SumTra: A Differentiable Pipeline for Few-Shot Cross-Lingual Summarization

arXiv:2403.13240v1 Announce Type: new
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 …

abstract arxiv cross-lingual cs.cl differentiable documents english few-shot language pipeline spanish speakers summarization type view