{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T10:21:18Z","timestamp":1773829278803,"version":"3.50.1"},"reference-count":111,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:00:00Z","timestamp":1732579200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:00:00Z","timestamp":1732579200000},"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":["Constraints"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s10601-024-09376-5","type":"journal-article","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T05:04:05Z","timestamp":1732597445000},"page":"261-299","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Ner4Opt: named entity recognition for optimization modelling from natural language"],"prefix":"10.1007","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4672-6830","authenticated-orcid":false,"given":"Serdar","family":"Kad\u0131o\u011flu","sequence":"first","affiliation":[]},{"given":"Parag","family":"Pravin Dakle","sequence":"additional","affiliation":[]},{"given":"Karthik","family":"Uppuluri","sequence":"additional","affiliation":[]},{"given":"Regina","family":"Politi","sequence":"additional","affiliation":[]},{"given":"Preethi","family":"Raghavan","sequence":"additional","affiliation":[]},{"given":"SaiKrishna","family":"Rallabandi","sequence":"additional","affiliation":[]},{"given":"Ravisutha","family":"Srinivasamurthy","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,26]]},"reference":[{"issue":"2","key":"9376_CR1","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/s10601-018-9281-x","volume":"23","author":"P Laborie","year":"2018","unstructured":"Laborie, P., Rogerie, J., Shaw, P., & Vil\u00edm, P. (2018). IBM ILOG CP optimizer for scheduling - 20+ years of scheduling with constraints at IBM\/ILOG. Constraints An Int. J., 23(2), 210\u2013250. https:\/\/doi.org\/10.1007\/s10601-018-9281-x","journal-title":"Constraints An Int. J."},{"key":"9376_CR2","unstructured":"Guns, T.: On learning and branching: a survey. The 18th workshop on Constraint Modelling and Reformulation. (2019)"},{"key":"9376_CR3","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1007\/978-3-540-74970-7_38","volume-title":"Principles and Practice of Constraint Programming - CP 2007","author":"N Nethercote","year":"2007","unstructured":"Nethercote, N., Stuckey, P. J., Becket, R., Brand, S., Duck, G. J., & Tack, G. (2007). Minizinc: Towards a standard cp modelling language. In C. Bessi\u00e8re (Ed.), Principles and Practice of Constraint Programming - CP 2007 (pp. 529\u2013543). Berlin, Heidelberg: Springer."},{"key":"9376_CR4","volume-title":"The OPL Optimization Programming Language","author":"P Van Hentenryck","year":"1999","unstructured":"Van Hentenryck, P. (1999). The OPL Optimization Programming Language. Cambridge, MA, USA: MIT Press."},{"key":"9376_CR5","doi-asserted-by":"crossref","unstructured":"Dakle, P.P., Kad\u0131o\u011flu, S., Uppuluri, K., Politi, R., Raghavan, P., Rallabandi, S., Srinivasamurthy, R.: Ner4opt: Named entity recognition for optimization modelling from natural language. In: International Conference on Integration of Constraint Programming, Artificial Intelligence, and Operations Research, pp. 299\u2013319 (2023). Springer","DOI":"10.1007\/978-3-031-33271-5_20"},{"key":"9376_CR6","doi-asserted-by":"publisher","unstructured":"Ramamonjison, R., Li, H., Yu, T.T., He, S., Rengan, V., Banitalebi-Dehkordi, A., Zhou, Z., Zhang, Y.: Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions. arXiv (2022). https:\/\/doi.org\/10.48550\/ARXIV.2209.15565.","DOI":"10.48550\/ARXIV.2209.15565"},{"key":"9376_CR7","doi-asserted-by":"crossref","unstructured":"Grishman, R., Sundheim, B.: Message Understanding Conference- 6: A brief history. In: COLING 1996 Volume 1: The 16th International Conference on Computational Linguistics (1996). https:\/\/aclanthology.org\/C96-1079","DOI":"10.3115\/992628.992709"},{"key":"9376_CR8","doi-asserted-by":"crossref","unstructured":"Tjong Kim Sang, E.F.: Introduction to the CoNLL-2002 shared task: Language-independent named entity recognition. In: COLING-02: The 6th Conference on Natural Language Learning 2002 (CoNLL-2002) (2002). https:\/\/aclanthology.org\/W02-2024","DOI":"10.3115\/1118853.1118877"},{"key":"9376_CR9","unstructured":"Chinchor, N., Robinson, P.: Appendix E: MUC-7 named entity task definition (version 3.5). In: Seventh Message Understanding Conference (MUC-7): Proceedings of a Conference Held in Fairfax, Virginia, April 29 - May 1, 1998 (1998). https:\/\/aclanthology.org\/M98-1028"},{"key":"9376_CR10","unstructured":"Le Meur, C., Galliano, S., Geoffrois, E.: Conventions d\u2019annotations en entit\u00e9s nomm\u00e9es-ester. Rapport technique de la campagne Ester. (2004)"},{"key":"9376_CR11","unstructured":"OpenAI: GPT-4 Technical Report (2023)"},{"key":"9376_CR12","unstructured":"Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Brodley, C.E., Danyluk, A.P. (eds.) Proceedings of the Eighteenth International Conference on Machine Learning (ICML 2001), Williams College, Williamstown, MA, USA, June 28 - July 1, 2001, pp. 282\u2013289. Morgan Kaufmann, USA (2001)"},{"key":"9376_CR13","unstructured":"Quattoni, A., Collins, M., Darrell, T.: Conditional random fields for object recognition. Advances in neural information processing systems. 