{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T15:09:00Z","timestamp":1763564940128,"version":"3.45.0"},"reference-count":31,"publisher":"Fuji Technology Press Ltd.","issue":"6","funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["23K28143"],"award-info":[{"award-number":["23K28143"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JACIII","J. Adv. Comput. Intell. Intell. Inform."],"published-print":{"date-parts":[[2025,11,20]]},"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.20965\/jaciii.2025.p1427","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T15:02:09Z","timestamp":1763564529000},"page":"1427-1442","source":"Crossref","is-referenced-by-count":0,"title":["Generating Natural Language Sentences Explaining Trends and Relationships of Two Time-Series Data"],"prefix":"10.20965","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5918-4868","authenticated-orcid":true,"given":"Yukako","family":"Nakano","sequence":"first","affiliation":[{"name":"Graduate School of Humanities and Sciences, Ochanomizu University, 2-1-1 Otsuka, Bunkyo-ku, Tokyo 112-8610, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"name":"Editorial Office","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7789-475X","authenticated-orcid":true,"given":"Ichiro","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"Graduate School of Humanities and Sciences, Ochanomizu University, 2-1-1 Otsuka, Bunkyo-ku, Tokyo 112-8610, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"8550","published-online":{"date-parts":[[2025,11,20]]},"reference":[{"key":"key-10.20965\/jaciii.2025.p1427-1","doi-asserted-by":"crossref","unstructured":"D. Ghosal, P. Nema, and A. Raghuveer, \u201cRetag: Reasoning aware table to analytic text generation,\u201d arXiv preprint, arXiv.2305.11826, 2023. https:\/\/doi.org\/10.48550\/arXiv.2305.11826","DOI":"10.18653\/v1\/2023.emnlp-main.389"},{"key":"key-10.20965\/jaciii.2025.p1427-2","doi-asserted-by":"crossref","unstructured":"B. J. Tang, A. Boggust, and A. Satyanarayan, \u201cVistext: A benchmark for semantically rich chart captioning,\u201d arXiv preprint, arXiv.2307.05356, 2023. https:\/\/doi.org\/10.48550\/arXiv.2307.05356","DOI":"10.18653\/v1\/2023.acl-long.401"},{"key":"key-10.20965\/jaciii.2025.p1427-3","doi-asserted-by":"crossref","unstructured":"J. Obeid and E. Hoque, \u201cChart-to-text: Generating natural language descriptions for charts by adapting the transformer model,\u201d arXiv preprint, arXiv.2010.09142, 2020. https:\/\/doi.org\/10.48550\/arXiv.2010.09142","DOI":"10.18653\/v1\/2020.inlg-1.20"},{"key":"key-10.20965\/jaciii.2025.p1427-4","doi-asserted-by":"crossref","unstructured":"S. Kantharaj, R. T. K. Leong, X. Lin, A. Masry, M. Thakkar, E. Hoque, and S. Joty, \u201cChart-to-text: A large-scale benchmark for chart summarization,\u201d arXiv preprint, arXiv.2203.06486, 2022. https:\/\/doi.org\/10.48550\/arXiv.2203.06486","DOI":"10.18653\/v1\/2022.acl-long.277"},{"key":"key-10.20965\/jaciii.2025.p1427-5","doi-asserted-by":"crossref","unstructured":"H. Jhamtani and T. Berg-Kirkpatrick, \u201cTruth-conditional captions for time series data,\u201d Proc. of the 2021 Conf. on Empirical Methods in Natural Language Processing, pp. 719-733, 2021. