A Variational Hierarchical Model for Neural Cross-Lingual Summarization

Anonymous

Abstract: The goal of the cross-lingual summarization (CLS) is to convert a document in one language (e.g., English) to a summary in another one (e.g., Chinese), which is essentially the combination of machine translation (MT) and monolingual summarization (MS). Existing studies on CLS mainly focus on utilizing pipeline methods or jointly training an end-to-end model through an auxiliary MT or MS objective. However, it is very challenging for the model to directly conduct CLS as it requires both the abilities to translate and summarize. Besides, the processes of MT and MS have a hierarchical relationship with CLS. Therefore, we propose a hierarchical model for the CLS task, based on the conditional variational auto-encoder. The hierarchical model contains two kinds of latent variables at the local and global levels, respectively. At the local level, there are two latent variables, one for translation and the other for summarization. As for the global level, there is another latent variable for cross-lingual summarization conditioned on the two local-level variables. Experiments on two language directions (English-Chinese) verify the effectiveness and superiority of the proposed approach, yielding state-of-the-art performances. In addition, we show that our model is able to generate better cross-lingual summaries than comparison models in the few-shot setting.