17 (2004)"},{"key":"9376_CR14","doi-asserted-by":"crossref","unstructured":"Ratinov, L., Roth, D.: Design challenges and misconceptions in named entity recognition. In: Proceedings of the thirteenth conference on computational natural language learning (CoNLL-2009), pp. 147\u2013155 (2009)","DOI":"10.3115\/1596374.1596399"},{"issue":"8","key":"9376_CR15","doi-asserted-by":"publisher","first-page":"1270","DOI":"10.1109\/5.880083","volume":"88","author":"R Rosenfeld","year":"2000","unstructured":"Rosenfeld, R. (2000). Two decades of statistical language modeling: where do we go from here? Proceedings of the IEEE., 88(8), 1270\u20131278. https:\/\/doi.org\/10.1109\/5.880083","journal-title":"Proceedings of the IEEE."},{"issue":"7","key":"9376_CR16","doi-asserted-by":"publisher","first-page":"1001","DOI":"10.1109\/29.32278","volume":"37","author":"LR Bahl","year":"1989","unstructured":"Bahl, L. R., Brown, P. F., De Souza, P. V., & Mercer, R. L. (1989). A tree-based statistical language model for natural language speech recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing., 37(7), 1001\u20131008.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing."},{"key":"9376_CR17","volume-title":"Statistical Methods for Speech Recognition","author":"F Jelinek","year":"1998","unstructured":"Jelinek, F. (1998). Statistical Methods for Speech Recognition. USA: MIT press."},{"key":"9376_CR18","doi-asserted-by":"crossref","unstructured":"Thede, S.M., Harper, M. (1999). A second-order hidden markov model for part-of-speech tagging. In: Proceedings of the 37th annual meeting of the association for computational linguistics, pp. 175\u2013182","DOI":"10.3115\/1034678.1034712"},{"key":"9376_CR19","doi-asserted-by":"publisher","DOI":"10.1145\/1034780.1034781","volume-title":"Introduction to the special issue on statistical language modeling","author":"J Gao","year":"2004","unstructured":"Gao, J., & Lin, C.-Y. (2004). Introduction to the special issue on statistical language modeling. NY, USA: ACM New York."},{"key":"9376_CR20","unstructured":"Brants, T., Popat, A., Xu, P., Och, F.J., Dean, J. (2007). Large language models in machine translation. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 858\u2013867"},{"key":"9376_CR21","unstructured":"Bengio, Y., Ducharme, R., Vincent, P. (2000). A neural probabilistic language model. Advances in neural information processing systems. 13"},{"key":"9376_CR22","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., Cernock\u1ef3, J., Khudanpur, S. (2010). Recurrent neural network based language model. In: Interspeech, vol. 2, pp. 1045\u20131048. Makuhari","DOI":"10.21437\/Interspeech.2010-343"},{"key":"9376_CR23","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J. (2013). Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems. 26"},{"key":"9376_CR24","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J. (2013). Efficient estimation of word representations in vector space. In: Bengio, Y., LeCun, Y. (eds.) 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, Arizona, USA, May 2-4, 2013, Workshop Track Proceedings. arXiv:1301.3781"},{"key":"9376_CR25","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems. 30"},{"key":"9376_CR26","doi-asserted-by":"publisher","unstructured":"Peters, M.E., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., Zettlemoyer, L. (2018). Deep contextualized word representations. In: Walker, M., Ji, H., Stent, A. (eds.) Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 2227\u20132237. Association for Computational Linguistics, New Orleans, Louisiana. https:\/\/doi.org\/10.18653\/v1\/N18-1202. https:\/\/aclanthology.org\/N18-1202","DOI":"10.18653\/v1\/N18-1202"},{"key":"9376_CR27","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 conference of the north american chapter of the association for computational linguistics: human language technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota. https:\/\/doi.org\/10.18653\/v1\/N19-1423. https:\/\/aclanthology.org\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"issue":"8","key":"9376_CR28","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al. (2019). Language models are unsupervised multitask learners. OpenAI blog., 1(8), 9.","journal-title":"OpenAI blog."