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.55","DOI":"10.18653\/v1\/2021.emnlp-main.55"},{"key":"key-10.20965\/jaciii.2025.p1427-6","doi-asserted-by":"crossref","unstructured":"S. Murakami, A. Watanabe, A. Miyazawa, K. Goshima, T. Yanase, H. Takamura, and Y. Miyao, \u201cLearning to generate market comments from stock prices,\u201d Proc. of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1374-1384, 2017. https:\/\/doi.org\/10.18653\/v1\/P17-1126","DOI":"10.18653\/v1\/P17-1126"},{"key":"key-10.20965\/jaciii.2025.p1427-7","doi-asserted-by":"crossref","unstructured":"K. Aoki, A. Miyazawa, T. Ishigaki, T. Aoki, H. Noji, K. Goshima, I. Kobayashi, H. Takamura, and Y. Miyao, \u201cControlling contents in data-to-document generation with human-designed topic labels,\u201d Proc. of the 12th Int. Conf. on Natural Language Generation, pp. 323-332, 2019. https:\/\/doi.org\/10.18653\/v1\/W19-8640.","DOI":"10.18653\/v1\/W19-8640"},{"key":"key-10.20965\/jaciii.2025.p1427-8","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, \u201cAttention is all you need,\u201d arXiv preprint, arXiv.1706.03762, 2023. https:\/\/doi.org\/10.48550\/arXiv.1706.03762"},{"key":"key-10.20965\/jaciii.2025.p1427-9","doi-asserted-by":"crossref","unstructured":"L. Gong, J. Crego, and J. Senellart, \u201cEnhanced transformer model for data-to-text generation,\u201d Proc. of the 3rd Workshop on Neural Generation and Translation, pp. 148-156, 2019. https:\/\/doi.org\/10.18653\/v1\/D19-5615","DOI":"10.18653\/v1\/D19-5615"},{"key":"key-10.20965\/jaciii.2025.p1427-10","doi-asserted-by":"crossref","unstructured":"L. Li, C. Ma, Y. Yue, and D. Hu, \u201cImproving encoder by auxiliary supervision tasks for table-to-text generation,\u201d Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int. Joint Conf. on Natural Language Processing (Volume 1: Long Papers), pp. 5979-5989, 2021. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.466.","DOI":"10.18653\/v1\/2021.acl-long.466"},{"key":"key-10.20965\/jaciii.2025.p1427-11","unstructured":"C. Rebuffel, L. Soulier, G. Scoutheeten, and P. Gallinari, \u201cA hierarchical model for data-to-text generation,\u201d arXiv preprint, arXiv.1912.10011, 2019. https:\/\/doi.org\/10.48550\/arXiv.1912.10011"},{"key":"key-10.20965\/jaciii.2025.p1427-12","doi-asserted-by":"crossref","unstructured":"S. Murakami, S. Tanaka, M. Hangyo, H. Kamigaito, K. Funakoshi, H. Takamura, and M. Okumura, \u201cGenerating weather comments from meteorological simulations,\u201d Proc. of the 16th Conf. of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 1462-1473, 2021. https:\/\/doi.org\/10.18653\/v1\/2021.eacl-main.125.","DOI":"10.18653\/v1\/2021.eacl-main.125"},{"key":"key-10.20965\/jaciii.2025.p1427-13","unstructured":"S. V. Mehta, J. Rao, Y. Tay, M. Kale, A. P. Parikh, and E. Strubell, \u201cImproving compositional generalization with self-training for data-to-text generation,\u201d arXiv preprint, arXiv.2110.08467, 2022. https:\/\/doi.org\/10.48550\/arXiv.2110.08467"},{"key":"key-10.20965\/jaciii.2025.p1427-14","doi-asserted-by":"crossref","unstructured":"J. Rao, K. Upasani, A. Balakrishnan, M. White, A. Kumar, and R. Subba, \u201cA tree-to-sequence model for neural NLG in task-oriented dialog,\u201d Proc. of the 12th Int. Conf. on Natural Language Generation, pp. 95-100, 2019. https:\/\/doi.org\/10.18653\/v1\/W19-8611","DOI":"10.18653\/v1\/W19-8611"},{"key":"key-10.20965\/jaciii.2025.p1427-15","doi-asserted-by":"crossref","unstructured":"T. Liu, F. Luo, Q. Xia, S. Ma, B. Chang, and