{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T00:12:18Z","timestamp":1709424738990},"reference-count":41,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2024,3,1]]},"DOI":"10.1587\/transinf.2023edp7111","type":"journal-article","created":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T22:25:08Z","timestamp":1709245508000},"page":"411-419","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Latent Alignment for Non-Autoregressive Generation under High Compression Ratio"],"prefix":"10.1587","volume":"E107.D","author":[{"given":"Wang","family":"XU","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology"}]},{"given":"Yongliang","family":"MA","sequence":"additional","affiliation":[{"name":"Beijing Langboat Technology Co., Ltd."}]},{"given":"Kehai","family":"CHEN","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology"}]},{"given":"Ming","family":"ZHOU","sequence":"additional","affiliation":[{"name":"Beijing Langboat Technology Co., Ltd."}]},{"given":"Muyun","family":"YANG","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology"}]},{"given":"Tiejun","family":"ZHAO","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] J. Gu, J. Bradbury, C. Xiong, V.O. Li, and R. Socher, \u201cNon-autoregressive neural machine translation,\u201d International Conference on Learning Representations, 2018."},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] M. Ghazvininejad, O. Levy, Y. Liu, and L. Zettlemoyer, \u201cMask-predict: Parallel decoding of conditional masked language models,\u201d Proc. Conference on Empirical Methods in Natural Language Processing and the International Joint Conference on Natural Language Processing, pp.6112-6121, 2019. 10.18653\/v1\/d19-1633","DOI":"10.18653\/v1\/D19-1633"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] J. Guo, X. Tan, L. Xu, T. Qin, E. Chen, and T.-Y. Liu, \u201cFine-tuning by curriculum learning for non-autoregressive neural machine translation,\u201d Proc. AAAI Conference on Artificial Intelligence, pp.7839-7846, 2020. 10.1609\/aaai.v34i05.6289","DOI":"10.1609\/aaai.v34i05.6289"},{"key":"4","unstructured":"[4] W. Qi, Y. Gong, J. Jiao, Y. Yan, W. Chen, D. Liu, K. Tang, H. Li, J. Chen, R. Zhang, M. Zhou, and N. Duan, \u201cBang: Bridging autoregressive and non-autoregressive generation with large scale pretraining,\u201d Proc. International Conference on Machine Learning, pp.8630-8639, 2021."},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] P. Liu, C. Huang, and L. Mou, \u201cLearning non-autoregressive models from search for unsupervised sentence summarization,\u201d Proc. Annual Meeting of the Association for Computational Linguistics, pp.7916-7929, 2022. 10.18653\/v1\/2022.acl-long.545","DOI":"10.18653\/v1\/2022.acl-long.545"},{"key":"6","unstructured":"[6] P. Liu, X. Zhang, and L. Mou, \u201cA character-level length-control algorithm for non-autoregressive sentence summarization,\u201d Advances in Neural Information Processing Systems, 2022."},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] Y. Xiao, L. Wu, J. Guo, J. Li, M. Zhang, T. Qin, and T.-Y. Liu, \u201cA survey on non-autoregressive generation for neural machine translation and beyond,\u201d vol.45, no.10, pp.11407-11427, 2023. 10.1109\/tpami.2023.3277122","DOI":"10.1109\/TPAMI.2023.3277122"},{"key":"8","unstructured":"[8] M. Ghazvininejad, V. Karpukhin, L. Zettlemoyer, and O. Levy, \u201cAligned cross entropy for non-autoregressive machine translation,\u201d Proc. International Conference on Machine Learning, pp.3515-3523, 2020."},{"key":"9","unstructured":"[9] C. Du, Z. Tu, L. Wang, and J. Jiang, \u201cngram-OAXE: Phrase-based order-agnostic cross entropy for non-autoregressive machine translation,\u201d Proc. International Conference on Computational Linguistics, pp.5035-5045, 2022."},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] C. Saharia, W. Chan, S. Saxena, and M. Norouzi, \u201cNon-autoregressive machine translation with latent alignments,\u201d Proc. Conference on Empirical Methods in Natural Language Processing, pp.1098-1108, 2020.","DOI":"10.18653\/v1\/2020.emnlp-main.83"},{"key":"11","unstructured":"[11] C. Shao and Y. Feng, \u201cNon-monotonic latent alignments for CTC-based non-autoregressive machine translation,\u201d Advances in Neural Information Processing Systems, 2022."},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] S. Narayan, S.B. Cohen, and M. Lapata, \u201cDon't give me the details, just the summary! topic-aware convolutional neural networks for extreme summarization,\u201d Proc. Conference on Empirical Methods in Natural Language Processing, pp.1797-1807, 2018. 