Alternating Language Modeling for Cross-Lingual Pre-Training
Citations Over TimeTop 10% of 2020 papers
Abstract
Language model pre-training has achieved success in many natural language processing tasks. Existing methods for cross-lingual pre-training adopt Translation Language Model to predict masked words with the concatenation of the source sentence and its target equivalent. In this work, we introduce a novel cross-lingual pre-training method, called Alternating Language Modeling (ALM). It code-switches sentences of different languages rather than simple concatenation, hoping to capture the rich cross-lingual context of words and phrases. More specifically, we randomly substitute source phrases with target translations to create code-switched sentences. Then, we use these code-switched data to train ALM model to learn to predict words of different languages. We evaluate our pre-training ALM on the downstream tasks of machine translation and cross-lingual classification. Experiments show that ALM can outperform the previous pre-training methods on three benchmarks.1
Related Papers
- Korean text-to-speech and concatenation cost function(2006)
- Applications of Virtual Concatenation in Digital Wrapper Technology(2003)
- → A Chinese Text Classification Method With Low Hardware Requirement Based on Improved Model Concatenation(2020)
- → Concatenations of Terms of an Arithmetic Progression(2022)
- → Concatenation-Informer: Pre-Distilling and Concatenation Improve Efficiency and Accuracy(2023)