{"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/compositional-generalisation-with-structured","title":"Compositional Generalisation with Structured Reordering and Fertility Layers","arxiv_id":"2210.03183","date":"2022-10-06","proceeding":null,"authors":["Matthias Lindemann","Alexander Koller","Ivan Titov"],"abstract":"Seq2seq models have been shown to struggle with compositional generalisation, i.e. generalising to new and potentially more complex structures than seen during training. Taking inspiration from grammar-based models that excel at compositional generalisation, we present a flexible end-to-end differentiable neural model that composes two structural operations: a fertility step, which we introduce in this work, and a reordering step based on previous work (Wang et al., 2021). To ensure differentiability, we use the expected value of each step. Our model outperforms seq2seq models by a wide margin on challenging compositional splits of realistic semantic parsing tasks that require generalisation to longer examples. It also compares favourably to other models targeting compositional generalisation.","url_abs":"https://arxiv.org/abs/2210.03183v2","url_pdf":"https://arxiv.org/pdf/2210.03183v2.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":"compositional-generalisation-with-structured","repo_url":"https://github.com/namednil/f-then-r","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.03183","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}