English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The usefulness of part-of-speech tags for parsing has been heavily questioneddue to the success of word-contextualized parsers. Yet, most studies arelimited to coarse-grained tags and high quality written content; while we knowlittle about their influence when it comes to models in production that facelexical errors. We expand these setups and design an adversarial attack toverify if the use of morphological information by parsers: (i) contributes toerror propagation or (ii) if on the other hand it can play a role to correctmistakes that word-only neural parsers make. The results on 14 diverse UDtreebanks show that under such attacks, for transition- and graph-based modelstheir use contributes to degrade the performance even faster, while for the(lower-performing) sequence labeling parsers they are helpful. We also showthat if morphological tags were utopically robust against lexicalperturbations, they would be able to correct parsing mistakes.

Another Dead End for Morphological Tags? Perturbed Inputs and Parsing