{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T16:01:31Z","timestamp":1765382491260,"version":"3.37.3"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T00:00:00Z","timestamp":1690761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T00:00:00Z","timestamp":1690761600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003600","name":"Korean National Police Agency","doi-asserted-by":"publisher","award":["PR10-02-000-22"],"award-info":[{"award-number":["PR10-02-000-22"]}],"id":[{"id":"10.13039\/501100003600","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Law"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s10506-023-09370-x","type":"journal-article","created":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T12:03:23Z","timestamp":1690805003000},"page":"1011-1044","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Lessons learned building a legal inference dataset"],"prefix":"10.1007","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2265-3013","authenticated-orcid":false,"given":"Sungmi","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0148-4732","authenticated-orcid":false,"given":"Joshua I.","family":"James","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,31]]},"reference":[{"key":"9370_CR1","unstructured":"Auto-GPT: An Autonomous GPT-4 Experiment. (2023). [Python]. Significant Gravitas. https:\/\/github.com\/Significant-Gravitas\/Auto-GPT"},{"key":"9370_CR2","doi-asserted-by":"publisher","DOI":"10.1145\/3544558","author":"M Bayer","year":"2022","unstructured":"Bayer M, Kaufhold M-A, Reuter C (2022) A survey on data augmentation for text classification. ACM Comput Surv. https:\/\/doi.org\/10.1145\/3544558","journal-title":"ACM Comput Surv"},{"key":"9370_CR3","unstructured":"Belinkov Y, Bisk Y (2018) Synthetic and natural noise both break neural machine translation (arXiv:1711.02173)"},{"key":"9370_CR4","unstructured":"Beltagy I, Peters ME, Cohan A (2020) Longformer: the long-document transformer (arXiv:2004.05150)"},{"key":"9370_CR5","unstructured":"Bhagavatula C, Bras RL, Malaviya C, Sakaguchi K, Holtzman A, Rashkin H, Downey D, Yih SW, Choi Y (2020) Abductive commonsense reasoning (arXiv:1908.05739)"},{"key":"9370_CR6","doi-asserted-by":"crossref","unstructured":"Bowman SR, Angeli G, Potts C, Manning CD (2015) A large annotated corpus for learning natural language inference (arXiv:1508.05326)","DOI":"10.18653\/v1\/D15-1075"},{"key":"9370_CR7","unstructured":"Bras RL, Swayamdipta S, Bhagavatula C, Zellers R, Peters ME, Sabharwal A, Choi Y (2020) Adversarial filters of dataset biases (arXiv:2002.04108)"},{"key":"9370_CR8","unstructured":"Clark K, Luong M-T, Le QV, Manning CD (2020) ELECTRA: pre-training text encoders as discriminators rather than generators (arXiv:2003.10555)"},{"key":"9370_CR9","doi-asserted-by":"publisher","unstructured":"Conneau A, Rinott R, Lample G, Williams A, Bowman S, Schwenk H, Stoyanov V (2018) XNLI: evaluating cross-lingual sentence representations. In: Proceedings of the 2018 conference on empirical methods in natural language processing, pp 2475\u20132485. https:\/\/doi.org\/10.18653\/v1\/D18-1269","DOI":"10.18653\/v1\/D18-1269"},{"key":"9370_CR10","unstructured":"Coulombe C (2018) Text data augmentation made simple by leveraging NLP cloud APIs (arXiv:1812.04718). arXiv. http:\/\/arxiv.org\/abs\/1812.04718"},{"key":"9370_CR11","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding (arXiv:1810.04805). arXiv. http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"9370_CR12","unstructured":"Goodfellow IJ, Shlens J, Szegedy C (2015) Explaining and harnessing adversarial examples. arXiv. http:\/\/arxiv.org\/abs\/1412.6572"},{"key":"9370_CR13","doi-asserted-by":"publisher","unstructured":"Gururangan S, Swayamdipta S, Levy O, Schwartz R, Bowman S, Smith NA (2018) Annotation artifacts in natural language inference data. In: Proceedings of the 2018 conference of the north American chapter of the association for computational linguistics: human language technologies, Volume 2 (Short Papers), pp 