{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T22:00:17Z","timestamp":1747173617354,"version":"3.40.5"},"reference-count":75,"publisher":"Cambridge University Press (CUP)","issue":"2","license":[{"start":{"date-parts":[[2022,2,4]],"date-time":"2022-02-04T00:00:00Z","timestamp":1643932800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["Nat. Lang. Eng."],"published-print":{"date-parts":[[2023,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Previouswork in slogan generation focused on utilising slogan skeletons mined from existing slogans. While some generated slogans can be catchy, they are often not coherent with the company\u2019s focus or style across their marketing communications because the skeletons are mined from other companies\u2019 slogans. We propose a sequence-to-sequence (seq2seq) Transformer model to generate slogans from a brief company description. A na\u00efve seq2seq model fine-tuned for slogan generation is prone to introducing false information. We use company name delexicalisation and entity masking to alleviate this problem and improve the generated slogans\u2019 quality and truthfulness. Furthermore, we apply conditional training based on the first words\u2019 part-of-speech tag to generate syntactically diverse slogans. Our best model achieved a ROUGE-1\/-2\/-L <jats:inline-formula><jats:alternatives><jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mime-subtype=\"png\" xlink:href=\"S1351324921000474_inline1.png\"\/><jats:tex-math>\n$\\mathrm{F}_1$\n<\/jats:tex-math><\/jats:alternatives><\/jats:inline-formula> score of 35.58\/18.47\/33.32. Besides, automatic and human evaluations indicate that our method generates significantly more factual, diverse and catchy slogans than strong long short-term memory and Transformer seq2seq baselines.<\/jats:p>","DOI":"10.1017\/s1351324921000474","type":"journal-article","created":{"date-parts":[[2022,2,4]],"date-time":"2022-02-04T07:05:13Z","timestamp":1643958313000},"page":"254-286","update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":3,"title":["Towards improving coherence and diversity of slogan generation"],"prefix":"10.1017","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9599-9181","authenticated-orcid":false,"given":"Yiping","family":"Jin","sequence":"first","affiliation":[]},{"given":"Akshay","family":"Bhatia","sequence":"additional","affiliation":[]},{"given":"Dittaya","family":"Wanvarie","sequence":"additional","affiliation":[]},{"given":"Phu T. V.","family":"Le","sequence":"additional","affiliation":[]}],"member":"56","published-online":{"date-parts":[[2022,2,4]]},"reference":[{"key":"S1351324921000474_ref62","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"S1351324921000474_ref73","unstructured":"Zhang, J. , Zhao, Y. , Saleh, M. and Liu, P. (2020a). Pegasus: Pre-training with extracted gap-sentences for abstractive summarization. In Proceedings of the International Conference on Machine Learning. PMLR, pp. 11328\u201311339."},{"key":"S1351324921000474_ref5","unstructured":"Bahdanau, D. , Cho, K. and Bengio, Y. (2015). Neural machine translation by jointly learning to align and translate. In Proceedings of the 3rd International Conference on Learning Representations, San Diego, CA, USA."},{"key":"S1351324921000474_ref3","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324920000236"},{"key":"S1351324921000474_ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330754"},{"key":"S1351324921000474_ref40","unstructured":"Liu, Y. , Ott, M. , Goyal, N. , Du, J. , Joshi, M. , Chen, D. , Levy, O. , Lewis, M. , Zettlemoyer, L. and Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692."},{"key":"S1351324921000474_ref45","doi-asserted-by":"publisher","DOI":"10.1111\/j.0022-3840.1977.00308.x"},{"key":"S1351324921000474_ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1320"},{"key":"S1351324921000474_ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"S1351324921000474_ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.58"},{"key":"S1351324921000474_ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1213"},{"key":"S1351324921000474_ref72","unstructured":"Zhang, H. , Duckworth, D. , Ippolito, D. and Neelakantan, A. (2021). Trading off diversity and quality in natural language generation. In Proceedings of the Workshop on Human Evaluation of NLP Systems (HumEval), Online. Association for Computational Linguistics, pp. 25\u201333."