An empirical study for Vietnamese dependency parsing
It addresses dependency parsing for Vietnamese, a language with specific challenges, but is incremental as it applies existing neural methods to this domain.
This paper tackled the problem of dependency parsing for Vietnamese, which has unique linguistic features like copula drop and verb serialization, and found that neural network-based parsers significantly outperform traditional parsers, achieving state-of-the-art labeled attachment score (LAS) of 73.53% and unlabeled attachment score (UAS) of 80.66%.
This paper presents an empirical comparison of different dependency parsers for Vietnamese, which has some unusual characteristics such as copula drop and verb serialization. Experimental results show that the neural network-based parsers perform significantly better than the traditional parsers. We report the highest parsing scores published to date for Vietnamese with the labeled attachment score (LAS) at 73.53% and the unlabeled attachment score (UAS) at 80.66%.