Transformer‐based reranking for improving Korean morphological analysis systems

Abstract

This study introduces a new approach in Korean morphological analysis combining dictionary‐based techniques with Transformer‐based deep learning models. The key innovation is the use of a BERT‐based reranking system, significantly enhancing the accuracy of traditional morphological analysis. The method generates multiple suboptimal paths, then employs BERT models for reranking, leveraging their advanced language comprehension. Results show remarkable performance improvements, with the first‐stage reranking achieving over 20% improvement in error reduction rate compared with existing models. The second stage, using another BERT variant, further increases this improvement to over 30%. This indicates a significant leap in accuracy, validating the effectiveness of merging dictionary‐based analysis with contemporary deep learning. The study suggests future exploration in refined integrations of dictionary and deep learning methods as well as using probabilistic models for enhanced morphological analysis. This hybrid approach sets a new benchmark in the field and offers insights for similar challenges in language processing applications.

Special issue on speech and language AI technologies

“…While deep learning approaches are of keen interest, combining and applying them to traditional language analysis is also worthy, especially to explain analysis outcomes. The fifth paper in this special issue [5], "Transformer-Based Reranking for Improving Korean Morphological Analysis Systems" by Ryu and others, introduces this approach to Korean morphological analysis by combining dictionary-based techniques with transformer-based deep learning models. In particular, they use the BERT-based reranking system that substantially enhances the accuracy of the traditional dictionarybased morphological analysis methods.…”