Mixed-Lingual Pre-training for Cross-lingual Summarization
This addresses the problem of limited labeled data for cross-lingual summarization, offering an incremental improvement for researchers and practitioners in multilingual NLP.
The paper tackled cross-lingual summarization by proposing a mixed-lingual pre-training method that leverages both cross-lingual and monolingual tasks, achieving improvements of 2.82 and 1.15 ROUGE-1 scores over state-of-the-art results on the NCLS dataset.
Cross-lingual Summarization (CLS) aims at producing a summary in the target language for an article in the source language. Traditional solutions employ a two-step approach, i.e. translate then summarize or summarize then translate. Recently, end-to-end models have achieved better results, but these approaches are mostly limited by their dependence on large-scale labeled data. We propose a solution based on mixed-lingual pre-training that leverages both cross-lingual tasks such as translation and monolingual tasks like masked language models. Thus, our model can leverage the massive monolingual data to enhance its modeling of language. Moreover, the architecture has no task-specific components, which saves memory and increases optimization efficiency. We show in experiments that this pre-training scheme can effectively boost the performance of cross-lingual summarization. In Neural Cross-Lingual Summarization (NCLS) dataset, our model achieves an improvement of 2.82 (English to Chinese) and 1.15 (Chinese to English) ROUGE-1 scores over state-of-the-art results.