Mixed-Lingual Pre-training for Cross-lingual Summarization
arXiv:2010.08892
Abstract
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.
arXiv commentAccepted at Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) 2020
References in corpus (10)
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Cross-lingual Language Model Pretraining
- The Curious Case of Neural Text Degeneration
- Unified Language Model Pre-training for Natural Language Understanding and Generation
- Multilingual Denoising Pre-training for Neural Machine Translation
- SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering
- Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks
- TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and Denoising
- Leveraging Lead Bias for Zero-shot Abstractive News Summarization
- NCLS: Neural Cross-Lingual Summarization