/jaciii.2025.p1427-27
  doi: 10.3115/1073083.1073135
– ident: key-10.20965/jaciii.2025.p1427-23
  doi: 10.1016/j.asoc.2022.108612
– ident: key-10.20965/jaciii.2025.p1427-29
– ident: key-10.20965/jaciii.2025.p1427-14
  doi: 10.18653/v1/W19-8611
– ident: key-10.20965/jaciii.2025.p1427-21
  doi: 10.1016/j.fss.2015.06.018
– ident: key-10.20965/jaciii.2025.p1427-2
  doi: 10.18653/v1/2023.acl-long.401
SSID ssj0001326041
ssib051641541
Score 2.3410776
Snippet We propose a method for generating natural language explanations that describe trends and relationships between two time-series data. To address this task, it...
SourceID proquest
crossref
SourceType Aggregation Database
Index Database
StartPage 1427
SubjectTerms Accuracy
Datasets
Natural language
Time series
Trends
Title Generating Natural Language Sentences Explaining Trends and Relationships of Two Time-Series Data
URI https://www.proquest.com/docview/3272969044
Volume 29
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: Open Access: DOAJ - Directory of Open Access Journals
  customDbUrl:
  eissn: 1883-8014
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001326041
  issn: 1343-0130
  databaseCode: DOA
  dateStart: 20070101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1883-8014
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib051641541
  issn: 1343-0130
  databaseCode: M~E
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 1883-8014
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001326041
  issn: 1343-0130
  databaseCode: P5Z
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: AUTh Library subscriptions: ProQuest Central
  customDbUrl:
  eissn: 1883-8014
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001326041
  issn: 1343-0130
  databaseCode: BENPR
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 1883-8014
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001326041
  issn: 1343-0130
  databaseCode: K7-
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwELagMLBQnqJQKg9syOAkju1MiKeQQFXFS4glcmxHlKEpbYG_z10ePBYWFi9Rosh3Pn93_vwdIXvWaJO53DBp85gJGVuWcRsz7qRInOAiK2UXH65Vv68fH5NBXXCb1rTKJiaWgdoVFmvkh1EIMBBSOSGOxq8Mu0bh6WrdQmOeLARhGKCfXynW-FMMqQAghOC75gJYhYsqBxNII4p4dY8mRA2UwxdjUdAhBBhwMA4ENpr5uVf9DtXl_nPR_u-fr5DlGnnS48pVVsmcH62RdtPVgdaLfJ2YSoka6dC0b0pZDnpdVzXpLUp4IvOaInmv6i5BK14tNSNHv7h1z8PxlBY5vfsoKF4zYViGg9fOzMxskPuL87vTS1Y3YmAWdn8FdvQQF4PMauXw_Nfl3PtIZSIGPAGDlRnXkJfIJHIqF4HRlhuppdQqM5Hw0SZpjYqR3yLUWOUj5xPtAbsIFZs8SwB1JNrIJNbKdMh-M-XpuNLbSCFPKQ2UVgZK0UBpaaAO6TZTntZrb5p-z_f23493yBJ-Cm8WhrxLWrPJm98li_Z9NpxOemTh5Lw_uOmVWXqvdCwYB_HTJ9Gx02U
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LT9wwEB4BRaIXKBQELRQf2lPl4k0c2zkghKAIxHZViS3iFhzbEcthd8tuQfwpfmNn4oTHpTcOveSSh5LM55lvxvMA-OyssaWvLFeuyrhUmeOlcBkXXsncSyHLuu3ieVf3eubiIv85Aw9tLQylVbY6sVbUfuQoRr6TJkgD0ZWTcm_8m9PUKNpdbUdoRFichvs7dNkmuyeHKN8vSXL0vX9wzJupAtyhKdP4UgEXead0RnvazPSVCCHVpczQOOLBqVIYJNkqT72uZMcaJ6wyShld2lSGFJ87C29kihfRJrDmLX4zdD2QkXSeYjzIjYSMPp-ktKVUxLqdhHqu7FxbRw0kEqQd38YdSYNtntvGl6ahtndHS__bn3oHiw2zZvtxKSzDTBiuwFI7tYI1Suw92Nhpm9K9Wc_WbUdYt4nasjNqUUqZ5YySE-P0DBbzhpkdevaYO3g1GE_YqGL9uxGjMhpOYUa87dBO7Sr8epUPXYO54WgY1oFZp0PqQ24CcjOpM1uVObKq3FiVZ0bbDfjairgYx34iBfphNSCKCIiCAFHUgNiAzVbERaNbJsWTfD_8-_Q2LBz3f3SL7knv9CO8pcdSFWUiNmFuevMnbMG8u50OJjefahgzuHxtNPwFkqIp_g
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Generating+Natural+Language+Sentences+Explaining+Trends+and+Relationships+of+Two+Time-Series+Data&rft.jtitle=Journal+of+advanced+computational+intelligence+and+intelligent+informatics&rft.au=Nakano%2C+Yukako&rft.au=Kobayashi%2C+Ichiro&rft.date=2025-11-20&rft.issn=1343-0130&rft.eissn=1883-8014&rft.volume=29&rft.issue=6&rft.spage=1427&rft.epage=1442&rft_id=info:doi/10.20965%2Fjaciii.2025.p1427&rft.externalDBID=n%2Fa&rft.externalDocID=10_20965_jaciii_2025_p1427
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1343-0130&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1343-0130&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1343-0130&client=summon