{"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/an-operation-sequence-model-for-explainable","title":"An Operation Sequence Model for Explainable Neural Machine Translation","arxiv_id":"1808.09688","date":"2018-08-29","proceeding":"WS 2018 11","authors":["Felix Stahlberg","Danielle Saunders","Bill Byrne"],"abstract":"We propose to achieve explainable neural machine translation (NMT) by\nchanging the output representation to explain itself. We present a novel\napproach to NMT which generates the target sentence by monotonically walking\nthrough the source sentence. Word reordering is modeled by operations which\nallow setting markers in the target sentence and move a target-side write head\nbetween those markers. In contrast to many modern neural models, our system\nemits explicit word alignment information which is often crucial to practical\nmachine translation as it improves explainability. Our technique can outperform\na plain text system in terms of BLEU score under the recent Transformer\narchitecture on Japanese-English and Portuguese-English, and is within 0.5 BLEU\ndifference on Spanish-English.","url_abs":"http://arxiv.org/abs/1808.09688v1","url_pdf":"http://arxiv.org/pdf/1808.09688v1.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":"an-operation-sequence-model-for-explainable","repo_url":"https://github.com/fstahlberg/ucam-scripts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-alignment","task_name":"Word Alignment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.09688","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}