{"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/sumtra-a-differentiable-pipeline-for-few-shot","title":"SumTra: A Differentiable Pipeline for Few-Shot Cross-Lingual Summarization","arxiv_id":"2403.13240","date":"2024-03-20","proceeding":null,"authors":["Jacob Parnell","Inigo Jauregi Unanue","Massimo Piccardi"],"abstract":"Cross-lingual summarization (XLS) generates summaries in a language different from that of the input documents (e.g., English to Spanish), allowing speakers of the target language to gain a concise view of their content. In the present day, the predominant approach to this task is to take a performing, pretrained multilingual language model (LM) and fine-tune it for XLS on the language pairs of interest. However, the scarcity of fine-tuning samples makes this approach challenging in some cases. For this reason, in this paper we propose revisiting the summarize-and-translate pipeline, where the summarization and translation tasks are performed in a sequence. This approach allows reusing the many, publicly-available resources for monolingual summarization and translation, obtaining a very competitive zero-shot performance. In addition, the proposed pipeline is completely differentiable end-to-end, allowing it to take advantage of few-shot fine-tuning, where available. Experiments over two contemporary and widely adopted XLS datasets (CrossSum and WikiLingua) have shown the remarkable zero-shot performance of the proposed approach, and also its strong few-shot performance compared to an equivalent multilingual LM baseline, that the proposed approach has been able to outperform in many languages with only 10% of the fine-tuning samples.","url_abs":"https://arxiv.org/abs/2403.13240v1","url_pdf":"https://arxiv.org/pdf/2403.13240v1.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":"sumtra-a-differentiable-pipeline-for-few-shot","repo_url":"https://github.com/jacob-parnell-rozetta/sumtra","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.13240","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}