{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T04:24:28Z","timestamp":1768710268120,"version":"3.49.0"},"reference-count":11,"publisher":"MIT Press - Journals","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["TACL"],"published-print":{"date-parts":[[2018,12]]},"abstract":"<jats:p> Stylistic dialogue response generation, with valuable applications in personality-based conversational agents, is a challenging task because the response needs to be fluent, contextually-relevant, as well as paralinguistically accurate. Moreover, parallel datasets for regular-to-stylistic pairs are usually unavailable. We present three weakly-supervised models that can generate diverse, polite (or rude) dialogue responses without parallel data. Our late fusion model (Fusion) merges the decoder of an encoder-attention-decoder dialogue model with a language model trained on stand-alone polite utterances. Our label-finetuning (LFT) model prepends to each source sequence a politeness-score scaled label (predicted by our state-of-the-art politeness classifier) during training, and at test time is able to generate polite, neutral, and rude responses by simply scaling the label embedding by the corresponding score. Our reinforcement learning model (Polite-RL) encourages politeness generation by assigning rewards proportional to the politeness classifier score of the sampled response. We also present two retrievalbased, polite dialogue model baselines. Human evaluation validates that while the Fusion and the retrieval-based models achieve politeness with poorer context-relevance, the LFT and Polite-RL models can produce significantly more polite responses without sacrificing dialogue quality. <\/jats:p>","DOI":"10.1162\/tacl_a_00027","type":"journal-article","created":{"date-parts":[[2018,12,10]],"date-time":"2018-12-10T19:32:50Z","timestamp":1544470370000},"page":"373-389","source":"Crossref","is-referenced-by-count":53,"title":["Polite Dialogue Generation Without Parallel Data"],"prefix":"10.1162","volume":"6","author":[{"given":"Tong","family":"Niu","sequence":"first","affiliation":[{"name":"UNC Chapel Hill,"}]},{"given":"Mohit","family":"Bansal","sequence":"additional","affiliation":[{"name":"UNC Chapel Hill,"}]}],"member":"281","reference":[{"key":"p_2","doi-asserted-by":"publisher","DOI":"10.1162\/coli.07-034-R2"},{"issue":"1","key":"p_6","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/1745691610393980","volume":"6","author":"Buhrmester Michael","year":"2011","journal-title":"Perspectives on Psychological Science"},{"issue":"4","key":"p_7","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1037\/h0026256","volume":"70","author":"Cohen Jacob","year":"1968","journal-title":"Psychological Bulletin"},{"key":"p_8","first-page":"2493","volume":"12","author":"Collobert Ronan","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"p_18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"p_19","first-page":"1587","author":"Hu Zhiting","year":"2017","journal-title":"PMLR 70, pages"},{"issue":"1","key":"p_20","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1037\/0021-9010.69.1.85","volume":"69","author":"James Lawrence R.","year":"1984","journal-title":"Journal of Applied Psychology"},{"key":"p_22","author":"Johnson Melvin","year":"2017","journal-title":"Transactions of the Association for Computational Linguistics"},{"issue":"11","key":"p_50","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"Schuster Mike","year":"1997","journal-title":"IEEE Transactions on Signal Processing"},{"key":"p_58","first-page":"1057","author":"Sutton Richard S.","year":"2000","journal-title":"Advances in Neural Information Processing Systems 12, pages"},{"issue":"3","key":"p_62","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/j.ijresmar.2010.02.004","volume":"27","author":"Weijters Bert","year":"2010","journal-title":"International Journal of Research in Marketing"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/tacl_a_00027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:37:58Z","timestamp":1615585078000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/43443"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":11,"alternative-id":["10.1162\/tacl_a_00027"],"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00027","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12]]}}}