},{"key":"9376_CR29","doi-asserted-by":"publisher","unstructured":"Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., Zettlemoyer, L. (2020). BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7871\u20137880. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.703. https:\/\/aclanthology.org\/2020.acl-main.703","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"9376_CR30","doi-asserted-by":"publisher","unstructured":"Mohammadi, S., Chapon, M. (2020). Investigating the performance of fine-tuned text classification models based-on bert. In: 2020 IEEE 22nd international conference on high performance computing and communications; IEEE 18th International Conference on Smart City; IEEE 6th International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS), pp. 1252\u20131257. https:\/\/doi.org\/10.1109\/HPCC-SmartCity-DSS50907.2020.00162","DOI":"10.1109\/HPCC-SmartCity-DSS50907.2020.00162"},{"key":"9376_CR31","unstructured":"Mosbach, M., Andriushchenko, M., Klakow, D. (2021). On the stability of fine-tuning bert: Misconceptions, explanations, and strong baselines. In: International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nzpLWnVAyah"},{"key":"9376_CR32","doi-asserted-by":"publisher","unstructured":"Xu, R., Luo, F., Zhang, Z., Tan, C., Chang, B., Huang, S., Huang, F. (2021). Raise a child in large language model: Towards effective and generalizable fine-tuning. In: Moens, M.-F., Huang, X., Specia, L., Yih, S.W.-t. (eds.) Proceedings of the 2021 conference on empirical methods in natural language processing, pp. 9514\u20139528. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.749. https:\/\/aclanthology.org\/2021.emnlp-main.749","DOI":"10.18653\/v1\/2021.emnlp-main.749"},{"key":"9376_CR33","doi-asserted-by":"publisher","unstructured":"He, R., Liu, L., Ye, H., Tan, Q., Ding, B., Cheng, L., Low, J., Bing, L., Si, L. (2021). On the effectiveness of adapter-based tuning for pretrained language model adaptation. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (Volume 1: Long Papers), pp. 2208\u20132222. Association for Computational Linguistics, Online. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.172. https:\/\/aclanthology.org\/2021.acl-long.172","DOI":"10.18653\/v1\/2021.acl-long.172"},{"key":"9376_CR34","first-page":"37484","volume-title":"Advances in Neural Information Processing Systems","author":"Y Sun","year":"2022","unstructured":"Sun, Y., Chen, Q., He, X., Wang, J., Feng, H., Han, J., Ding, E., Cheng, J., Li, Z., & Wang, J. (2022). Singular value fine-tuning: Few-shot segmentation requires few-parameters fine-tuning. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, & A. Oh (Eds.), Advances in Neural Information Processing Systems (Vol. 35, pp. 37484\u201337496). USA: Curran Associates Inc."},{"issue":"11","key":"9376_CR35","doi-asserted-by":"publisher","first-page":"12799","DOI":"10.1609\/aaai.v37i11.26505","volume":"37","author":"Z Fu","year":"2023","unstructured":"Fu, Z., Yang, H., So, A.M.-C., Lam, W., Bing, L., & Collier, N. (2023). On the effectiveness of parameter-efficient fine-tuning. Proceedings of the AAAI Conference on Artificial Intelligence., 37(11), 12799\u201312807. https:\/\/doi.org\/10.1609\/aaai.v37i11.26505","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence."},{"key":"9376_CR36","doi-asserted-by":"crossref","unstructured":"Lamproudis, A., Henriksson, A., Dalianis, H. (2021). Developing a clinical language model for Swedish: Continued pretraining of generic BERT with in-domain data. In: Mitkov, R., Angelova, G. (eds.) Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pp. 790\u2013797. INCOMA Ltd., Held Online. https:\/\/aclanthology.org\/2021.ranlp-1.90","DOI":"10.26615\/978-954-452-072-4_090"},{"key":"9376_CR37","unstructured":"Gupta, K., Th\u00e9rien, B., Ibrahim, A., Richter, M.L., Anthony, Q., Belilovsky, E., Rish, I., Lesort, T. (2023). Continual pre-training of large language models: How to (re) warm your model? . arXiv:2308.04014."},{"key":"9376_CR38","unstructured":"Y\u0131ld\u0131z, \u00c7., Ravichandran, N.K., Punia, P., Bethge, M., Ermis, B. (2024). Investigating continual pretraining in large language models: Insights and implications. arXiv:2402.17400."