{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:05:16Z","timestamp":1750219516777,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819681723","type":"print"},{"value":"9789819681730","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-8173-0_31","type":"book-chapter","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T11:41:40Z","timestamp":1750160500000},"page":"393-404","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual Learning Between Molecules and\u00a0Natural Language"],"prefix":"10.1007","author":[{"given":"Haodi","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Yong","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Liang-Jie","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Weicheng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yuanfeng","family":"Song","sequence":"additional","affiliation":[]},{"given":"Di","family":"Jiang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Chen, A., Lou, L., Chen, K., Bai, X., Xiang, Y., Yang, M., et\u00a0al.: DUAL-REFLECT: enhancing large language models for reflective translation through dual learning feedback mechanisms. In: ACL (2024)","DOI":"10.18653\/v1\/2024.acl-short.64"},{"key":"31_CR2","unstructured":"Christofidellis, D., Giannone, G., Born, J., Winther, O., Laino, T., Manica, M.: Unifying molecular and textual representations via multi-task language modelling. In: ICML (2023)"},{"key":"31_CR3","unstructured":"Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., et\u00a0al.: The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"issue":"6","key":"31_CR4","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1021\/ci010132r","volume":"42","author":"JL Durant","year":"2002","unstructured":"Durant, J.L., Leland, B.A., Henry, D.R., Nourse, J.G.: Reoptimization of mdl keys for use in drug discovery. J. Chem. Inf. Comput. Sci. 42(6), 1273\u20131280 (2002)","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Edwards, C., Lai, T., Ros, K., Honke, G., Cho, K., Ji, H.: Translation between molecules and natural language. In: EMNLP (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.26"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Edwards, C., Zhai, C., Ji, H.: Text2Mol: cross-modal molecule retrieval with natural language queries. In: EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.47"},{"key":"31_CR7","unstructured":"Fei, H., Wu, S., Ren, Y., Zhang, M.: Matching structure for dual learning. In: ICML (2022)"},{"issue":"D1","key":"31_CR8","doi-asserted-by":"publisher","first-page":"D1214","DOI":"10.1093\/nar\/gkv1031","volume":"44","author":"J Hastings","year":"2016","unstructured":"Hastings, J., Owen, G., Dekker, A., Ennis, M., Kale, N., Muthukrishnan, V., et al.: ChEBI in 2016: improved services and an expanding collection of metabolites. Nucleic Acids Res. 44(D1), D1214\u2013D1219 (2016)","journal-title":"Nucleic Acids Res."},{"key":"31_CR9","unstructured":"He, D., et al.: Dual learning for machine translation. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"issue":"D1","key":"31_CR10","doi-asserted-by":"publisher","first-page":"D1373","DOI":"10.1093\/nar\/gkac956","volume":"51","author":"S Kim","year":"2023","unstructured":"Kim, S., Chen, J., Cheng, T., Gindulyte, A., He, J., He, S., et al.: Pubchem 2023 update. Nucleic Acids Res. 51(D1), D1373\u2013D1380 (2023)","journal-title":"Nucleic Acids Res."},{"issue":"4","key":"31_CR11","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/aba947","volume":"1","author":"M Krenn","year":"2020","unstructured":"Krenn, M., H\u00e4se, F., Nigam, A., Friederich, P., Aspuru-Guzik, A.: Self-referencing embedded strings (SELFIES): a 100% robust molecular string representation. Mach. Learn. Sci. Technol. 1(4), 045024 (2020)","journal-title":"Mach. Learn. Sci. Technol."},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Visual question generation as dual task of visual question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00640"},{"key":"31_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108073","volume":"171","author":"P Liu","year":"2024","unstructured":"Liu, P., Ren, Y., Tao, J., Ren, Z.: GIT-MoL: a multi-modal large language model for molecular science with graph, image, and text. Comput. Biol. Med. 171, 108073 (2024)","journal-title":"Comput. Biol. Med."