{"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/araml-a-stable-adversarial-training-framework","title":"ARAML: A Stable Adversarial Training Framework for Text Generation","arxiv_id":"1908.07195","date":"2019-08-20","proceeding":"IJCNLP 2019 11","authors":["Pei Ke","Fei Huang","Minlie Huang","Xiaoyan Zhu"],"abstract":"Most of the existing generative adversarial networks (GAN) for text generation suffer from the instability of reinforcement learning training algorithms such as policy gradient, leading to unstable performance. To tackle this problem, we propose a novel framework called Adversarial Reward Augmented Maximum Likelihood (ARAML). During adversarial training, the discriminator assigns rewards to samples which are acquired from a stationary distribution near the data rather than the generator's distribution. The generator is optimized with maximum likelihood estimation augmented by the discriminator's rewards instead of policy gradient. Experiments show that our model can outperform state-of-the-art text GANs with a more stable training process.","url_abs":"https://arxiv.org/abs/1908.07195v1","url_pdf":"https://arxiv.org/pdf/1908.07195v1.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":"araml-a-stable-adversarial-training-framework","repo_url":"https://github.com/kepei1106/ARAML","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.07195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07195"}},"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/kepei1106/ARAML","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"a3124578eae0196c","entry":"highway","repo":"kepei1106/ARAML","repo_kind":"official","path":"src/coco_emnlp/araml_rewarder.py","file_url":"https://github.com/kepei1106/ARAML/blob/HEAD/src/coco_emnlp/araml_rewarder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a3124578eae0196c"}},{"code_sha256_prefix":"0a26e6ea99bbd1eb","entry":"linear","repo":"kepei1106/ARAML","repo_kind":"official","path":"src/coco_emnlp/araml_rewarder.py","file_url":"https://github.com/kepei1106/ARAML/blob/HEAD/src/coco_emnlp/araml_rewarder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0a26e6ea99bbd1eb"}},{"code_sha256_prefix":"35d59903533d24ac","entry":"output_projection_layer","repo":"kepei1106/ARAML","repo_kind":"official","path":"src/coco_emnlp/lm/my_output_projection.py","file_url":"https://github.com/kepei1106/ARAML/blob/HEAD/src/coco_emnlp/lm/my_output_projection.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"35d59903533d24ac"}},{"code_sha256_prefix":"59c960268be04f6d","entry":"sequence_loss","repo":"kepei1106/ARAML","repo_kind":"official","path":"src/coco_emnlp/lm/my_loss.py","file_url":"https://github.com/kepei1106/ARAML/blob/HEAD/src/coco_emnlp/lm/my_loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59c960268be04f6d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}