{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/polite-dialogue-generation-without-parallel","title":"Polite Dialogue Generation Without Parallel Data","arxiv_id":"1805.03162","date":"2018-05-08","proceeding":"TACL 2018 1","authors":["Tong Niu","Mohit Bansal"],"abstract":"Stylistic dialogue response generation, with valuable applications in\npersonality-based conversational agents, is a challenging task because the\nresponse needs to be fluent, contextually-relevant, as well as\nparalinguistically accurate. Moreover, parallel datasets for\nregular-to-stylistic pairs are usually unavailable. We present three\nweakly-supervised models that can generate diverse polite (or rude) dialogue\nresponses without parallel data. Our late fusion model (Fusion) merges the\ndecoder of an encoder-attention-decoder dialogue model with a language model\ntrained on stand-alone polite utterances. Our label-fine-tuning (LFT) model\nprepends to each source sequence a politeness-score scaled label (predicted by\nour state-of-the-art politeness classifier) during training, and at test time\nis able to generate polite, neutral, and rude responses by simply scaling the\nlabel embedding by the corresponding score. Our reinforcement learning model\n(Polite-RL) encourages politeness generation by assigning rewards proportional\nto the politeness classifier score of the sampled response. We also present two\nretrieval-based polite dialogue model baselines. Human evaluation validates\nthat while the Fusion and the retrieval-based models achieve politeness with\npoorer context-relevance, the LFT and Polite-RL models can produce\nsignificantly more polite responses without sacrificing dialogue quality.","url_abs":"http://arxiv.org/abs/1805.03162v1","url_pdf":"http://arxiv.org/pdf/1805.03162v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"polite-dialogue-generation-without-parallel","repo_url":"https://github.com/WolfNiu/polite-dialogue-generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"response-generation","task_name":"Response Generation"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.03162"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/WolfNiu/polite-dialogue-generation","reach":null}],"summary":{"ran_honours":1,"ran_violates":1},"by_repo_kind":{"listed":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"17bef5d0477a9528","entry":"compute_n_examples","repo":"WolfNiu/polite-dialogue-generation","repo_kind":"listed","path":"src/model/LSTM-CNN-multi-GPU-new_vocab.py","file_url":"https://github.com/WolfNiu/polite-dialogue-generation/blob/HEAD/src/model/LSTM-CNN-multi-GPU-new_vocab.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"17bef5d0477a9528"}},{"code_sha256_prefix":"a4b5a8d188329b96","entry":"shuffle","repo":"WolfNiu/polite-dialogue-generation","repo_kind":"listed","path":"src/model/LSTM-CNN-multi-GPU-new_vocab.py","file_url":"https://github.com/WolfNiu/polite-dialogue-generation/blob/HEAD/src/model/LSTM-CNN-multi-GPU-new_vocab.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4b5a8d188329b96"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}