},{"key":"31_CR14","unstructured":"Luo, Y., Yang, K., Hong, M., Liu, X.Y., Nie, Z.: MolFM: a multimodal molecular foundation model. arXiv preprint arXiv:2307.09484 (2023)"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Oniani, D., et al.: Emerging opportunities of using large language models for translation between drug molecules and indications. Sci. Rep. (2024)","DOI":"10.1038\/s41598-024-61124-0"},{"key":"31_CR16","unstructured":"OpenAI: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Pei, Q., Wu, L., Gao, K., Liang, X., Fang, Y., Zhu, J., et\u00a0al.: BioT5+: towards generalized biological understanding with IUPAC integration and multi-task tuning. In: ACL Findings (2024)","DOI":"10.18653\/v1\/2024.findings-acl.71"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Pei, Q., Zhang, W., Zhu, J., Wu, K., Gao, K., Wu, L., et\u00a0al.: BioT5: enriching cross-modal integration in biology with chemical knowledge and natural language associations. In: EMNLP (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.70"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Preuer, K., Renz, P., Unterthiner, T., Hochreiter, S., Klambauer, G.: Fr\u00e9chet ChemNet distance: a metric for generative models for molecules in drug discovery. J. Chem. Inf. Modeling (2018)","DOI":"10.1021\/acs.jcim.8b00234"},{"issue":"140","key":"31_CR20","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"issue":"5","key":"31_CR21","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","volume":"50","author":"D Rogers","year":"2010","unstructured":"Rogers, D., Hahn, M.: Extended-connectivity fingerprints. J. Chem. Inf. Model. 50(5), 742\u2013754 (2010)","journal-title":"J. Chem. Inf. Model."},{"issue":"10","key":"31_CR22","doi-asserted-by":"publisher","first-page":"2111","DOI":"10.1021\/acs.jcim.5b00543","volume":"55","author":"N Schneider","year":"2015","unstructured":"Schneider, N., Sayle, R.A., Landrum, G.A.: Get your atoms in order-an open-source implementation of a novel and robust molecular canonicalization algorithm. J. Chem. Inf. Model. 55(10), 2111\u20132120 (2015)","journal-title":"J. Chem. Inf. Model."},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Song, Y., Huang, X., Zhao, X., Wong, R.C.W.: Natural language generation meets data visualization: vis-to-text and its duality with text-to-vis. In: ICDM (2023)","DOI":"10.1109\/ICDM58522.2023.00171"},{"key":"31_CR24","unstructured":"Taylor, R., Kardas, M., Cucurull, G., Scialom, T., Hartshorn, A., et\u00a0al.: Galactica: a large language model for science. arXiv preprint arXiv:2211.09085 (2022)"},{"key":"31_CR25","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., et\u00a0al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"31_CR26","unstructured":"Wei, B., Li, G., Xia, X., Fu, Z., Jin, Z.: Code generation as a dual task of code summarization. In: NeurIPS (2019)"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Weininger, D.: SMILES, a chemical language and information system. 1. introduction to methodology and encoding rules. J. Chem. Inf. Comput. Sci. 28(1), 31\u201336 (1988)","DOI":"10.1021\/ci00057a005"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Ye, W., Xie, R., Zhang, J., Hu, T., Wang, X., Zhang, S.: Leveraging code generation to improve code retrieval and summarization via dual learning. In: The Web Conference (2020)","DOI":"10.1145\/3366423.3380295"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Zeinalipour, K., Jamshidi, N., Bianchini, M., Maggini, M., Gori, M.: Design proteins using large language models: enhancements and comparative analyses. In: the 1st Workshop on Language + Molecules (L+M 2024) (2024)","DOI":"10.18653\/v1\/2024.langmol-1.5"},{"key":"31_CR30","doi-asserted-by":"crossref","unstructured":"Zeng, X., Wang, F., Luo, Y., Kang, S.G., Tang, J., Lightstone, F.C., et\u00a0al.: Deep generative molecular design reshapes drug discovery. Cell Rep. Med. 3(12) (2022)","DOI":"10.1016\/j.xcrm.2022.100794"},{"issue":"1","key":"31_CR31","doi-asserted-by":"publisher","first-page":"862","DOI":"10.1038\/s41467-022-28494-3","volume":"13","author":"Z Zeng","year":"2022","unstructured":"Zeng, Z., Yao, Y., Liu, Z., Sun, M.: A deep-learning system bridging molecule structure and biomedical text with comprehension comparable to human professionals. Nat. Commun. 13(1), 862 (2022)","journal-title":"Nat. Commun."},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, W., et al.: Dual learning for cross-domain image captioning. In: CIKM (2017)","DOI":"10.1145\/3132847.3132920"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8173-0_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T11:41:50Z","timestamp":1750160510000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8173-0_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819681723","9789819681730"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8173-0_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"18 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}