},{"key":"S1351324921000474_ref47","unstructured":"Misawa, S. , Miura, Y. , Taniguchi, T. and Ohkuma, T. (2020). Distinctive slogan generation with reconstruction. In Proceedings of Workshop on Natural Language Processing in E-Commerce, Barcelona, Spain. Association for Computational Linguistics, pp. 87\u201397."},{"key":"S1351324921000474_ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.456"},{"key":"S1351324921000474_ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"S1351324921000474_ref52","unstructured":"\u00d6zbal, G. , Pighin, D. and Strapparava, C. (2013). Brainsup: Brainstorming support for creative sentence generation. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Sofia, Bulgaria. Association for Computational Linguistics, pp. 1446\u20131455."},{"key":"S1351324921000474_ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330955"},{"key":"S1351324921000474_ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1034"},{"key":"S1351324921000474_ref28","unstructured":"Holtzman, A. , Buys, J. , Du, L. , Forbes, M. and Choi, Y. (2019). The curious case of neural text degeneration. In Proceedings of the International Conference on Learning Representations, New Orleans, Louisiana."},{"key":"S1351324921000474_ref36","unstructured":"Keskar, N.S. , McCann, B. , Varshney, L. , Xiong, C. and Socher, R. (2019). CTRL - A conditional transformer language model for controllable generation. arXiv preprint arXiv:1909.05858."},{"key":"S1351324921000474_ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.383"},{"key":"S1351324921000474_ref10","doi-asserted-by":"crossref","unstructured":"Cao, Z. , Wei, F. , Li, W. and Li, S. (2018). Faithful to the original: Fact aware neural abstractive summarization. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32, New Orleans, Louisiana.","DOI":"10.1609\/aaai.v32i1.11912"},{"key":"S1351324921000474_ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.475"},{"key":"S1351324921000474_ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1043"},{"key":"S1351324921000474_ref68","unstructured":"Welleck, S. , Kulikov, I. , Roller, S. , Dinan, E. , Cho, K. and Weston, J. (2019). Neural text generation with unlikelihood training. In Proceedings of the International Conference on Learning Representations, New Orleans, Louisiana."},{"key":"S1351324921000474_ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1395"},{"key":"S1351324921000474_ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.749"},{"key":"S1351324921000474_ref56","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"S1351324921000474_ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"S1351324921000474_ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.42"},{"key":"S1351324921000474_ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3186345"},{"key":"S1351324921000474_ref65","first-page":"5998","volume-title":"In Advances in neural information processing systems","author":"Vaswani","year":"2017"},{"key":"S1351324921000474_ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1099"},{"key":"S1351324921000474_ref26","first-page":"1693","volume-title":"In Advances in Neural Information Processing Systems","author":"Hermann","year":"2015"},{"key":"S1351324921000474_ref69","doi-asserted-by":"publisher","DOI":"10.1080\/00913367.1972.10672470"},{"key":"S1351324921000474_ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2048"},{"key":"S1351324921000474_ref6","unstructured":"Boigne, J. (2020). Building a slogan generator with gpt-2. Available at https:\/\/jonathanbgn.com\/gpt2\/2020\/01\/20\/slogan-gen-erator.html (accessed 14 January 2020)."},{"key":"S1351324921000474_ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1125"},{"key":"S1351324921000474_ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.506"},{"key":"S1351324921000474_ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77105-0_57"},{"key":"S1351324921000474_ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.123"},{"key":"S1351324921000474_ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"key":"S1351324921000474_ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.235"},{"key":"S1351324921000474_ref58","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00349"},{"key":"S1351324921000474_ref12","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"S1351324921000474_ref70","doi-asserted-by":"crossref","unstructured":"Williams, A. , Nangia, N. and 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, Volume 1 (Long Papers), pp. 1112\u20131122, New Orleans, Louisiana. Association for Computational Linguistics.","DOI":"10.18653\/v1\/N18-1101"},{"key":"S1351324921000474_ref39","unstructured":"Li, J. , Monroe, W. and Jurafsky, D. (2016). A simple, fast diverse decoding algorithm for neural generation. arXiv preprint arXiv:1611.08562."