{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T13:26:57Z","timestamp":1773840417945,"version":"3.50.1"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030884796","type":"print"},{"value":"9783030884802","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-88480-2_61","type":"book-chapter","created":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T11:04:52Z","timestamp":1633950292000},"page":"758-769","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning"],"prefix":"10.1007","author":[{"given":"Cunxiang","family":"Wang","sequence":"first","affiliation":[]},{"given":"Boyuan","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Yuchen","family":"Niu","sequence":"additional","affiliation":[]},{"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,10,6]]},"reference":[{"key":"61_CR1","unstructured":"Chung, J., G\u00fcl\u00e7ehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv:abs\/1412.3555 (2014)"},{"key":"61_CR2","doi-asserted-by":"publisher","unstructured":"Clark, P., Tafjord, O., Richardson, K.: Transformers as soft reasoners over language. In: Bessiere, C. (ed.) Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020, pp. 3882\u20133890. International Joint Conferences on Artificial Intelligence Organization (2020). https:\/\/doi.org\/10.24963\/ijcai.2020\/537, main track","DOI":"10.24963\/ijcai.2020\/537"},{"key":"61_CR3","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Long and Short Papers), vol. 1, pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, June 2019. https:\/\/doi.org\/10.18653\/v1\/N19-1423, https:\/\/www.aclweb.org\/anthology\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"61_CR4","doi-asserted-by":"publisher","unstructured":"Dua, D., Wang, Y., Dasigi, P., Stanovsky, G., Singh, S., Gardner, M.: DROP: a reading comprehension benchmark requiring discrete reasoning over paragraphs. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Long and Short Papers), vol. 1, pp. 2368\u20132378. Association for Computational Linguistics, Minneapolis, June 2019. https:\/\/doi.org\/10.18653\/v1\/N19-1246, https:\/\/www.aclweb.org\/anthology\/N19-1246","DOI":"10.18653\/v1\/N19-1246"},{"key":"61_CR5","doi-asserted-by":"publisher","unstructured":"Geva, M., Gupta, A., Berant, J.: Injecting numerical reasoning skills into language models. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 946\u2013958. Association for Computational Linguistics, July 2020. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.89, https:\/\/www.aclweb.org\/anthology\/2020.acl-main.89","DOI":"10.18653\/v1\/2020.acl-main.89"},{"issue":"8","key":"61_CR6","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"61_CR7","unstructured":"Lake, B., Baroni, M.: Generalization without systematicity: on the compositional skills of sequence-to-sequence recurrent networks. In: ICML (2018)"},{"key":"61_CR8","doi-asserted-by":"publisher","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7871\u20137880. Association for Computational Linguistics, July 2020. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.703, https:\/\/www.aclweb.org\/anthology\/2020.acl-main.703","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"61_CR9","doi-asserted-by":"crossref","unstructured":"Lewis, P., Stenetorp, P., Riedel, S.: Question and answer test-train overlap in open-domain question answering datasets (2020)","DOI":"10.18653\/v1\/2021.eacl-main.86"},{"key":"61_CR10","doi-asserted-by":"publisher","unstructured":"Linzen, T.: How can we accelerate progress towards human-like linguistic generalization? In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 5210\u20135217. Association for Computational Linguistics, July 2020. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.465, https:\/\/www.aclweb.org\/anthology\/2020.acl-main.465","DOI":"10.18653\/v1\/2020.acl-main.465"},{"key":"61_CR11","unstructured":"Madsen, A., Johansen, A.R.: Measuring arithmetic extrapolation performance. arXiv:abs\/1910.01888 (2019)"},{"key":"61_CR12","doi-asserted-by":"publisher","unstructured":"McCoy, R.T., Min, J., Linzen, T.: BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance. In: Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pp. 217\u2013227. Association for Computational Linguistics, November 2020. https:\/\/doi.org\/10.18653\/v1\/2020.blackboxnlp-1.21, https:\/\/www.aclweb.org\/anthology\/2020.blackboxnlp-1.21","DOI":"10.18653\/v1\/2020.blackboxnlp-1.21"},{"key":"61_CR13","unstructured":"Nogueira, R., Jiang, Z., Li, J.: Investigating the limitations of the transformers with simple arithmetic tasks. arXiv:abs\/2102.13019 (2021)"},{"key":"61_CR14","doi-asserted-by":"publisher","unstructured":"Pennington, J., Socher, R., Manning, C.: GloVe: Global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543. Association for Computational Linguistics, Doha, October 2014. https:\/\/doi.org\/10.3115\/v1\/D14-1162, https:\/\/www.aclweb.org\/anthology\/D14-1162","DOI":"10.3115\/v1\/D14-1162"},{"issue":"8","key":"61_CR15","first-page":"9","volume":"1","author":"A Radford","year":"2019","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)","journal-title":"OpenAI Blog"},{"key":"61_CR16","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":"61_CR17","doi-asserted-by":"publisher","unstructured":"Roberts, A., Raffel, C., Shazeer, N.: How much knowledge can you pack into the parameters of a language model? In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 5418\u20135426. Association for Computational Linguistics, November 2020. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.437, https:\/\/www.aclweb.org\/anthology\/2020.emnlp-main.437","DOI":"10.18653\/v1\/2020.emnlp-main.437"},{"key":"61_CR18","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. arXiv preprint arXiv:1409.3215 (2014)"},{"key":"61_CR19","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS 2017, pp. 6000\u20136010. Curran Associates Inc., Red Hook (2017)"},{"key":"61_CR20","doi-asserted-by":"publisher","unstructured":"Wallace, E., Wang, Y., Li, S., Singh, S., Gardner, M.: Do NLP models know numbers? probing numeracy in embeddings. 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. 5307\u20135315. Association for Computational Linguistics, Hong Kong, November 2019. https:\/\/doi.org\/10.18653\/v1\/D19-1534, https:\/\/www.aclweb.org\/anthology\/D19-1534","DOI":"10.18653\/v1\/D19-1534"},{"key":"61_CR21","doi-asserted-by":"crossref","unstructured":"Wang, C., Liu, P., Zhang, Y.: Can generative pre-trained language models serve as knowledge bases for closed-book qa? (2021)","DOI":"10.18653\/v1\/2021.acl-long.251"},{"key":"61_CR22","doi-asserted-by":"publisher","unstructured":"Wang, Y., Liu, X., Shi, S.: Deep neural solver for math word problems. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 845\u2013854. Association for Computational Linguistics, Copenhagen, September 2017. https:\/\/doi.org\/10.18653\/v1\/D17-1088, https:\/\/www.aclweb.org\/anthology\/D17-1088","DOI":"10.18653\/v1\/D17-1088"},{"key":"61_CR23","unstructured":"Wangperawong, A.: Attending to mathematical language with transformers. arXiv:abs\/1812.02825 (2018)"},{"key":"61_CR24","unstructured":"Zhang, N., et al.: Can fine-tuning pre-trained models lead to perfect nlp? a study of the generalizability of relation extraction. arXiv:abs\/2009.06206 (2020)"},{"key":"61_CR25","unstructured":"Zhao, W., Shang, M., Liu, Y., Wang, L., Liu, J.: Ape210k: a large-scale and template-rich dataset of math word problems. CoRR abs\/2009.11506 (2020). https:\/\/arxiv.org\/abs\/2009.11506"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-88480-2_61","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T15:51:00Z","timestamp":1709826660000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-88480-2_61"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030884796","9783030884802"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-88480-2_61","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"6 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Qingdao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"446","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"66","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"15% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23 poster papers and 27 workshop papers are also included.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}