A Falta de Pan, Buenas Son Tortas: The Efficacy of Predicted UPOS Tags for Low Resource UD Parsing
This work addresses parsing challenges for low-resource languages, but it is incremental as it builds on existing methods.
The study investigated the impact of predicted UPOS tags on dependency parsing performance in low-resource settings, finding that they are somewhat helpful, especially with fewer annotated trees, but this benefit diminishes as data increases.
We evaluate the efficacy of predicted UPOS tags as input features for dependency parsers in lower resource settings to evaluate how treebank size affects the impact tagging accuracy has on parsing performance. We do this for real low resource universal dependency treebanks, artificially low resource data with varying treebank sizes, and for very small treebanks with varying amounts of augmented data. We find that predicted UPOS tags are somewhat helpful for low resource treebanks, especially when fewer fully-annotated trees are available. We also find that this positive impact diminishes as the amount of data increases.