What Taggers Fail to Learn, Parsers Need the Most
This work addresses a bottleneck in NLP by explaining the minimal impact of predicted tags on parsing, which is incremental as it builds on existing error analysis methods.
The paper analyzes why neural dependency parsers benefit from gold standard UPOS tags but not from predicted tags, finding that taggers' errors in certain contexts limit their utility for parsing.
We present an error analysis of neural UPOS taggers to evaluate why using gold standard tags has such a large positive contribution to parsing performance while using predicted UPOS tags either harms performance or offers a negligible improvement. We evaluate what neural dependency parsers implicitly learn about word types and how this relates to the errors taggers make to explain the minimal impact using predicted tags has on parsers. We also present a short analysis on what contexts result in reductions in tagging performance. We then mask UPOS tags based on errors made by taggers to tease away the contribution of UPOS tags which taggers succeed and fail to classify correctly and the impact of tagging errors.