{"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/copy-that-editing-sequences-by-copying-spans-1","title":"Copy that! Editing Sequences by Copying Spans","arxiv_id":"2006.04771","date":"2020-06-08","proceeding":null,"authors":["Sheena Panthaplackel","Miltiadis Allamanis","Marc Brockschmidt"],"abstract":"Neural sequence-to-sequence models are finding increasing use in editing of documents, for example in correcting a text document or repairing source code. In this paper, we argue that common seq2seq models (with a facility to copy single tokens) are not a natural fit for such tasks, as they have to explicitly copy each unchanged token. We present an extension of seq2seq models capable of copying entire spans of the input to the output in one step, greatly reducing the number of decisions required during inference. This extension means that there are now many ways of generating the same output, which we handle by deriving a new objective for training and a variation of beam search for inference that explicitly handles this problem. In our experiments on a range of editing tasks of natural language and source code, we show that our new model consistently outperforms simpler baselines.","url_abs":"https://arxiv.org/abs/2006.04771v2","url_pdf":"https://arxiv.org/pdf/2006.04771v2.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":"copy-that-editing-sequences-by-copying-spans-1","repo_url":"https://github.com/microsoft/aaai21-copy-that","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.04771","atlas_url":"https://app.syntology.ai/?focus=2006.04771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04771"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/microsoft/aaai21-copy-that","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"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":0,"samples":[{"code_sha256_prefix":"912f05720e2aef3a","entry":"compute_bleu","repo":"microsoft/aaai21-copy-that","repo_kind":"official","path":"model/testencdec.py","file_url":"https://github.com/microsoft/aaai21-copy-that/blob/HEAD/model/testencdec.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":"912f05720e2aef3a"}},{"code_sha256_prefix":"0bde2258f9638e6c","entry":"get_token_types","repo":"microsoft/aaai21-copy-that","repo_kind":"official","path":"model/testencdec.py","file_url":"https://github.com/microsoft/aaai21-copy-that/blob/HEAD/model/testencdec.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":"0bde2258f9638e6c"}},{"code_sha256_prefix":"b05b10e0e86b1bcb","entry":"is_num_literal","repo":"microsoft/aaai21-copy-that","repo_kind":"official","path":"model/testencdec.py","file_url":"https://github.com/microsoft/aaai21-copy-that/blob/HEAD/model/testencdec.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":"b05b10e0e86b1bcb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}