},{"key":"S1351324921000474_ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.450"},{"key":"S1351324921000474_ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.501"},{"key":"S1351324921000474_ref46","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume":"26","author":"Mikolov","year":"2013","journal-title":"In Advances in neural information processing systems"},{"key":"S1351324921000474_ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.458"},{"key":"S1351324921000474_ref22","unstructured":"Gatti, L. , \u00d6zbal, G. , Guerini, M. , Stock, O. and Strapparava, C. (2015). Slogans are not forever: Adapting linguistic expressions to the news. In Proceedings of the 24th International Joint Conference on Artificial Intelligence, Buenos Aires, Argentina, pp. 2452\u20132458."},{"key":"S1351324921000474_ref7","doi-asserted-by":"publisher","DOI":"10.1509\/jmr.14.0117"},{"key":"S1351324921000474_ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.454"},{"key":"S1351324921000474_ref2","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0901_7"},{"key":"S1351324921000474_ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412720"},{"key":"S1351324921000474_ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1452"},{"key":"S1351324921000474_ref13","doi-asserted-by":"publisher","DOI":"10.1177\/001316446002000104"},{"key":"S1351324921000474_ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.420"},{"key":"S1351324921000474_ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"S1351324921000474_ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.173"},{"key":"S1351324921000474_ref35","doi-asserted-by":"publisher","DOI":"10.3115\/1572433.1572440"},{"key":"S1351324921000474_ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1082"},{"key":"S1351324921000474_ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.750"},{"key":"S1351324921000474_ref41","doi-asserted-by":"publisher","DOI":"10.1037\/h0072217"},{"key":"S1351324921000474_ref8","unstructured":"Caccia, M. , Caccia, L. , Fedus, W. , Larochelle, H. , Pineau, J. and Charlin, L. (2019). Language gans falling short. In Proceedings of the International Conference on Learning Representations, New Orleans, Louisiana."},{"key":"S1351324921000474_ref54","doi-asserted-by":"publisher","DOI":"10.2753\/JOA0091-3367380104"},{"key":"S1351324921000474_ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-industry.33"},{"key":"S1351324921000474_ref64","unstructured":"Toma\u0161ic, P. , Znidar\u0161ic, M. and Papa, G. (2014). Implementation of a slogan generator. In Proceedings of 5th International Conference on Computational Creativity, volume 301, Ljubljana, Slovenia, pp. 340\u2013343."},{"key":"S1351324921000474_ref29","doi-asserted-by":"publisher","DOI":"10.3390\/info11020108"},{"key":"S1351324921000474_ref14","unstructured":"Devlin, J. , Chang, M.-W. , Lee, K. and Toutanova, K. (2019). 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, Volume 1 (Long and Short Papers), Minneapolis, Minnesota. Association for Computational Linguistics, pp. 4171\u20134186."},{"key":"S1351324921000474_ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6526"},{"key":"S1351324921000474_ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-55218-3_2"},{"volume-title":"Speech understanding systems: A summary of results of the five-year research effort","year":"1977","author":"Reddy","key":"S1351324921000474_ref57"},{"key":"S1351324921000474_ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"}],"container-title":["Natural Language Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1351324921000474","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T04:19:45Z","timestamp":1678681185000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1351324921000474\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,4]]},"references-count":75,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["S1351324921000474"],"URL":"https:\/\/doi.org\/10.1017\/s1351324921000474","relation":{},"ISSN":["1351-3249","1469-8110"],"issn-type":[{"type":"print","value":"1351-3249"},{"type":"electronic","value":"1469-8110"}],"subject":[],"published":{"date-parts":[[2022,2,4]]},"assertion":[{"value":"\u00a9 The Author(s), 2022. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}}]}}