{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T20:22:16Z","timestamp":1769545336356,"version":"3.49.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032156310","type":"print"},{"value":"9783032156327","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-15632-7_10","type":"book-chapter","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T07:22:56Z","timestamp":1769498576000},"page":"171-193","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Interpretable Automated Question Answering Model Evaluation and\u00a0Comparison"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7891-3748","authenticated-orcid":false,"given":"Ricardo Saraiva","family":"Grava","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8992-4768","authenticated-orcid":false,"given":"Anarosa Alves Franco","family":"Brand\u00e3o","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3551-6480","authenticated-orcid":false,"given":"Sarajane Marques","family":"Peres","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4077-4935","authenticated-orcid":false,"given":"Fabio Gagliardi","family":"Cozman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,28]]},"reference":[{"key":"10_CR1","unstructured":"Banerjee, S., Lavie, A.: Meteor: an automatic metric for mt evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"10_CR2","unstructured":"Callison-Burch, C., Osborne, M., Koehn, P.: Re-evaluating the role of bleu in machine translation research. In: 11th Conference of the European Chapter of the Association for Computational Linguistics, pp. 249\u2013256. Association for Computational Linguistics (2006)"},{"issue":"4","key":"10_CR3","doi-asserted-by":"publisher","first-page":"4124","DOI":"10.1007\/s10489-022-03732-9","volume":"53","author":"R Etezadi","year":"2023","unstructured":"Etezadi, R., Shamsfard, M.: The state of the art in open domain complex question answering: a survey. Appl. Intell. 53(4), 4124\u20134144 (2023)","journal-title":"Appl. Intell."},{"key":"10_CR4","unstructured":"Falconer, J.: Google: Our new search strategy is to compute answers, not links. The Next Web (2011). https:\/\/thenextweb.com\/news\/google-our-new-search-strategy-is-to-compute-answers-not-links"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Gao, J., Lanchantin, J., Soffa, M.L., Qi, Y.: Black-box generation of adversarial text sequences to evade deep learning classifiers. In: 2018 IEEE Security and Privacy Workshops (SPW), pp. 50\u201356. IEEE (2018)","DOI":"10.1109\/SPW.2018.00016"},{"key":"10_CR6","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)"},{"key":"10_CR7","unstructured":"Honnibal, M., Montani, I., Van\u00a0Landeghem, S., Boyd, A., et\u00a0al.: spacy: industrial-strength natural language processing in Python (2020)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Iyyer, M., Wieting, J., Gimpel, K., Zettlemoyer, L.: Adversarial example generation with syntactically controlled paraphrase networks. arXiv preprint arXiv:1804.06059 (2018)","DOI":"10.18653\/v1\/N18-1170"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Jia, R., Liang, P.: Adversarial examples for evaluating reading comprehension systems. arXiv preprint arXiv:1707.07328 (2017)","DOI":"10.18653\/v1\/D17-1215"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Kry\u015bci\u0144ski, W., Keskar, N.S., McCann, B., Xiong, C., Socher, R.: Neural text summarization: a critical evaluation. arXiv preprint arXiv:1908.08960 (2019)","DOI":"10.18653\/v1\/D19-1051"},{"key":"10_CR11","unstructured":"Kumar, A., et al.: Ask me anything: dynamic memory networks for natural language processing. In: International Conference on Machine Learning, pp. 1378\u20131387. PMLR (2016)"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Li, J., Ji, S., Du, T., Li, B., Wang, T.: TextBugger: generating adversarial text against real-world applications. arXiv preprint arXiv:1812.05271 (2018)","DOI":"10.14722\/ndss.2019.23138"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Li, L., Ma, R., Guo, Q., Xue, X., Qiu, X.: BERT-attack: adversarial attack against BERT using BERT. arXiv preprint arXiv:2004.09984 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.500"},{"key":"10_CR14","unstructured":"Likert, R.: A technique for the measurement of attitudes. Archives of psychology (1932)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Morris, J.X., Lifland, E., Yoo, J.Y., Grigsby, J., Jin, D., Qi, Y.: TextAttack: a framework for adversarial attacks, data augmentation, and adversarial training in NLP. arXiv preprint arXiv:2005.05909 (2020)","DOI":"10.18653\/v1\/2020.emnlp-demos.16"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Novikova, J., Du\u0161ek, O., Curry, A.C., Rieser, V.: Why we need new evaluation metrics for NLG. arXiv preprint arXiv:1707.06875 (2017)","DOI":"10.18653\/v1\/D17-1238"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Papernot, N., McDaniel, P., Swami, A., Harang, R.: Crafting adversarial input sequences for recurrent neural networks. In: MILCOM 2016-2016 IEEE Military Communications Conference, pp. 49\u201354. IEEE (2016)","DOI":"10.1109\/MILCOM.2016.7795300"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"10_CR19","unstructured":"Parnami, A., Lee, M.: Learning from few examples: a summary of approaches to few-shot learning. arXiv preprint arXiv:2203.04291 (2022)"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)","DOI":"10.18653\/v1\/D16-1264"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: Semantically equivalent adversarial rules for debugging NLP models. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (volume 1: long papers), pp. 856\u2013865 (2018)","DOI":"10.18653\/v1\/P18-1079"},{"issue":"2","key":"10_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3485766","volume":"55","author":"AB Sai","year":"2022","unstructured":"Sai, A.B., Mohankumar, A.K., Khapra, M.M.: A survey of evaluation metrics used for NLG systems. ACM Comput. Surv. (CSUR) 55(2), 1\u201339 (2022)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"10_CR23","unstructured":"Szegedy, C.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Tan, S., Joty, S., Kan, M.Y., Socher, R.: It\u2019s morphin\u2019time! combating linguistic discrimination with inflectional perturbations. arXiv preprint arXiv:2005.04364 (2020)","DOI":"10.18653\/v1\/2020.acl-main.263"},{"key":"10_CR25","unstructured":"Team, G., et\u00a0al.: Gemma: open models based on Gemini research and technology. arXiv preprint arXiv:2403.08295 (2024)"},{"key":"10_CR26","unstructured":"Touvron, H., et\u00a0al.: LLAMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"10_CR27","unstructured":"Wang, B., et al.: Adversarial glue: a multi-task benchmark for robustness evaluation of language models. arXiv preprint arXiv:2111.02840 (2021)"}],"container-title":["Communications in Computer and Information Science","Computational Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-15632-7_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T07:23:01Z","timestamp":1769498581000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-15632-7_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032156310","9783032156327"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-15632-7_10","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"28 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors\u00a0have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests."}},{"value":"IJCCI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Joint Conference on Computational Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marbella","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","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":"22 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ijcci2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ijcci.scitevents.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}