{"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/exact-hard-monotonic-attention-for-character","title":"Exact Hard Monotonic Attention for Character-Level Transduction","arxiv_id":"1905.06319","date":"2019-05-15","proceeding":"ACL 2019 7","authors":["Shijie Wu","Ryan Cotterell"],"abstract":"Many common character-level, string-to string transduction tasks, e.g., grapheme-tophoneme conversion and morphological inflection, consist almost exclusively of monotonic transductions. However, neural sequence-to sequence models that use non-monotonic soft attention often outperform popular monotonic models. In this work, we ask the following question: Is monotonicity really a helpful inductive bias for these tasks? We develop a hard attention sequence-to-sequence model that enforces strict monotonicity and learns a latent alignment jointly while learning to transduce. With the help of dynamic programming, we are able to compute the exact marginalization over all monotonic alignments. Our models achieve state-of-the-art performance on morphological inflection. Furthermore, we find strong performance on two other character-level transduction tasks. Code is available at https://github.com/shijie-wu/neural-transducer.","url_abs":"https://arxiv.org/abs/1905.06319v3","url_pdf":"https://arxiv.org/pdf/1905.06319v3.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":"exact-hard-monotonic-attention-for-character","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":"exact-hard-monotonic-attention-for-character","repo_url":"https://github.com/AssafSinger94/sigmorphon-2020-inflection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"hard-attention","task_name":"Hard Attention"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"morphological-inflection","task_name":"Morphological Inflection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1905.06319","atlas_url":"https://app.syntology.ai/?focus=1905.06319","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}