107\u2013112. https:\/\/doi.org\/10.18653\/v1\/N18-2017","DOI":"10.18653\/v1\/N18-2017"},{"key":"9370_CR14","doi-asserted-by":"publisher","unstructured":"Ham J, Choe YJ, Park K, Choi I, Soh H (2020) KorNLI and KorSTS: new benchmark datasets for Korean natural language understanding. Findings of the Association for Computational Linguistics: EMNLP 2020, pp 422\u2013430. https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.39","DOI":"10.18653\/v1\/2020.findings-emnlp.39"},{"key":"9370_CR15","unstructured":"Heo J (2021) 110 cases per person... Police investigation examiner who was hit by a \u201cday bomb.\u201d Seoul Economic Daily. https:\/\/www.sedaily.com\/NewsView\/22M7D9OSWB"},{"key":"9370_CR16","doi-asserted-by":"publisher","unstructured":"Jia Y, Liu Y, Yu X, Voida S (2017) Designing leaderboards for gamification: perceived differences based on user ranking, application domain, and personality traits. In: Proceedings of the 2017 CHI conference on human factors in computing systems, pp 1949\u20131960. https:\/\/doi.org\/10.1145\/3025453.3025826","DOI":"10.1145\/3025453.3025826"},{"key":"9370_CR17","unstructured":"Kaushik D, Hovy E, Lipton ZC (2020) Learning the difference that makes a difference with counterfactually-augmented data (arXiv:1909.12434)"},{"key":"9370_CR18","unstructured":"Kim A (2022) How Democratic Party of Korea-led prosecution reforms fail victims. Korean Herald. https:\/\/www.koreaherald.com\/view.php?ud=20220501000254&ACE_SEARCH=1"},{"issue":"1","key":"9370_CR19","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s12626-022-00103-1","volume":"16","author":"M-Y Kim","year":"2022","unstructured":"Kim M-Y, Rabelo J, Okeke K, Goebel R (2022) Legal information retrieval and entailment based on BM25, transformer and semantic thesaurus methods. Rev Socionetwork Strateg 16(1):157\u2013174. https:\/\/doi.org\/10.1007\/s12626-022-00103-1","journal-title":"Rev Socionetwork Strateg"},{"key":"9370_CR20","unstructured":"Kim T (2020) KorEDA [Python]. https:\/\/github.com\/catSirup\/KorEDA (Original work published 2020)"},{"key":"9370_CR21","unstructured":"KLAID LJP Base (2022) Law&Company. lawcompany\/KLAID_LJP_base"},{"key":"9370_CR22","unstructured":"LBox Open (2022) [Python]. LBOX. https:\/\/github.com\/lbox-kr\/lbox-open"},{"issue":"140","key":"9370_CR23","first-page":"55","volume":"22","author":"R Likert","year":"1932","unstructured":"Likert R (1932) A technique for the measurement of attitudes. Arch Psychol 22(140):55\u201355","journal-title":"Arch Psychol"},{"key":"9370_CR24","doi-asserted-by":"crossref","unstructured":"Liu, H., Cui, L., Liu, J., & Zhang, Y. (2020). Natural Language Inference in Context\u2014Investigating Contextual Reasoning over Long Texts (arXiv:2011.04864)","DOI":"10.1609\/aaai.v35i15.17580"},{"key":"9370_CR25","unstructured":"Nakajima, Y. (2023). BabyAGI [Python]. https:\/\/github.com\/yoheinakajima\/babyagi"},{"key":"9370_CR26","doi-asserted-by":"publisher","unstructured":"Nie Y, Williams A, Dinan E, Bansal M, Weston J, Kiela D (2020) Adversarial NLI: a new benchmark for natural language understanding. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 4885\u20134901. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.441","DOI":"10.18653\/v1\/2020.acl-main.441"},{"key":"9370_CR27","unstructured":"Oshin M (2023) GPT-4 & LangChain\u2014Create a ChatGPT Chatbot for Your PDF Files [TypeScript]. https:\/\/github.com\/mayooear\/gpt4-pdf-chatbot-langchain"},{"key":"9370_CR28","unstructured":"Park D (2021) KoEDA [Python]. https:\/\/github.com\/toriving\/KoEDA (Original work published 2020)"},{"key":"9370_CR29","unstructured":"Park J (2022) KoELECTRA [Python]. https:\/\/github.com\/monologg\/KoELECTRA"},{"key":"9370_CR30","unstructured":"Park S, Moon J, Kim S, Cho WI, Han J, Park J, Song C, Kim J, Song Y, Oh T, Lee J, Oh J, Lyu S, Jeong Y, Lee I, Seo S, Lee D, Kim H, Lee M et al (2021) KLUE: Korean language understanding evaluation (arXiv:2105.09680)"},{"key":"9370_CR31","unstructured":"Pirolli P, Card S (2005) The