},{"key":"9376_CR39","doi-asserted-by":"crossref","unstructured":"Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzm\u00e1n, F., Grave, E., Ott, M., Zettlemoyer, L., Stoyanov, V. (2019). Unsupervised cross-lingual representation learning at scale. arXiv:1911.02116.","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"9376_CR40","unstructured":"Pascanu, R., Mikolov, T., Bengio, Y. (2013). On the difficulty of training recurrent neural networks. In: International conference on machine learning, pp. 1310\u20131318. PMLR"},{"key":"9376_CR41","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv:1907.11692."},{"key":"9376_CR42","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805."},{"key":"9376_CR43","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R. (2018). Glue: A multi-task benchmark and analysis platform for natural language understanding. arXiv:1804.07461.","DOI":"10.18653\/v1\/W18-5446"},{"key":"9376_CR44","doi-asserted-by":"crossref","unstructured":"Lai, G., Xie, Q., Liu, H., Yang, Y., Hovy, E. (2017). Race: Large-scale reading comprehension dataset from examinations. arXiv:1704.04683.","DOI":"10.18653\/v1\/D17-1082"},{"key":"9376_CR45","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P. (2016). Squad: 100,000+ questions for machine comprehension of text. arXiv:1606.05250.","DOI":"10.18653\/v1\/D16-1264"},{"key":"9376_CR46","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Jia, R., Liang, P. (2018). Know what you don\u2019t know: Unanswerable questions for squad. arXiv:1806.03822.","DOI":"10.18653\/v1\/P18-2124"},{"key":"9376_CR47","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al. (2018). Improving language understanding by generative pre-training. OpenAI"},{"key":"9376_CR48","doi-asserted-by":"crossref","unstructured":"Howard, J., Ruder, S. (2018). Universal language model fine-tuning for text classification. arXiv:1801.06146.","DOI":"10.18653\/v1\/P18-1031"},{"key":"9376_CR49","unstructured":"Araci, D. (2019). Finbert: Financial sentiment analysis with pre-trained language models. arXiv:1908.10063."},{"key":"9376_CR50","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682","author":"J Lee","year":"2019","unstructured":"Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2019). BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics.[SPACE]https:\/\/doi.org\/10.1093\/bioinformatics\/btz682","journal-title":"Bioinformatics."},{"key":"9376_CR51","doi-asserted-by":"publisher","unstructured":"Beltagy, I., Lo, K., Cohan, A. (2019). SciBERT: A pretrained language model for scientific text. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3615\u20133620. Association for Computational Linguistics, Hong Kong, China. https:\/\/doi.org\/10.18653\/v1\/D19-1371.<error l=\"400\" c=\"Undefined command \" \/>https:\/\/aclanthology.org\/D19-1371","DOI":"10.18653\/v1\/D19-1371"},{"key":"9376_CR52","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441","volume-title":"Convex Optimization","author":"S Boyd","year":"2004","unstructured":"Boyd, S., Boyd, S. P., & Vandenberghe, L. (2004). Convex Optimization. USA: Cambridge University Press."},{"key":"9376_CR53","volume-title":"An Introduction to Linear Programming and Game Theory","author":"PR Thie","year":"2011","unstructured":"Thie, P. R., & Keough, G. E. (2011). An Introduction to Linear Programming and Game Theory. USA: John Wiley & Sons."},{"key":"9376_CR54","unstructured":"Hildebrand, R., Poirrier, L., Bish, D., Moran, D. (2022). Mathematical programming and operations research. https:\/\/github.com\/open-optimization\/open-optimization-or-book"},{"key":"9376_CR55","doi-asserted-by":"crossref","unstructured":"Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2019). Huggingface\u2019s transformers: State-of-the-art natural language processing. arXiv:1910.03771.","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"9376_CR56","unstructured":"Rajapakse, T.C. (2019). Simple Transformers. https:\/\/github.com\/ThilinaRajapakse\/simpletransformers"},{"key":"9376_CR57","volume-title":"spaCy: Industrial-Strength Natural Language Processing in Python","author":"M Honnibal","year":"2020","unstructured":"Honnibal, M., Montani, I., Van Landeghem, S., & Boyd, A. (2020). spaCy: Industrial-Strength Natural Language Processing in Python. Honolulu, HI, USA: Zenodo."},{"issue":"4","key":"9376_CR58","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1145\/279232.279236","volume":"23","author":"C Zhu","year":"1997","unstructured":"Zhu, C., Byrd, R. H., Lu, P., & Nocedal, J. (1997). Algorithm 778: L-bfgs-b: Fortran subroutines for large-scale bound-constrained optimization. ACM Transactions on Mathematical Software (TOMS)., 23(4), 550\u2013560.","journal-title":"ACM Transactions on Mathematical Software (TOMS)."