{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T23:11:15Z","timestamp":1765667475167,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031703775"},{"type":"electronic","value":"9783031703782"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70378-2_10","type":"book-chapter","created":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T09:02:05Z","timestamp":1725181325000},"page":"157-173","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["KAT5: Knowledge-Aware Transfer Learning with\u00a0a\u00a0Text-to-Text Transfer Transformer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5540-7834","authenticated-orcid":false,"given":"Mohammad Golam","family":"Sohrab","sequence":"first","affiliation":[]},{"given":"Makoto","family":"Miwa","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"10_CR1","unstructured":"Ba, J., Kiros, J.R., Hinton, G.E.: Layer normalization. ArXiv abs\/1607.06450 (2016). https:\/\/api.semanticscholar.org\/CorpusID:8236317"},{"key":"10_CR2","unstructured":"Br\u00fcmmer, M., Dojchinovski, M., Hellmann, S.: DBpedia abstracts: a large-scale, open, multilingual NLP training corpus. In: Calzolari, N., et al. (eds.) Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), Portoro\u017e, Slovenia, pp. 3339\u20133343, May 2016. https:\/\/aclanthology.org\/L16-1532"},{"key":"10_CR3","unstructured":"Chang, A.X., Manning, C.: SUTime: a library for recognizing and normalizing time expressions. In: Calzolari, N., et al. (eds.) Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC 2012), Istanbul, Turkey, May 2012, pp. 3735\u20133740 (2012). http:\/\/www.lrec-conf.org\/proceedings\/lrec2012\/pdf\/284_Paper.pdf"},{"key":"10_CR4","unstructured":"Conneau, A., Lample, G.: Cross-lingual language model pretraining. In: Advances in Neural Information Processing Systems, vol.\u00a032, pp. 7059\u20137069 (2019). https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/c04c19c2c2474dbf5f7ac4372c5b9af1-Paper.pdf"},{"key":"10_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: 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), Minneapolis, Minnesota, June 2019, pp. 4171\u20134186. ACL (2019). https:\/\/aclanthology.org\/N19-1423"},{"key":"10_CR6","unstructured":"Eberts, M., Ulges, A.: Span-based joint entity and relation extraction with transformer pre-training. CoRR (2019). http:\/\/arxiv.org\/abs\/1909.07755"},{"key":"10_CR7","unstructured":"Elsahar, H., et al.: T-REx: a large scale alignment of natural language with knowledge base triples. In: Calzolari, N., et al. (eds.) Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). European Language Resources Association (ELRA), Miyazaki, Japan, May 2018. https:\/\/aclanthology.org\/L18-1544"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Ghazvininejad, M., Levy, O., Liu, Y., Zettlemoyer, L.: Mask-predict: parallel decoding of conditional masked language models. In: Inui, K., Jiang, J., Ng, V., Wan, X. (eds.) 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. 6112\u20136121, Hong Kong, China, November 2019. Association for Computational Linguistics (2019). https:\/\/aclanthology.org\/D19-1633","DOI":"10.18653\/v1\/D19-1633"},{"key":"10_CR9","unstructured":"Gu, J., Bradbury, J., Xiong, C., Li, V.O., Socher, R.: Non-autoregressive neural machine translation. In: International Conference on Learning Representations (2018). https:\/\/doi.org\/10.48550\/arXiv.1711.02281"},{"key":"10_CR10","unstructured":"Gu, J., Wang, C., Zhao, J.: Levenshtein transformer. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a032. Curran Associates, Inc. (2019). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/675f9820626f5bc0afb47b57890b466e-Paper.pdf"},{"key":"10_CR11","unstructured":"Gupta, P., Sch\u00fctze, H., Andrassy, B.: Table filling multi-task recurrent neural network for joint entity and relation extraction. In: Matsumoto, Y., Prasad, R. (eds.) Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics, pp. 2537\u20132547. https:\/\/aclanthology.org\/C16-1239"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Gurulingappa, H., Rajput, A.M., Roberts, A., Fluck, J., Hofmann-Apitius, M., Toldo, L.: Development of a benchmark corpus to support the automatic extraction of drug-related adverse effects from medical case reports. J. Biomed. Inform. 