{"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/rethinking-perturbations-in-encoder-decoders","title":"Rethinking Perturbations in Encoder-Decoders for Fast Training","arxiv_id":"2104.01853","date":"2021-04-05","proceeding":"NAACL 2021 4","authors":["Sho Takase","Shun Kiyono"],"abstract":"We often use perturbations to regularize neural models. For neural encoder-decoders, previous studies applied the scheduled sampling (Bengio et al., 2015) and adversarial perturbations (Sato et al., 2019) as perturbations but these methods require considerable computational time. Thus, this study addresses the question of whether these approaches are efficient enough for training time. We compare several perturbations in sequence-to-sequence problems with respect to computational time. Experimental results show that the simple techniques such as word dropout (Gal and Ghahramani, 2016) and random replacement of input tokens achieve comparable (or better) scores to the recently proposed perturbations, even though these simple methods are faster. Our code is publicly available at https://github.com/takase/rethink_perturbations.","url_abs":"https://arxiv.org/abs/2104.01853v1","url_pdf":"https://arxiv.org/pdf/2104.01853v1.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":"rethinking-perturbations-in-encoder-decoders","repo_url":"https://github.com/takase/rethink_perturbations","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-iwslt2014-german","task":"Machine Translation","dataset":"IWSLT2014 German-English","model":"Transformer+Rep(Sim)+WDrop","rank_in_archive_order":17,"of":34,"metrics":{"BLEU score":"36.22","Number of Params":"37M"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"Transformer+Rep(Uni)","rank_in_archive_order":3,"of":91,"metrics":{"BLEU score":"33.89","SacreBLEU":"32.35"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-duc-2004-task-1","task":"Text Summarization","dataset":"DUC 2004 Task 1","model":"Transformer+WDrop","rank_in_archive_order":1,"of":13,"metrics":{"ROUGE-1":"33.06","ROUGE-2":"11.45","ROUGE-L":"28.51"},"uses_additional_data":true},{"leaderboard":"/sota/text-summarization-on-gigaword","task":"Text Summarization","dataset":"GigaWord","model":"Transformer+Rep(Uni)","rank_in_archive_order":7,"of":41,"metrics":{"ROUGE-1":"39.81","ROUGE-2":"20.40","ROUGE-L":"36.93"},"uses_additional_data":true},{"leaderboard":"/sota/text-summarization-on-gigaword","task":"Text Summarization","dataset":"GigaWord","model":"Transformer+Wdrop","rank_in_archive_order":8,"of":41,"metrics":{"ROUGE-1":"39.66","ROUGE-2":"20.45","ROUGE-L":"36.59"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.01853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.01853"}},"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":"deterministic:regex_extraction","url":"https://github.com/takase/rethink_perturbations","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":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":1,"samples":[{"code_sha256_prefix":"82bdf940665aeeb4","entry":"safe_readline","repo":"takase/rethink_perturbations","repo_kind":"official","path":"fairseq/binarizer.py","file_url":"https://github.com/takase/rethink_perturbations/blob/HEAD/fairseq/binarizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"82bdf940665aeeb4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}