},{"key":"9376_CR59","unstructured":"Fisch, A., Jia, R., Schuster, T. (2022). Uncertainty estimation for natural language processing. In: COLING. https:\/\/sites.google.com\/view\/uncertainty-nlp"},{"key":"9376_CR60","unstructured":"Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., Neubig, G. (2021). Pre-train, Prompt, and Predict: a systematic survey of prompting methods in natural language processing"},{"key":"9376_CR61","unstructured":"Ramamonjison, R., Yu, T.T., Li, R., Li, H., Carenini, G., Ghaddar, B., He, S., Mostajabdaveh, M., Banitalebi-Dehkordi, A., Zhou, Z., Zhang, Y. (2023). NL4Opt competition: formulating optimization problems based on their natural language descriptions"},{"key":"9376_CR62","unstructured":"He, J., N, M., Vignesh, S., Kumar, D., Uppal, A. (2022). Linear programming word problems formulation using EnsembleCRF NER labeler and T5 text generator with data augmentations"},{"key":"9376_CR63","unstructured":"Wang, K., Chen, Z., Zheng, J. (2023). OPD@NL4Opt: An ensemble approach for the NER task of the optimization problem"},{"key":"9376_CR64","unstructured":"Ning, Y., Liu, J., Qin, L., Xiao, T., Xue, S., Huang, Z., Liu, Q., Chen, E., Wu, J. (2023). A Novel Approach for Auto-Formulation of Optimization Problems"},{"key":"9376_CR65","unstructured":"Doan, X.-D. (2022). VTCC-NLP at NL4Opt competition subtask 1: an ensemble pre-trained language models for named entity recognition"},{"key":"9376_CR66","unstructured":"Tsouros, D., Verhaeghe, H., Kadioglu, S., Guns, T. (2023). Holy grail 2.0: From natural language to constraint models. arXiv:2308.01589."},{"key":"9376_CR67","doi-asserted-by":"crossref","unstructured":"Rau, L.F. (1991). Extracting company names from text. In: Proceedings the Seventh IEEE Conference on Artificial Intelligence Application, pp. 29\u201330. IEEE Computer Society","DOI":"10.1109\/CAIA.1991.120841"},{"key":"9376_CR68","doi-asserted-by":"crossref","unstructured":"Morwal, S., Jahan, N., Chopra, D. (2012). Named entity recognition using hidden markov model (hmm). International Journal on Natural Language Computing (IJNLC) Vol. 1","DOI":"10.5121\/ijnlc.2012.1402"},{"key":"9376_CR69","doi-asserted-by":"crossref","unstructured":"Zhou, G., Su, J. (2002). Named entity recognition using an hmm-based chunk tagger. In: Proceedings of the 40th annual meeting of the association for computational linguistics, pp. 473\u2013480","DOI":"10.3115\/1073083.1073163"},{"key":"9376_CR70","doi-asserted-by":"crossref","unstructured":"Zhao, S. (2004). Named entity recognition in biomedical texts using an hmm model. In: Proceedings of the international joint workshop on natural language processing in biomedicine and its applications (NLPBA\/BioNLP), pp. 87\u201390","DOI":"10.3115\/1567594.1567613"},{"key":"9376_CR71","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805."},{"key":"9376_CR72","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V. (2019). Xlnet: Generalized autoregressive pretraining for language understanding. Advances in neural information processing systems. 32"},{"key":"9376_CR73","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners. Advances in neural information processing systems., 33, 1877\u20131901.","journal-title":"Advances in neural information processing systems."},{"key":"9376_CR74","doi-asserted-by":"crossref","unstructured":"Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzm\u00e1n, F., Grave, E., Ott, M., Zettlemoyer, L., Stoyanov, V. (2019). Unsupervised cross-lingual representation learning at scale. arXiv:1911.02116.","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"9376_CR75","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv:1907.11692."},{"key":"9376_CR76","unstructured":"Yadav, V., Bethard, S. (2019). A survey on recent advances in named entity recognition from deep learning models. arXiv:1910.11470."},{"key":"9376_CR77","doi-asserted-by":"publisher","unstructured":"Kadioglu, S., Malitsky, Y., Sellmann, M., Tierney, K. (2010). ISAC - instance-specific algorithm configuration. In: Coelho, H., Studer, R., Wooldridge, M.J. (eds.) ECAI 2010 - 19th European Conference on Artificial Intelligence, Lisbon, Portugal, August 16-20, 2010, Proceedings. Frontiers in Artificial Intelligence and Applications, vol. 215, pp. 751\u2013756. IOS Press, USA. https:\/\/doi.org\/10.3233\/978-1-60750-606-5-751.","DOI":"10.3233\/978-1-60750-606-5-751"},{"issue":"1","key":"9376_CR78","first-page":"267","volume":"36","author":"F Hutter","year":"2009","unstructured":"Hutter, F., Hoos, H. H., Leyton-Brown, K., & St\u00fctzle, T. (2009). Paramils: An automatic algorithm configuration framework. J. Artif. Int. Res., 36(1), 267\u2013306.","journal-title":"J. Artif. Int. Res."