$μ$PLAN: Summarizing using a Content Plan as Cross-Lingual Bridge
This addresses the problem of disseminating content across languages for speakers of different languages, representing a novel method for a known bottleneck in cross-lingual summarization.
The paper tackles cross-lingual summarization by introducing μPLAN, which uses an intermediate content plan as a bridge to generate summaries in a different language from the input, achieving state-of-the-art performance in informativeness and faithfulness on the XWikis dataset across four language pairs and improving zero-shot transfer to new language pairs.
Cross-lingual summarization consists of generating a summary in one language given an input document in a different language, allowing for the dissemination of relevant content across speakers of other languages. The task is challenging mainly due to the paucity of cross-lingual datasets and the compounded difficulty of summarizing and translating. This work presents $μ$PLAN, an approach to cross-lingual summarization that uses an intermediate planning step as a cross-lingual bridge. We formulate the plan as a sequence of entities capturing the summary's content and the order in which it should be communicated. Importantly, our plans abstract from surface form: using a multilingual knowledge base, we align entities to their canonical designation across languages and generate the summary conditioned on this cross-lingual bridge and the input. Automatic and human evaluation on the XWikis dataset (across four language pairs) demonstrates that our planning objective achieves state-of-the-art performance in terms of informativeness and faithfulness. Moreover, $μ$PLAN models improve the zero-shot transfer to new cross-lingual language pairs compared to baselines without a planning component.