What Taggers Fail to Learn, Parsers Need the Most
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 7 of its 16 references that are in the map. First posted on arXiv 2 Apr 2021.
Builds on
7 of 16 references.
References · 7
- 2016Enriching Word Vectors with Subword Informationcited by 1,578
- 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
- 2018Learning Word Vectors for 157 Languagescited by 279
- 2015Improved Transition-Based Parsing by Modeling Characters instead of Words with LSTMscited by 10
- 2018An Investigation of the Interactions Between Pre-Trained Word Embeddings, Character Models and POS Tags in Dependency Parsingcited by 10
- 2020Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing?cited by 9
- 2020On the Frailty of Universal POS Tags for Neural UD Parserscited by 4
Built on by
Citing papers per year: 2021: 1; 2022: 0; 2023: 1.
2 papers.