{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/a-multilayer-convolutional-encoder-decoder","title":"A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction","arxiv_id":"1801.08831","date":"2018-01-26","proceeding":null,"authors":["Shamil Chollampatt","Hwee Tou Ng"],"abstract":"We improve automatic correction of grammatical, orthographic, and collocation\nerrors in text using a multilayer convolutional encoder-decoder neural network.\nThe network is initialized with embeddings that make use of character N-gram\ninformation to better suit this task. When evaluated on common benchmark test\ndata sets (CoNLL-2014 and JFLEG), our model substantially outperforms all prior\nneural approaches on this task as well as strong statistical machine\ntranslation-based systems with neural and task-specific features trained on the\nsame data. Our analysis shows the superiority of convolutional neural networks\nover recurrent neural networks such as long short-term memory (LSTM) networks\nin capturing the local context via attention, and thereby improving the\ncoverage in correcting grammatical errors. By ensembling multiple models, and\nincorporating an N-gram language model and edit features via rescoring, our\nnovel method becomes the first neural approach to outperform the current\nstate-of-the-art statistical machine translation-based approach, both in terms\nof grammaticality and fluency.","url_abs":"http://arxiv.org/abs/1801.08831v1","url_pdf":"http://arxiv.org/pdf/1801.08831v1.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-multilayer-convolutional-encoder-decoder","repo_url":"https://github.com/nusnlp/mlconvgec2018","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"a-multilayer-convolutional-encoder-decoder","repo_url":"https://github.com/seaweiqing/image2story","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"a-multilayer-convolutional-encoder-decoder","repo_url":"https://github.com/seaweiqing/neuraltalk_plus_charcnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"grammatical-error-correction","task_name":"Grammatical Error Correction"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/grammatical-error-correction-on-conll-2014","task":"Grammatical Error Correction","dataset":"CoNLL-2014 Shared Task","model":"CNN Seq2Seq","rank_in_archive_order":23,"of":23,"metrics":{"F0.5":"54.79"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-correction-on-conll-2014-1","task":"Grammatical Error Correction","dataset":"CoNLL-2014 Shared Task (10 annotations)","model":"CNN Seq2Seq","rank_in_archive_order":3,"of":3,"metrics":{"F0.5":"70.14"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-correction-on-jfleg","task":"Grammatical Error Correction","dataset":"JFLEG","model":"CNN Seq2Seq","rank_in_archive_order":6,"of":6,"metrics":{"GLEU":"57.47"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-correction-on-restricted","task":"Grammatical Error Correction","dataset":"Restricted","model":"CNN Seq2Seq","rank_in_archive_order":1,"of":4,"metrics":{"F0.5":"70.14 (measured by Ge et al., 2018)"},"uses_additional_data":false},{"leaderboard":"/sota/grammatical-error-correction-on-_restricted_","task":"Grammatical Error Correction","dataset":"_Restricted_","model":"CNN Seq2Seq","rank_in_archive_order":2,"of":2,"metrics":{"GLEU":"57.47"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.08831","atlas_url":"https://app.syntology.ai/?focus=1801.08831","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1801.08831"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1801.08831\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1801.08831"},"call":"get_concepts_for_paper(arxiv_id=\"1801.08831\")"}],"by_repo":[{"repo":"nusnlp/mlconvgec2018","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"seaweiqing/image2story","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"seaweiqing/neuraltalk_plus_charcnn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f43291c1b99e36f90149fa89156dcd1f5a2490626cb1e64be2af33b75ebb7969","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}