},{"key":"9376_CR79","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1007\/978-3-642-23786-7_35","volume-title":"Principles and Practice of Constraint Programming - CP 2011","author":"S Kadioglu","year":"2011","unstructured":"Kadioglu, S., Malitsky, Y., Sabharwal, A., Samulowitz, H., & Sellmann, M. (2011). Algorithm selection and scheduling. In J. Lee (Ed.), Principles and Practice of Constraint Programming - CP 2011 (pp. 454\u2013469). Berlin, Heidelberg: Springer."},{"issue":"2","key":"9376_CR80","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1016\/j.ejor.2020.07.063","volume":"290","author":"Y Bengio","year":"2021","unstructured":"Bengio, Y., Lodi, A., & Prouvost, A. (2021). Machine learning for combinatorial optimization: A methodological tour d\u2019horizon. European Journal of Operational Research., 290(2), 405\u2013421. https:\/\/doi.org\/10.1016\/j.ejor.2020.07.063","journal-title":"European Journal of Operational Research."},{"key":"9376_CR81","unstructured":"Kadioglu, S., Malitsky, Y., Sellmann, M. (2012). Non-model-based search guidance for set partitioning problems. In: Hoffmann, J., Selman, B. (eds.) Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, July 22-26, 2012, Toronto, Ontario, Canada. AAAI Press, USA. http:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI12\/paper\/view\/5082"},{"issue":"3","key":"9376_CR82","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1016\/j.ejor.2015.08.018","volume":"248","author":"GMD Liberto","year":"2016","unstructured":"Liberto, G. M. D., Kadioglu, S., Leo, K., & Malitsky, Y. (2016). DASH: dynamic approach for switching heuristics. Eur. J. Oper. Res., 248(3), 943\u2013953. https:\/\/doi.org\/10.1016\/j.ejor.2015.08.018","journal-title":"Eur. J. Oper. Res."},{"issue":"2","key":"9376_CR83","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1007\/s11750-017-0451-6","volume":"25","author":"A Lodi","year":"2017","unstructured":"Lodi, A., & Zarpellon, G. (2017). On learning and branching: a survey. Top., 25(2), 207\u2013236.","journal-title":"Top."},{"issue":"3","key":"9376_CR84","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1016\/j.ejor.2021.11.050","volume":"301","author":"Y Yang","year":"2022","unstructured":"Yang, Y., Boland, N., Dilkina, B., & Savelsbergh, M. (2022). Learning generalized strong branching for set covering, set packing, and 0\u20131 knapsack problems. European Journal of Operational Research., 301(3), 828\u2013840. https:\/\/doi.org\/10.1016\/j.ejor.2021.11.050","journal-title":"European Journal of Operational Research."},{"key":"9376_CR85","unstructured":"Tang, Y., Agrawal, S., Faenza, Y. (2020). Reinforcement learning for integer programming: Learning to cut. In: III, H.D., Singh, A. (eds.) Proceedings of the 37th international conference on machine learning. proceedings of machine learning research, vol. 119, pp. 9367\u20139376. PMLR, USA. https:\/\/proceedings.mlr.press\/v119\/tang20a.html"},{"key":"9376_CR86","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1007\/978-3-642-29828-8_23","volume-title":"Integration of AI and OR Techniques in Contraint Programming for Combinatorial Optimzation Problems","author":"A Sabharwal","year":"2012","unstructured":"Sabharwal, A., Samulowitz, H., & Reddy, C. (2012). Guiding combinatorial optimization with uct. In N. Beldiceanu, N. Jussien, & \u00c9. Pinson (Eds.), Integration of AI and OR Techniques in Contraint Programming for Combinatorial Optimzation Problems (pp. 356\u2013361). Berlin, Heidelberg: Springer."},{"key":"9376_CR87","unstructured":"He, H., Daume III, H., Eisner, J.M. (2014). Learning to search in branch and bound algorithms. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K.Q. (eds.) Advances in neural information processing systems, vol. 27. Curran Associates, Inc., USA. https:\/\/proceedings.neurips.cc\/paper\/2014\/file\/757f843a169cc678064d9530d12a1881-Paper.pdf"},{"key":"9376_CR88","unstructured":"Balcan, M., Prasad, S., Sandholm, T., Vitercik, E. (2021). Sample complexity of tree search configuration: Cutting planes and beyond. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, Virtual, USA, pp. 4015\u20134027. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/210b7ec74fc9cec6fb8388dbbdaf23f7-Abstract.html"},{"key":"9376_CR89","doi-asserted-by":"publisher","unstructured":"Balcan, M.