The recent success of statistical parsing methods has made treebanks become important resources for building good parsers. However, constructing highquality annotated treebanks is a challenging task. We utilized two publicly available parsers, Berkeley and MST parsers, for feedback on improving the quality of part-of-speech tagging for the Vietnamese Treebank. Analysis of the treebank and parsing errors revealed how problems with the Vietnamese Treebank influenced the parsing results and real difficulties of Vietnamese parsing that required further improvements to existing parsing technologies. 1