{"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/a-simple-and-effective-approach-to-automatic","title":"A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning","arxiv_id":"1906.06253","date":"2019-06-14","proceeding":null,"authors":["Gonçalo M. Correia","André F. T. Martins"],"abstract":"Automatic post-editing (APE) seeks to automatically refine the output of a black-box machine translation (MT) system through human post-edits. APE systems are usually trained by complementing human post-edited data with large, artificial data generated through back-translations, a time-consuming process often no easier than training an MT system from scratch. In this paper, we propose an alternative where we fine-tune pre-trained BERT models on both the encoder and decoder of an APE system, exploring several parameter sharing strategies. By only training on a dataset of 23K sentences for 3 hours on a single GPU, we obtain results that are competitive with systems that were trained on 5M artificial sentences. When we add this artificial data, our method obtains state-of-the-art results.","url_abs":"https://arxiv.org/abs/1906.06253v1","url_pdf":"https://arxiv.org/pdf/1906.06253v1.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":"a-simple-and-effective-approach-to-automatic","repo_url":"https://github.com/deep-spin/OpenNMT-APE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"automatic-post-editing","task_name":"Automatic Post-Editing"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.06253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.06253"}},"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/deep-spin/OpenNMT-APE","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":"0c93830510f645a3","entry":"check_sru_requirement","repo":"deep-spin/OpenNMT-APE","repo_kind":"official","path":"onmt/models/sru.py","file_url":"https://github.com/deep-spin/OpenNMT-APE/blob/HEAD/onmt/models/sru.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c93830510f645a3"}},{"code_sha256_prefix":"0c8cfd6442c243f1","entry":"count_features","repo":"deep-spin/OpenNMT-APE","repo_kind":"official","path":"preprocess.py","file_url":"https://github.com/deep-spin/OpenNMT-APE/blob/HEAD/preprocess.py","link_basis":"harvester_set","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":"0c8cfd6442c243f1"}},{"code_sha256_prefix":"83253c9435403627","entry":"collapse_copy_scores","repo":"deep-spin/OpenNMT-APE","repo_kind":"official","path":"onmt/modules/copy_generator.py","file_url":"https://github.com/deep-spin/OpenNMT-APE/blob/HEAD/onmt/modules/copy_generator.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":"83253c9435403627"}},{"code_sha256_prefix":"0c3bddd7d3eaba02","entry":"seq_linear","repo":"deep-spin/OpenNMT-APE","repo_kind":"official","path":"onmt/modules/conv_multi_step_attention.py","file_url":"https://github.com/deep-spin/OpenNMT-APE/blob/HEAD/onmt/modules/conv_multi_step_attention.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":"0c3bddd7d3eaba02"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}