45(5), 885\u2013892 (2012). https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1532046412000615","DOI":"10.1016\/j.jbi.2012.04.008"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Huguet\u00a0Cabot, P.L., Navigli, R.: REBEL: relation extraction by end-to-end language generation. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.t. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 2370\u20132381. ACL. https:\/\/aclanthology.org\/2021.findings-emnlp.204","DOI":"10.18653\/v1\/2021.findings-emnlp.204"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Lee, J., Mansimov, E., Cho, K.: Deterministic non-autoregressive neural sequence modeling by iterative refinement. In: Riloff, E., Chiang, D., Hockenmaier, J., Tsujii, J. (eds.) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, October\u2013November 2018, pp. 1173\u20131182. Association for Computational Linguistics (2018). https:\/\/aclanthology.org\/D18-1149","DOI":"10.18653\/v1\/D18-1149"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: 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. ACL, July 2020. https:\/\/aclanthology.org\/2020.acl-main.703","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., Tang, T., Zhao, W.X., Nie, J.Y., Wen, J.R.: ELMER: a non-autoregressive pre-trained language model for efficient and effective text generation. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 1044\u20131058, Abu Dhabi, United Arab Emirates, December 2022. Association for Computational Linguistics (2022). https:\/\/aclanthology.org\/2022.emnlp-main.68","DOI":"10.18653\/v1\/2022.emnlp-main.68"},{"key":"10_CR17","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, Barcelona, Spain, July 2004, pp. 74\u201381. ACL (2004). https:\/\/aclanthology.org\/W04-1013"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., Lapata, M.: Text summarization with pretrained encoders. In: Inui, K., Jiang, J., Ng, V., Wan, X. (eds.) Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, November 2019, pp. 3730\u20133740. ACL (2019). https:\/\/aclanthology.org\/D19-1387","DOI":"10.18653\/v1\/D19-1387"},{"key":"10_CR19","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. CoRR abs\/1907.11692 (2019). http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Manning, C., Surdeanu, M., Bauer, J., Finkel, J., Bethard, S., McClosky, D.: The Stanford CoreNLP natural language processing toolkit. In: Bontcheva, K., Zhu, J. (eds.) Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, Baltimore, Maryland, June 2014, pp. 55\u201360. ACL (2014). https:\/\/aclanthology.org\/P14-5010","DOI":"10.3115\/v1\/P14-5010"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Mendes, P.N., Jakob, M., Garc\u00eda-Silva, A., Bizer, C.: DBpedia spotlight: shedding light on the web of documents. In: Proceedings of the 7th International Conference on Semantic Systems, I-Semantics 2011, New York, NY, USA, pp. 1\u20138. Association for Computing Machinery (2011). https:\/\/doi.org\/10.1145\/2063518.2063519","DOI":"10.1145\/2063518.2063519"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Narayan, S., Cohen, S.B., Lapata, M.: Don\u2019t give me the details, just the summary! Topic-aware convolutional neural networks for extreme summarization. In: Riloff, E., Chiang, D., Hockenmaier, J., Tsujii, J. (eds.) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 1797\u20131807. ACL, Brussels, Belgium, Oct-Nov 2018 (2018). https:\/\/aclanthology.org\/D18-1206","DOI":"10.18653\/v1\/D18-1206"},{"key":"10_CR23","unstructured":"Paolini, G., et al.: Structured prediction as translation between augmented natural languages. In: 9th International Conference on Learning Representations, ICLR 2021 (2021)"},{"key":"10_CR24","unstructured":"Paolini, G., et al.: Structured prediction as translation between augmented natural languages. CoRR abs\/2101.05779 (2021). https:\/\/arxiv.org\/abs\/2101.05779"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Isabelle, P., Charniak, E., Lin, D. (eds.) Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, Pennsylvania, USA, July 2002, pp. 311\u2013318. ACL (2002). https:\/\/aclanthology.org\/P02-1040","DOI":"10.3115\/1073083.1073135"},{"key":"10_CR26","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training. OpenAI Blog (2018). https:\/\/s3-us-west-2.amazonaws.com\/openai-assets\/research-covers\/language-unsupervised\/language_understanding_paper.pdf"},{"key":"10_CR27","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019). https:\/\/d4mucfpksywv.cloudfront.net\/better-language-models\/language_models_are_unsupervised_multitask_learners.pdf"},{"key":"10_CR28","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020). http:\/\/jmlr.org\/papers\/v21\/20-074.html"},{"key":"10_CR29","unstructured":"Roth, D., Yih, W.t.: A linear programming formulation for global inference in natural language tasks. In: Proceedings of the Eighth Conference on Computational Natural Language Learning (CoNLL 2004) at HLT-NAACL 2004, pp.\u00a01\u20138, Boston, Massachusetts, USA, May 6\u2013May 7 2004. Association for Computational Linguistics (2004). https:\/\/aclanthology.org\/W04-2401"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Rothe, S., Narayan, S., Severyn, A.: Leveraging pre-trained checkpoints for sequence generation tasks. Trans. Assoc. Comput. Linguist. 8, 264\u2013280 (2020). https:\/\/aclanthology.org\/2020.tacl-1.18","DOI":"10.1162\/tacl_a_00313"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"See, A., Liu, P.J., Manning, C.D.: Get to the point: summarization with pointer-generator networks. In: Barzilay, R., Kan, M.Y. (eds.) Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1073\u20131083, Vancouver, Canada, July 2017. Association for Computational Linguistics (2017). https:\/\/aclanthology.org\/P17-1099","DOI":"10.18653\/v1\/P17-1099"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Shafiq, M., Gu, Z.: Deep residual learning for image recognition: a survey. Appl. Sci. 12(18) (2022). https:\/\/www.mdpi.com\/2076-3417\/12\/18\/8972","DOI":"10.3390\/app12188972"},{"key":"10_CR33","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/ACCESS.2023.3346952","volume":"12","author":"MG Sohrab","year":"2024","unstructured":"Sohrab, M.G., Asada, M., Rikters, M., Miwa, M.: BERT-NAR-BERT: a non-autoregressive pre-trained sequence-to-sequence model leveraging BERT checkpoints. IEEE Access 12, 23\u201333 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2023.3346952","journal-title":"IEEE Access"},{"key":"10_CR34","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(56), 1929\u20131958 (2014). http:\/\/jmlr.org\/papers\/v15\/srivastava14a.html"},{"key":"10_CR35","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"10_CR36","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: XLNet: generalized autoregressive pretraining for language understanding. In: Advances in Neural Information Processing Systems, vol.\u00a032, pp. 5753\u20135763 (2019). https:\/\/dl.acm.org\/doi\/pdf\/10.5555\/3454287.3454804"},{"key":"10_CR37","unstructured":"Yu, B., et al.: Joint extraction of entities and relations based on a novel decomposition strategy. CoRR abs\/1909.04273 (2019). http:\/\/arxiv.org\/abs\/1909.04273"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Zeng, X., Zeng, D., He, S., Liu, K., Zhao, J.: Extracting relational facts by an end-to-end neural model with copy mechanism. In: Gurevych, I., Miyao, Y. (eds.) Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Melbourne, Australia, July 2018, pp. 506\u2013514. ACL. https:\/\/aclanthology.org\/P18-1047","DOI":"10.18653\/v1\/P18-1047"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Zhao, T., Yan, Z., Cao, Y., Li, Z.: Asking effective and diverse questions: a machine reading comprehension based framework for joint entity-relation extraction. In: Bessiere, C. (ed.) Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, pp. 3948\u20133954, IJCAI 2020 (2020). https:\/\/doi.org\/10.24963\/ijcai.2020\/546, main track","DOI":"10.24963\/ijcai.2020\/546"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70378-2_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T09:04:17Z","timestamp":1725181457000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70378-2_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031703775","9783031703782"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70378-2_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"22 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"We use only publicly available datasets and relatively low compute amounts while conducting our experiments to enable reproducibility. We do not perform any studies on other humans or animals in this research.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Statement"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}