sensemaking process and leverage points for analyst technology as identified through cognitive task analysis. In: The sensemaking process and leverage points for analyst technology as identified through cognitive task analysis"},{"key":"9370_CR32","doi-asserted-by":"publisher","unstructured":"Poliak A, Naradowsky J, Haldar A, Rudinger R, Van Durme B (2018) Hypothesis only baselines in natural language inference. In: Proceedings of the seventh joint conference on lexical and computational semantics, pp 180\u2013191. https:\/\/doi.org\/10.18653\/v1\/S18-2023","DOI":"10.18653\/v1\/S18-2023"},{"issue":"1","key":"9370_CR33","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s12626-022-00105-z","volume":"16","author":"J Rabelo","year":"2022","unstructured":"Rabelo J, Goebel R, Kim M-Y, Kano Y, Yoshioka M, Satoh K (2022) Overview and discussion of the competition on legal information extraction\/entailment (COLIEE) 2021. Rev Socionetwork Strateg 16(1):111\u2013133. https:\/\/doi.org\/10.1007\/s12626-022-00105-z","journal-title":"Rev Socionetwork Strateg"},{"key":"9370_CR34","unstructured":"Um J (2022) S. Korean Democrats\u2019 long road to reforming prosecution service: Victory or blunder? Hankyoreh. https:\/\/english.hani.co.kr\/arti\/english_edition\/e_national\/1041606.html"},{"key":"9370_CR35","doi-asserted-by":"publisher","unstructured":"Wei J, Zou K (2019) EDA: easy data augmentation techniques for boosting performance on text classification tasks. 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 6381\u20136387. https:\/\/doi.org\/10.18653\/v1\/D19-1670","DOI":"10.18653\/v1\/D19-1670"},{"key":"9370_CR36","doi-asserted-by":"publisher","unstructured":"Williams A, Nangia N, Bowman S (2018) A broad-coverage challenge corpus for sentence understanding through inference. In: Proceedings of the 2018 conference of the north american chapter of the association for computational linguistics: human language technologies, vol 1 (Long Papers), pp 1112\u20131122. https:\/\/doi.org\/10.18653\/v1\/N18-1101","DOI":"10.18653\/v1\/N18-1101"},{"key":"9370_CR37","unstructured":"Woo J (2020) S. Korea takes long overdue steps to rein in prosecution service, but task far from over. Yonhap News. https:\/\/en.yna.co.kr\/view\/AEN20201217008100315"},{"key":"9370_CR38","unstructured":"Xie Q, Dai Z, Hovy E, Luong M-T, Le QV (2020) Unsupervised data augmentation for consistency training (arXiv:1904.12848)"},{"key":"9370_CR39","unstructured":"Yu AW, Dohan D, Luong M-T, Zhao R, Chen K, Norouzi M, Le QV (2018) QANet: combining local convolution with global self-attention for reading comprehension (arXiv:1804.09541)"},{"issue":"3","key":"9370_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3374217","volume":"11","author":"WE Zhang","year":"2020","unstructured":"Zhang WE, Sheng QZ, Alhazmi A, Li C (2020) Adversarial attacks on deep-learning models in natural language processing: a survey. ACM Tran Intell Syst Technol 11(3):1\u201341. https:\/\/doi.org\/10.1145\/3374217","journal-title":"ACM Tran Intell Syst Technol"}],"container-title":["Artificial Intelligence and Law"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10506-023-09370-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10506-023-09370-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10506-023-09370-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T12:09:43Z","timestamp":1729685383000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10506-023-09370-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,31]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["9370"],"URL":"https:\/\/doi.org\/10.1007\/s10506-023-09370-x","relation":{},"ISSN":["0924-8463","1572-8382"],"issn-type":[{"type":"print","value":"0924-8463"},{"type":"electronic","value":"1572-8382"}],"subject":[],"published":{"date-parts":[[2023,7,31]]},"assertion":[{"value":"1 July 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2023","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 declare that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}