10.18653\/v1\/d18-1206","DOI":"10.18653\/v1\/D18-1206"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] R. Nallapati, B. Zhou, C. dos Santos, \u00c7. Gul\u00e7ehre, and B. Xiang, \u201cAbstractive text summarization using sequence-to-sequence RNNs and beyond,\u201d Proc. SIGNLL Conference on Computational Natural Language Learning, pp.280-290, 2016. 10.18653\/v1\/k16-1028","DOI":"10.18653\/v1\/K16-1028"},{"key":"14","unstructured":"[14] C. Napoles, M. Gormley, and B. Van Durme, \u201cAnnotated gigaword,\u201d Proc. Joint Workshop on Automatic Knowledge Base Construction and Web-scale Knowledge Extraction, pp.95-100, 2012."},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] L. Lebanoff, K. Song, F. Dernoncourt, D.S. Kim, S. Kim, W. Chang, and F. Liu, \u201cScoring sentence singletons and pairs for abstractive summarization,\u201d Proc. Annual Meeting of the Association for Computational Linguistics, pp.2175-2189, 2019. 10.18653\/v1\/p19-1209","DOI":"10.18653\/v1\/P19-1209"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] L. Qian, H. Zhou, Y. Bao, M. Wang, L. Qiu, W. Zhang, Y. Yu, and L. Li, \u201cGlancing transformer for non-autoregressive neural machine translation,\u201d Proc. Annual Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing, pp.1993-2003, 2021. 10.18653\/v1\/2021.acl-long.155","DOI":"10.18653\/v1\/2021.acl-long.155"},{"key":"17","unstructured":"[17] Z. Sun, Z. Li, H. Wang, D. He, Z. Lin, and Z. Deng, \u201cFast structured decoding for sequence models,\u201d Advances in Neural Information Processing Systems, vol.32, 2019."},{"key":"18","unstructured":"[18] F. Huang, H. Zhou, Y. Liu, H. Li, and M. Huang, \u201cDirected acyclic transformer for non-autoregressive machine translation,\u201d Proc. International Conference on Machine Learning, pp.9410-9428, 2022."},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] Y. Feng and C. Shao, \u201cNon-autoregressive models for fast sequence generation,\u201d Proc. Conference on Empirical Methods in Natural Language Processing, pp.30-35, 2022. 10.18653\/v1\/2022.emnlp-tutorials.6","DOI":"10.18653\/v1\/2022.emnlp-tutorials.6"},{"key":"20","unstructured":"[20] J. Gu, C. Wang, and J. Zhao, \u201cLevenshtein transformer,\u201d Advances in Neural Information Processing Systems, vol.32, 2019."},{"key":"21","unstructured":"[21] C. Zhou, J. Gu, and G. Neubig, \u201cUnderstanding knowledge distillation in non-autoregressive machine translation,\u201d International Conference on Learning Representations, 2020."},{"key":"22","unstructured":"[22] G. Hinton, O. Vinyals, and J. Dean, \u201cDistilling the knowledge in a neural network,\u201d 2015."},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] J. Libovick\u00fd and J. Helcl, \u201cEnd-to-end non-autoregressive neural machine translation with connectionist temporal classification,\u201d Proc. Conference on Empirical Methods in Natural Language Processing, pp.3016-3021, 2018. 10.18653\/v1\/d18-1336","DOI":"10.18653\/v1\/D18-1336"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] A. Haviv, L. Vassertail, and O. Levy, \u201cCan latent alignments improve autoregressive machine translation?,\u201d Proc. Conference of the North American Chapter of the Association for Computational Linguistics, pp.2637-2641, 2021. 10.18653\/v1\/2021.naacl-main.209","DOI":"10.18653\/v1\/2021.naacl-main.209"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] Y. Su, D. Cai, Y. Wang, D. Vandyke, S. Baker, P. Li, and N. Collier, \u201cNon-autoregressive text generation with pre-trained language models,\u201d Proc. Conference of the European Chapter of the Association for Computational Linguistics, pp.234-243, 2021. 10.18653\/v1\/2021.eacl-main.18","DOI":"10.18653\/v1\/2021.eacl-main.18"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] H. Daum\u00e9 III and D. Marcu, \u201cBayesian query-focused summarization,\u201d Proc. International Conference on Computational Linguistics and Annual Meeting of the Association for Computational Linguistics, pp.305-312, 2006. 10.3115\/1220175.1220214","DOI":"10.3115\/1220175.1220214"},{"key":"27","doi-asserted-by":"publisher","unstructured":"[27] M. Allahyari, S. Pouriyeh, M. Assefi, S. Safaei, E.D. Trippe, J.B. Gutierrez, and K. Kochut, \u201cText summarization techniques: A brief survey,\u201d vol.8, no.10, 2017. 10.14569\/ijacsa.2017.081052","DOI":"10.14569\/IJACSA.2017.081052"},{"key":"28","doi-asserted-by":"publisher","unstructured":"[28] J.A. Xu, J.M. Liu, and K. Araki, \u201cA hybrid topic model for multi-document summarization,\u201d Institute of Electronics, Information and Communication Engineers, vol.E98-D, no.5, pp.1089-1094, 2015. 