{"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/unisumm-unified-few-shot-summarization-with","title":"UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization","arxiv_id":"2211.09783","date":"2022-11-17","proceeding":null,"authors":["Yulong Chen","Yang Liu","Ruochen Xu","ZiYi Yang","Chenguang Zhu","Michael Zeng","Yue Zhang"],"abstract":"The high annotation costs and diverse demands of various summarization tasks motivate the development of few-shot summarization. However, despite the emergence of many summarization tasks and datasets, the current training paradigm for few-shot summarization systems ignores potentially shareable knowledge in heterogeneous datasets. To this end, we propose \\textsc{UniSumm}, a unified few-shot summarization model pre-trained with multiple summarization tasks and can be prefix-tuned to excel at any few-shot summarization task. Meanwhile, to better evaluate few-shot summarizers, under the principles of diversity and robustness, we assemble and release a new benchmark \\textsc{SummZoo}. It consists of $8$ summarization tasks with multiple sets of few-shot samples for each task, covering diverse domains. Experimental results and analysis show that \\textsc{UniSumm} outperforms strong baselines by a large margin across all sub-tasks in \\textsc{SummZoo} under both automatic and human evaluations and achieves comparable results in human evaluation compared with a GPT-3.5 model.","url_abs":"https://arxiv.org/abs/2211.09783v6","url_pdf":"https://arxiv.org/pdf/2211.09783v6.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":"unisumm-unified-few-shot-summarization-with","repo_url":"https://github.com/microsoft/unisumm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[{"slug":"summzoo","name":"SummZoo","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.09783","atlas_url":"https://app.syntology.ai/?focus=2211.09783","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}