{"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/improving-conditional-sequence-generative","title":"Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation","arxiv_id":"1808.05599","date":"2018-08-16","proceeding":null,"authors":["Yi-Lin Tuan","Hung-Yi Lee"],"abstract":"Sequence generative adversarial networks (SeqGAN) have been used to improve\nconditional sequence generation tasks, for example, chit-chat dialogue\ngeneration. To stabilize the training of SeqGAN, Monte Carlo tree search (MCTS)\nor reward at every generation step (REGS) is used to evaluate the goodness of a\ngenerated subsequence. MCTS is computationally intensive, but the performance\nof REGS is worse than MCTS. In this paper, we propose stepwise GAN (StepGAN),\nin which the discriminator is modified to automatically assign scores\nquantifying the goodness of each subsequence at every generation step. StepGAN\nhas significantly less computational costs than MCTS. We demonstrate that\nStepGAN outperforms previous GAN-based methods on both synthetic experiment and\nchit-chat dialogue generation.","url_abs":"http://arxiv.org/abs/1808.05599v2","url_pdf":"http://arxiv.org/pdf/1808.05599v2.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":"improving-conditional-sequence-generative","repo_url":"https://github.com/Pascalson/Conditional-Seq-GANs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.05599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.05599"}},"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/Pascalson/Conditional-Seq-GANs","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"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":0,"samples":[{"code_sha256_prefix":"b8d5ad2a265be324","entry":"parse_buckets","repo":"Pascalson/Conditional-Seq-GANs","repo_kind":"official","path":"args.py","file_url":"https://github.com/Pascalson/Conditional-Seq-GANs/blob/HEAD/args.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8d5ad2a265be324"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}