10.1587\/transinf.2014edp7229","DOI":"10.1587\/transinf.2014EDP7229"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] Z.-Y. Dou, P. Liu, H. Hayashi, Z. Jiang, and G. Neubig, \u201cGsum: A general framework for guided neural abstractive summarization,\u201d Proc. Conference of the North American Chapter of the Association for Computational Linguistics, pp.4830-4842, 2021. 10.18653\/v1\/2021.naacl-main.384","DOI":"10.18653\/v1\/2021.naacl-main.384"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] N. Gu, E. Ash, and R. Hahnloser, \u201cMemSum: Extractive summarization of long documents using multi-step episodic Markov decision processes,\u201d Proc. Annual Meeting of the Association for Computational Linguistics, pp.6507-6522, 2022. 10.18653\/v1\/2022.acl-long.450","DOI":"10.18653\/v1\/2022.acl-long.450"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] M. Zhong, P. Liu, Y. Chen, D. Wang, X. Qiu, and X. Huang, \u201cExtractive summarization as text matching,\u201d Proc. Annual Meeting of the Association for Computational Linguistics, pp.6197-6208, 2020. 10.18653\/v1\/2020.acl-main.552","DOI":"10.18653\/v1\/2020.acl-main.552"},{"key":"32","doi-asserted-by":"publisher","unstructured":"[32] E.-k. Kim and K.-S. Choi, \u201cEntity summarization based on entity grouping in multilingual projected entity space,\u201d Institute of Electronics, Information and Communication Engineers, pp.2138-2146, 2017. 10.1587\/transinf.2016edp7235","DOI":"10.1587\/transinf.2016EDP7235"},{"key":"33","unstructured":"[33] W. Qi, Y. Gong, J. Jiao, Y. Yan, W. Chen, D. Liu, K. Tang, H. Li, J. Chen, R. Zhang, M. Zhou, and N. Duan, \u201cBang: Bridging autoregressive and non-autoregressive generation with large scale pretraining,\u201d Proc. International Conference on Machine Learning, pp.8630-8639, 2021."},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] R. Schumann, L. Mou, Y. Lu, O. Vechtomova, and K. Markert, \u201cDiscrete optimization for unsupervised sentence summarization with word-level extraction,\u201d Proc. Annual Meeting of the Association for Computational Linguistics, pp.5032-5042, 2020. 10.18653\/v1\/2020.acl-main.452","DOI":"10.18653\/v1\/2020.acl-main.452"},{"key":"35","unstructured":"[35] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, L.u. Kaiser, and I. Polosukhin, \u201cAttention is all you need,\u201d Advances in Neural Information Processing Systems, pp.5998-6008, 2017."},{"key":"36","doi-asserted-by":"crossref","unstructured":"[36] A. Graves, S. Fern\u00e1ndez, F. Gomez, and J. Schmidhuber, \u201cConnectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks,\u201d Proc. International Conference on Machine Learning, pp.369-376, 2006. 10.1145\/1143844.1143891","DOI":"10.1145\/1143844.1143891"},{"key":"37","doi-asserted-by":"crossref","unstructured":"[37] M. Ott, S. Edunov, A. Baevski, A. Fan, S. Gross, N. Ng, D. Grangier, and M. Auli, \u201cfairseq: A fast, extensible toolkit for sequence modeling,\u201d Proc. Conference of the North American Chapter of the Association for Computational Linguistics, pp.48-53, 2019. 10.18653\/v1\/n19-4009","DOI":"10.18653\/v1\/N19-4009"},{"key":"38","unstructured":"[38] T. Jiang, S. Huang, Z. Zhang, D. Wang, F. Zhuang, F. Wei, H. Huang, L. Zhang, and Q. Zhang, \u201cImproving non-autoregressive generation with mixup training,\u201d arXiv:2110.11115, 2021."},{"key":"39","unstructured":"[39] K.M. Hermann, T. Kocisky, E. Grefenstette, L. Espeholt, W. Kay, M. Suleyman, and P. Blunsom, \u201cTeaching machines to read and comprehend,\u201d Advances in Neural Information Processing Systems, pp.1693-1701, 2015."},{"key":"40","unstructured":"[40] J. Gu, C. Wang, and J. Zhao, \u201cLevenshtein transformer,\u201d Advances in Neural Information Processing Systems, 2019."},{"key":"41","doi-asserted-by":"crossref","unstructured":"[41] R. Jia, Y. Cao, H. Tang, F. Fang, C. Cao, and S. Wang, \u201cNeural extractive summarization with hierarchical attentive heterogeneous graph network,\u201d Proc. 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), (Online), pp.3622-3631, Association for Computational Linguistics, Nov. 2020. 10.18653\/v1\/2020.emnlp-main.295","DOI":"10.18653\/v1\/2020.emnlp-main.295"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/3\/E107.D_2023EDP7111\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T04:24:19Z","timestamp":1709353459000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/3\/E107.D_2023EDP7111\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,1]]},"references-count":41,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2023edp7111","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,1]]},"article-number":"2023EDP7111"}}