-F., Prasad, S., Sandholm, T., Vitercik, E. (2022). Improved Sample Complexity Bounds for Branch-And-Cut. In: Solnon, C. (ed.) 28th International conference on principles and practice of constraint programming (CP 2022). Leibniz International Proceedings in Informatics (LIPIcs), vol. 235, pp. 3\u20131319. Schloss Dagstuhl \u2013 Leibniz-Zentrum f\u00fcr Informatik, Dagstuhl, Germany. https:\/\/doi.org\/10.4230\/LIPIcs.CP.2022.3. https:\/\/drops.dagstuhl.de\/entities\/document\/10.4230\/LIPIcs.CP.2022.3","DOI":"10.4230\/LIPIcs.CP.2022.3"},{"key":"9376_CR90","doi-asserted-by":"publisher","unstructured":"Kumar, M., Kolb, S., Guns, T. (2022). Learning constraint programming models from data using generate-and-aggregate. In: Solnon, C. (ed.) 28th International conference on principles and practice of constraint programming, CP 2022, July 31 to August 8, 2022, Haifa, Israel. LIPIcs, vol. 235, pp. 29\u201312916. Schloss Dagstuhl - Leibniz-Zentrum f\u00fcr Informatik, USA. https:\/\/doi.org\/10.4230\/LIPIcs.CP.2022.29.","DOI":"10.4230\/LIPIcs.CP.2022.29"},{"key":"9376_CR91","unstructured":"Raedt, L.D., Passerini, A., Teso, S. (2018). Learning constraints from examples. In: AAAI Conference on Artificial Intelligence"},{"issue":"9\u201310","key":"9376_CR92","doi-asserted-by":"publisher","first-page":"1441","DOI":"10.1007\/s10994-017-5640-x","volume":"106","author":"S Kolb","year":"2017","unstructured":"Kolb, S., Paramonov, S., Guns, T., & Raedt, L. D. (2017). Learning constraints in spreadsheets and tabular data. Mach. Learn., 106(9\u201310), 1441\u20131468. https:\/\/doi.org\/10.1007\/s10994-017-5640-x","journal-title":"Mach. Learn."},{"key":"9376_CR93","doi-asserted-by":"publisher","unstructured":"Paramonov, S., Kolb, S., Guns, T., Raedt, L.D. (2017). Tacle: Learning constraints in tabular data. In: Lim, E., Winslett, M., Sanderson, M., Fu, A.W., Sun, J., Culpepper, J.S., Lo, E., Ho, J.C., Donato, D., Agrawal, R., Zheng, Y., Castillo, C., Sun, A., Tseng, V.S., Li, C. (eds.) Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, CIKM 2017, Singapore, November 06 - 10, 2017, pp. 2511\u20132514. ACM, USA. https:\/\/doi.org\/10.1145\/3132847.3133193.","DOI":"10.1145\/3132847.3133193"},{"key":"9376_CR94","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/978-3-642-33558-7_13","volume-title":"Principles and Practice of Constraint Programming","author":"N Beldiceanu","year":"2012","unstructured":"Beldiceanu, N., & Simonis, H. (2012). A model seeker: Extracting global constraint models from positive examples. In M. Milano (Ed.), Principles and Practice of Constraint Programming (pp. 141\u2013157). Berlin, Heidelberg: Springer."},{"key":"9376_CR95","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/978-3-540-30201-8_12","volume-title":"Principles and Practice of Constraint Programming - CP 2004","author":"C Bessiere","year":"2004","unstructured":"Bessiere, C., Coletta, R., Freuder, E. C., & O\u2019Sullivan, B. (2004). Leveraging the learning power of examples in automated constraint acquisition. In M. Wallace (Ed.), Principles and Practice of Constraint Programming - CP 2004 (pp. 123\u2013137). Berlin, Heidelberg: Springer."},{"issue":"3","key":"9376_CR96","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1016\/j.ejor.2017.02.034","volume":"261","author":"TP Pawlak","year":"2017","unstructured":"Pawlak, T. P., & Krawiec, K. (2017). Automatic synthesis of constraints from examples using mixed integer linear programming. European Journal of Operational Research., 261(3), 1141\u20131157. https:\/\/doi.org\/10.1016\/j.ejor.2017.02.034","journal-title":"European Journal of Operational Research."},{"issue":"7","key":"9376_CR97","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1016\/j.future.2004.04.005","volume":"21","author":"HAD Nascimento","year":"2005","unstructured":"Nascimento, H. A. D., & Eades, P. (2005). User hints: a framework for interactive optimization. Future Gener. Comput. Syst., 21(7), 1171\u20131191. https:\/\/doi.org\/10.1016\/j.future.2004.04.005","journal-title":"Future Gener. Comput. Syst."