{"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/learning-to-recombine-and-resample-data-for-1","title":"Learning to Recombine and Resample Data for Compositional Generalization","arxiv_id":"2010.03706","date":"2020-10-08","proceeding":"ICLR 2021 1","authors":["Ekin Akyürek","Afra Feyza Akyürek","Jacob Andreas"],"abstract":"Flexible neural sequence models outperform grammar- and automaton-based counterparts on a variety of tasks. However, neural models perform poorly in settings requiring compositional generalization beyond the training data -- particularly to rare or unseen subsequences. Past work has found symbolic scaffolding (e.g. grammars or automata) essential in these settings. We describe R&R, a learned data augmentation scheme that enables a large category of compositional generalizations without appeal to latent symbolic structure. R&R has two components: recombination of original training examples via a prototype-based generative model and resampling of generated examples to encourage extrapolation. Training an ordinary neural sequence model on a dataset augmented with recombined and resampled examples significantly improves generalization in two language processing problems -- instruction following (SCAN) and morphological analysis (SIGMORPHON 2018) -- where R&R enables learning of new constructions and tenses from as few as eight initial examples.","url_abs":"https://arxiv.org/abs/2010.03706v6","url_pdf":"https://arxiv.org/pdf/2010.03706v6.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":"learning-to-recombine-and-resample-data-for-1","repo_url":"https://github.com/ekinakyurek/compgen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"morphological-analysis","task_name":"Morphological Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.03706","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}