LCP-dropout: Compression-based Multiple Subword Segmentation for Neural Machine Translation
This addresses a preprocessing bottleneck for Neural Machine Translation researchers, offering an incremental improvement over existing compression-based methods.
The paper tackles the difficulty of generating multiple segmentations in compression-based subword segmentation for Neural Machine Translation by proposing LCP-dropout, which improves upon BPE/BPE-dropout and outperforms various baselines, especially with small training data.
In this study, we propose a simple and effective preprocessing method for subword segmentation based on a data compression algorithm. Compression-based subword segmentation has recently attracted significant attention as a preprocessing method for training data in Neural Machine Translation. Among them, BPE/BPE-dropout is one of the fastest and most effective method compared to conventional approaches. However, compression-based approach has a drawback in that generating multiple segmentations is difficult due to the determinism. To overcome this difficulty, we focus on a probabilistic string algorithm, called locally-consistent parsing (LCP), that has been applied to achieve optimum compression. Employing the probabilistic mechanism of LCP, we propose LCP-dropout for multiple subword segmentation that improves BPE/BPE-dropout, and show that it outperforms various baselines in learning from especially small training data.