{"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/applying-the-transformer-to-character-level","title":"Applying the Transformer to Character-level Transduction","arxiv_id":"2005.10213","date":"2020-05-20","proceeding":"EACL 2021 2","authors":["Shijie Wu","Ryan Cotterell","Mans Hulden"],"abstract":"The transformer has been shown to outperform recurrent neural network-based sequence-to-sequence models in various word-level NLP tasks. Yet for character-level transduction tasks, e.g. morphological inflection generation and historical text normalization, there are few works that outperform recurrent models using the transformer. In an empirical study, we uncover that, in contrast to recurrent sequence-to-sequence models, the batch size plays a crucial role in the performance of the transformer on character-level tasks, and we show that with a large enough batch size, the transformer does indeed outperform recurrent models. We also introduce a simple technique to handle feature-guided character-level transduction that further improves performance. With these insights, we achieve state-of-the-art performance on morphological inflection and historical text normalization. We also show that the transformer outperforms a strong baseline on two other character-level transduction tasks: grapheme-to-phoneme conversion and transliteration.","url_abs":"https://arxiv.org/abs/2005.10213v2","url_pdf":"https://arxiv.org/pdf/2005.10213v2.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":"applying-the-transformer-to-character-level","repo_url":"https://github.com/shijie-wu/neural-transducer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"applying-the-transformer-to-character-level","repo_url":"https://github.com/Aso-UniMelb/neural-fieldwork-guide","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"applying-the-transformer-to-character-level","repo_url":"https://github.com/sigmorphon/2022inflectionst","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"Grapheme-to-Phoneme Conversion"},{"task_slug":"morphological-inflection","task_name":"Morphological Inflection"},{"task_slug":"text-normalization","task_name":"Text Normalization"},{"task_slug":"transliteration","task_name":"Transliteration"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.10213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.10213"}},"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/Aso-UniMelb/neural-fieldwork-guide","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sigmorphon/2022inflectionst","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shijie-wu/neural-transducer","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"listed":{"samples":3,"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":2,"samples":[{"code_sha256_prefix":"a3e27bd1e8b628ed","entry":"Embedding","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a3e27bd1e8b628ed"}},{"code_sha256_prefix":"8cd8cb0d1e9e63e4","entry":"Linear","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"8cd8cb0d1e9e63e4"}},{"code_sha256_prefix":"2a665253ba09b438","entry":"get_form","repo":"Aso-UniMelb/neural-fieldwork-guide","repo_kind":"listed","path":"guide/exp1-2-3_cycle1.py","file_url":"https://github.com/Aso-UniMelb/neural-fieldwork-guide/blob/HEAD/guide/exp1-2-3_cycle1.py","link_basis":"harvester_set","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":"2a665253ba09b438"}},{"code_sha256_prefix":"f316c17c5e70cb0d","entry":"get_form","repo":"Aso-UniMelb/neural-fieldwork-guide","repo_kind":"listed","path":"guide/exp1-2_cycle2-5.py","file_url":"https://github.com/Aso-UniMelb/neural-fieldwork-guide/blob/HEAD/guide/exp1-2_cycle2-5.py","link_basis":"harvester_set","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":"f316c17c5e70cb0d"}},{"code_sha256_prefix":"b08554160cd3bf2c","entry":"main","repo":"Aso-UniMelb/neural-fieldwork-guide","repo_kind":"listed","path":"guide/exp4_cycle1-2.py","file_url":"https://github.com/Aso-UniMelb/neural-fieldwork-guide/blob/HEAD/guide/exp4_cycle1-2.py","link_basis":"harvester_set","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":"b08554160cd3bf2c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}