},{"issue":"1","key":"9376_CR98","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1109\/TVCG.2016.2598545","volume":"23","author":"S Goodwin","year":"2017","unstructured":"Goodwin, S., Mears, C., Dwyer, T., Banda, M. G., Tack, G., & Wallace, M. (2017). What do constraint programming users want to see? exploring the role of visualisation in profiling of models and search. IEEE Trans. Vis. Comput. Graph., 23(1), 281\u2013290. https:\/\/doi.org\/10.1109\/TVCG.2016.2598545","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"9376_CR99","doi-asserted-by":"publisher","unstructured":"Simonis, H., Davern, P., Feldman, J., Mehta, D., Quesada, L., Carlsson, M. (2010). A generic visualization platform for CP. In: Cohen, D. (ed.) Principles and practice of constraint programming - CP 2010 - 16th International Conference, CP 2010, St. Andrews, Scotland, UK, September 6-10, 2010. Proceedings. Lecture Notes in Computer Science, vol. 6308, pp. 460\u2013474. Springer, USA. https:\/\/doi.org\/10.1007\/978-3-642-15396-9_37.","DOI":"10.1007\/978-3-642-15396-9_37"},{"key":"9376_CR100","doi-asserted-by":"publisher","unstructured":"O\u2019Callaghan, B., O\u2019Sullivan, B., Freuder, E.C. (2005). Generating corrective explanations for interactive constraint satisfaction. In: Beek, P. (ed.) Principles and Practice of Constraint Programming - CP 2005, 11th International Conference, CP 2005, Sitges, Spain, October 1-5, 2005, Proceedings. Lecture Notes in Computer Science, vol. 3709, pp. 445\u2013459. Springer, USA. https:\/\/doi.org\/10.1007\/11564751_34.","DOI":"10.1007\/11564751_34"},{"key":"9376_CR101","unstructured":"Michailidis, K., Tsouros, D., Guns, T. (2024). Constraint modelling with llms using in-context learning. In: 30th International Conference on Principles and Practice of Constraint Programming"},{"key":"9376_CR102","unstructured":"Wasserkrug, S., Boussioux, L., Hertog, D.d., Mirzazadeh, F., Birbil, I., Kurtz, J., Maragno, D. (2024). From large language models and optimization to decision optimization copilot: A research manifesto. arXiv:2402.16269."},{"key":"9376_CR103","unstructured":"AhmadiTeshnizi, A., Gao, W., Udell, M. (2023). Optimus: Optimization modeling using mip solvers and large language models. arXiv:2310.06116."},{"key":"9376_CR104","doi-asserted-by":"crossref","unstructured":"Ahmed, T., Choudhury, S. (2024). Lm4opt: Unveiling the potential of large language models in formulating mathematical optimization problems. arXiv:2403.01342.","DOI":"10.1080\/03155986.2024.2388452"},{"key":"9376_CR105","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023). Llama: Open and efficient foundation language models. arXiv:2302.13971."},{"key":"9376_CR106","unstructured":"Li, B., Mellou, K., Zhang, B., Pathuri, J., Menache, I. (2023). Large language models for supply chain optimization. arXiv:2307.03875."},{"key":"9376_CR107","unstructured":"Liu, O., Fu, D., Yogatama, D., Neiswanger, W. (2024). Dellma: A framework for decision making under uncertainty with large language models. arXiv:2402.02392."},{"key":"9376_CR108","unstructured":"Liu, F., Xialiang, T., Yuan, M., Lin, X., Luo, F., Wang, Z., Lu, Z., Zhang, Q. (2024). Evolution of heuristics: Towards efficient automatic algorithm design using large language model. In: Forty-first International Conference on Machine Learning"},{"key":"9376_CR109","unstructured":"Xiao, Z., Zhang, D., Wu, Y., Xu, L., Wang, Y.J., Han, X., Fu, X., Zhong, T., Zeng, J., Song, M., et al. (2023). Chain-of-experts: When llms meet complex operations research problems. In: The twelfth international conference on learning representations"},{"key":"9376_CR110","doi-asserted-by":"crossref","unstructured":"Chen, H., Constante-Flores, G.E., Li, C. (2023). Diagnosing infeasible optimization problems using large language models. arXiv:2308.12923.","DOI":"10.1080\/03155986.2024.2385189"},{"key":"9376_CR111","unstructured":"Zhong, V., Xiong, C., Socher, R. (2017). Seq2sql: Generating structured queries from natural language using reinforcement learning. arXiv:1709.00103."}],"container-title":["Constraints"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10601-024-09376-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10601-024-09376-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10601-024-09376-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T12:21:26Z","timestamp":1737375686000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10601-024-09376-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,26]]},"references-count":111,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["9376"],"URL":"https:\/\/doi.org\/10.1007\/s10601-024-09376-5","relation":{},"ISSN":["1383-7133","1572-9354"],"issn-type":[{"value":"1383-7133","type":"print"},{"value":"1572-9354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,26]]},"assertion":[{"value":"3 November 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 November 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no competing interests or conflicts to declare relevant to this article\u2019s content.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"All authors declare that we express our consent for the publication of this article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}