{"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/diversifying-dialog-generation-via-adaptive","title":"Diversifying Dialog Generation via Adaptive Label Smoothing","arxiv_id":"2105.14556","date":"2021-05-30","proceeding":"ACL 2021 5","authors":["Yida Wang","Yinhe Zheng","Yong Jiang","Minlie Huang"],"abstract":"Neural dialogue generation models trained with the one-hot target distribution suffer from the over-confidence issue, which leads to poor generation diversity as widely reported in the literature. Although existing approaches such as label smoothing can alleviate this issue, they fail to adapt to diverse dialog contexts. In this paper, we propose an Adaptive Label Smoothing (AdaLabel) approach that can adaptively estimate a target label distribution at each time step for different contexts. The maximum probability in the predicted distribution is used to modify the soft target distribution produced by a novel light-weight bi-directional decoder module. The resulting target distribution is aware of both previous and future contexts and is adjusted to avoid over-training the dialogue model. Our model can be trained in an end-to-end manner. Extensive experiments on two benchmark datasets show that our approach outperforms various competitive baselines in producing diverse responses.","url_abs":"https://arxiv.org/abs/2105.14556v1","url_pdf":"https://arxiv.org/pdf/2105.14556v1.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":"diversifying-dialog-generation-via-adaptive","repo_url":"https://github.com/lemon234071/AdaLabel","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"dialogue-generation","task_name":"Dialogue Generation"},{"task_slug":"diversity","task_name":"Diversity"}],"methods":[{"method_slug":"aware","method_name":"AWARE"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.14556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14556"}},"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/lemon234071/AdaLabel","reach":null}],"summary":{"ran":2,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":"3389446ed90d80b6","entry":"AdaLabLoss","repo":"lemon234071/AdaLabel","repo_kind":"official","path":"onmt/utils/loss.py","file_url":"https://github.com/lemon234071/AdaLabel/blob/HEAD/onmt/utils/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3389446ed90d80b6"}},{"code_sha256_prefix":"c4741c2232030fcb","entry":"LossComputeBase","repo":"lemon234071/AdaLabel","repo_kind":"official","path":"onmt/utils/loss.py","file_url":"https://github.com/lemon234071/AdaLabel/blob/HEAD/onmt/utils/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c4741c2232030fcb"}},{"code_sha256_prefix":"e6f9b7a73fec596e","entry":"filter_shard_state","repo":"lemon234071/AdaLabel","repo_kind":"official","path":"onmt/utils/loss.py","file_url":"https://github.com/lemon234071/AdaLabel/blob/HEAD/onmt/utils/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e6f9b7a73fec596e"}},{"code_sha256_prefix":"38cecda28cf3e292","entry":"shards","repo":"lemon234071/AdaLabel","repo_kind":"official","path":"onmt/utils/loss.py","file_url":"https://github.com/lemon234071/AdaLabel/blob/HEAD/onmt/utils/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"38cecda28cf3e292"}},{"code_sha256_prefix":"0c1ba651d677a958","entry":"AdaLabLossCompute","repo":"lemon234071/AdaLabel","repo_kind":"official","path":"onmt/utils/loss.py","file_url":"https://github.com/lemon234071/AdaLabel/blob/HEAD/onmt/utils/loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c1ba651d677a958"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}