{"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/adversarial-learning-for-neural-dialogue","title":"Adversarial Learning for Neural Dialogue Generation","arxiv_id":"1701.06547","date":"2017-01-23","proceeding":"EMNLP 2017 9","authors":["Jiwei Li","Will Monroe","Tianlin Shi","Sébastien Jean","Alan Ritter","Dan Jurafsky"],"abstract":"In this paper, drawing intuition from the Turing test, we propose using\nadversarial training for open-domain dialogue generation: the system is trained\nto produce sequences that are indistinguishable from human-generated dialogue\nutterances. We cast the task as a reinforcement learning (RL) problem where we\njointly train two systems, a generative model to produce response sequences,\nand a discriminator---analagous to the human evaluator in the Turing test--- to\ndistinguish between the human-generated dialogues and the machine-generated\nones. The outputs from the discriminator are then used as rewards for the\ngenerative model, pushing the system to generate dialogues that mostly resemble\nhuman dialogues.\n  In addition to adversarial training we describe a model for adversarial {\\em\nevaluation} that uses success in fooling an adversary as a dialogue evaluation\nmetric, while avoiding a number of potential pitfalls. Experimental results on\nseveral metrics, including adversarial evaluation, demonstrate that the\nadversarially-trained system generates higher-quality responses than previous\nbaselines.","url_abs":"http://arxiv.org/abs/1701.06547v5","url_pdf":"http://arxiv.org/pdf/1701.06547v5.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":"adversarial-learning-for-neural-dialogue","repo_url":"https://github.com/AIJoris/DPAC-DialogueGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-learning-for-neural-dialogue","repo_url":"https://github.com/CatherineWong/dancin_seq2seq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"adversarial-learning-for-neural-dialogue","repo_url":"https://github.com/YufanPaPa/GAN_SSN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"adversarial-learning-for-neural-dialogue","repo_url":"https://github.com/aqzheng/Adversarial-Learning-for-Neural-Dialogue-Generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"adversarial-learning-for-neural-dialogue","repo_url":"https://github.com/jsbaan/DPAC-DialogueGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"adversarial-learning-for-neural-dialogue","repo_url":"https://github.com/liuyuemaicha/Adversarial-Learning-for-Neural-Dialogue-Generation-in-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"adversarial-learning-for-neural-dialogue","repo_url":"https://github.com/thomashuang2017/simpson-dialogue-gan-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"adversarial-learning-for-neural-dialogue","repo_url":"https://github.com/zpschang/seqGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"dialogue-evaluation","task_name":"Dialogue Evaluation"},{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dialogue-generation-on-amazon-5","task":"Dialogue Generation","dataset":"Amazon-5","model":"mm","rank_in_archive_order":1,"of":1,"metrics":{"1 in 10 R@2":"5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1701.06547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.06547"}},"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/zpschang/seqGAN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aqzheng/Adversarial-Learning-for-Neural-Dialogue-Generation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AIJoris/DPAC-DialogueGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jsbaan/DPAC-DialogueGAN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liuyuemaicha/Adversarial-Learning-for-Neural-Dialogue-Generation-in-Tensorflow","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thomashuang2017/simpson-dialogue-gan-master","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YufanPaPa/GAN_SSN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CatherineWong/dancin_seq2seq","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"ran":1,"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":2,"samples":[{"code_sha256_prefix":"b2d8244fa9563626","entry":"softmax","repo":"liuyuemaicha/Adversarial-Learning-for-Neural-Dialogue-Generation-in-Tensorflow","repo_kind":"listed","path":"al_neural_dialogue_train.py","file_url":"https://github.com/liuyuemaicha/Adversarial-Learning-for-Neural-Dialogue-Generation-in-Tensorflow/blob/HEAD/al_neural_dialogue_train.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b2d8244fa9563626"}},{"code_sha256_prefix":"071b40b5cfc7f9db","entry":"disc_step","repo":"liuyuemaicha/Adversarial-Learning-for-Neural-Dialogue-Generation-in-Tensorflow","repo_kind":"listed","path":"al_neural_dialogue_train.py","file_url":"https://github.com/liuyuemaicha/Adversarial-Learning-for-Neural-Dialogue-Generation-in-Tensorflow/blob/HEAD/al_neural_dialogue_train.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"071b40b5cfc7f9db"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}