Z. Sui, \u201cHierarchical encoder with auxiliary supervision for neural table-to-text generation: Learning better representation for tables,\u201d Proc. of the Thirty-Third AAAI Conf. on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conf. and Ninth AAAI Symp. on Educational Advances in Artificial Intelligence, 2019. https:\/\/doi.org\/10.1609\/aaai.v33i01.33016786","DOI":"10.1609\/aaai.v33i01.33016786"},{"key":"key-10.20965\/jaciii.2025.p1427-16","doi-asserted-by":"crossref","unstructured":"P. Pasupat and P. Liang, \u201cCompositional semantic parsing on semi-structured tables,\u201d Proc. of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th Int. Joint Conf. on Natural Language Processing (Volume 1: Long Papers), pp. 1470-1480, arXiv preprint, arXiv.1508.00305, 2015. https:\/\/doi.org\/10.48550\/arXiv.1508.00305","DOI":"10.3115\/v1\/P15-1142"},{"key":"key-10.20965\/jaciii.2025.p1427-17","unstructured":"H. Banaee, M. U. Ahmed, and A. Loutfi, \u201cTowards NLG for physiological data monitoring with body area networks,\u201d Proc. of the 14th European Workshop on Natural Language Generation, pp. 193-197, 2013."},{"key":"key-10.20965\/jaciii.2025.p1427-18","unstructured":"A. Schneider, A. Mort, C. Mellish, E. Reiter, P. Wilson, and P.-L. Vaudry, \u201cMIME \u2013 NLG in pre-hospital care,\u201d Proc. of the 14th European Workshop on Natural Language Generation, pp. 152-156, 2013."},{"key":"key-10.20965\/jaciii.2025.p1427-19","doi-asserted-by":"crossref","unstructured":"G. Moyse and M.-J. Lesot, \u201cLinguistic summaries of locally periodic time series,\u201d Fuzzy Sets and Systems, Vol.285, pp. 94-117, 2016. https:\/\/doi.org\/10.1016\/j.fss.2015.06.016.","DOI":"10.1016\/j.fss.2015.06.016"},{"key":"key-10.20965\/jaciii.2025.p1427-20","doi-asserted-by":"crossref","unstructured":"H. Hatipo\u011flu, E. Boran, M. Avci, and D. Akay, \u201cLinguistic summarization of europe brent spot price time series along with the interpretations from the perspective of turkey,\u201d Int. J. of Intelligent Systems, Vol.29, No.10, 2014. https:\/\/doi.org\/10.1002\/int.21671","DOI":"10.1002\/int.21671"},{"key":"key-10.20965\/jaciii.2025.p1427-21","doi-asserted-by":"crossref","unstructured":"D. Sanchez-Valdes, A. Alvarez-Alvarez, and G. Trivino, \u201cDynamic linguistic descriptions of time series applied to self-track the physical activity,\u201d Fuzzy Sets and Systems, Vol.285, pp. 162-181, 2015. https:\/\/doi.org\/10.1016\/j.fss.2015.06.018","DOI":"10.1016\/j.fss.2015.06.018"},{"key":"key-10.20965\/jaciii.2025.p1427-22","doi-asserted-by":"crossref","unstructured":"J. F. Gait\u00e1n-Guerrero, J. L. L\u00f3pez Ruiz, M. Espinilla, and C. Mart\u00ednez-Cruz, \u201cToward an interpretable continuous glucose monitoring data modeling,\u201d IEEE Internet of Things J., Vol.11, No.19, pp. 31080-31094, 2024. https:\/\/doi.org\/10.1109\/JIOT.2024.3419260","DOI":"10.1109\/JIOT.2024.3419260"},{"key":"key-10.20965\/jaciii.2025.p1427-23","doi-asserted-by":"crossref","unstructured":"A. Cascallar-Fuentes, J. Gallego-Fern\u00e1ndez, A. Ramos-Soto, A. Saunders-Est\u00e9vez, and A. Bugar\u00edn-Diz, \u201cAutomatic generation of textual descriptions in data-to-text systems using a fuzzy temporal ontology: Application in air quality index