{"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/imitation-learning-for-neural-morphological","title":"Imitation Learning for Neural Morphological String Transduction","arxiv_id":"1808.10701","date":"2018-08-31","proceeding":"EMNLP 2018 10","authors":["Peter Makarov","Simon Clematide"],"abstract":"We employ imitation learning to train a neural transition-based string\ntransducer for morphological tasks such as inflection generation and\nlemmatization. Previous approaches to training this type of model either rely\non an external character aligner for the production of gold action sequences,\nwhich results in a suboptimal model due to the unwarranted dependence on a\nsingle gold action sequence despite spurious ambiguity, or require warm\nstarting with an MLE model. Our approach only requires a simple expert policy,\neliminating the need for a character aligner or warm start. It also addresses\nfamiliar MLE training biases and leads to strong and state-of-the-art\nperformance on several benchmarks.","url_abs":"http://arxiv.org/abs/1808.10701v1","url_pdf":"http://arxiv.org/pdf/1808.10701v1.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":"imitation-learning-for-neural-morphological","repo_url":"https://github.com/ZurichNLP/emnlp2018-imitation-learning-for-neural-morphology","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"lemmatization","task_name":"Lemmatization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.10701","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}