data series,\u201d Applied Soft Computing, Vol.119, Article No.108612, 2022. https:\/\/doi.org\/10.1016\/j.asoc.2022.108612","DOI":"10.1016\/j.asoc.2022.108612"},{"key":"key-10.20965\/jaciii.2025.p1427-24","doi-asserted-by":"crossref","unstructured":"Y. Hamazono, Y. Uehara, H. Noji, Y. Miyao, H. Takamura, and I. Kobayashi, \u201cMarket comment generation from data with noisy alignments,\u201d Proc. of the 13th Int. Conf. on Natural Language Generation, pp. 148-157, 2020. https:\/\/doi.org\/10.18653\/v1\/2020.inlg-1.21","DOI":"10.18653\/v1\/2020.inlg-1.21"},{"key":"key-10.20965\/jaciii.2025.p1427-25","doi-asserted-by":"crossref","unstructured":"S. Tuli, G. Casale, and N. R. Jennings, \u201cTranAD: Deep transformer networks for anomaly detection in multivariate time series data,\u201d arXiv preprint, arXiv.2201.07284, 2022. https:\/\/doi.org\/10.48550\/arXiv.2201.07284","DOI":"10.14778\/3514061.3514067"},{"key":"key-10.20965\/jaciii.2025.p1427-26","unstructured":"J. Shi, M. Jain, and G. Narasimhan, \u201cTime series forecasting (TSF) using various deep learning models,\u201d arXiv preprint, arXiv.2204.11115, 2022. https:\/\/doi.org\/10.48550\/arXiv.2204.11115"},{"key":"key-10.20965\/jaciii.2025.p1427-27","doi-asserted-by":"crossref","unstructured":"K. Papineni, S. Roukos, T. Ward, and W.-J. Zhu, \u201cBLEU: A method for automatic evaluation of machine translation,\u201d Proc. of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 311-318, 2022. https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"key-10.20965\/jaciii.2025.p1427-28","unstructured":"C.-Y. Lin, \u201cROUGE: A package for automatic evaluation of summaries,\u201d Text Summarization Branches Out, pp. 74-81, 2004."},{"key":"key-10.20965\/jaciii.2025.p1427-29","unstructured":"T. Zhang, V. Kishore, F. Wu, K. Q. Weinberger, and Y. Artzi, \u201cBERTScore: Evaluating text generation with BERT,\u201d arXiv preprint, arXiv.1904.09675, 2020. https:\/\/doi.org\/10.48550\/arXiv.1904.09675"},{"key":"key-10.20965\/jaciii.2025.p1427-30","unstructured":"S. Banerjee and A. Lavie, \u201cMETEOR: An automatic metric for MT evaluation with improved correlation with human judgments,\u201d Proc. of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65-72, 2005."},{"key":"key-10.20965\/jaciii.2025.p1427-31","unstructured":"J. Vig, \u201cVisualizing attention in transformer-based language representation models,\u201d arXiv preprint, arXiv.1904.02679, 2019. https:\/\/doi.org\/10.48550\/arXiv.1904.02679"}],"container-title":["Journal of Advanced Computational Intelligence and Intelligent Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.fujipress.jp\/main\/wp-content\/themes\/Fujipress\/hyosetsu.php?ppno=jacii002900060018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T15:04:18Z","timestamp":1763564658000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.fujipress.jp\/jaciii\/jc\/jacii002900061427"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,20]]},"references-count":31,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,11,20]]},"published-print":{"date-parts":[[2025,11,20]]}},"URL":"https:\/\/doi.org\/10.20965\/jaciii.2025.p1427","relation":{},"ISSN":["1883-8014","1343-0130"],"issn-type":[{"type":"electronic","value":"1883-8014"},{"type":"print","value":"1343-0130"}],"subject":[],"published":{"date-parts":[[2025,11,20]]}}}