On the feasibility of dependency parsing of non-human sequences without a gold standard. Is evaluation possible in other species?
Dependency parsing consists of finding a tree representation for a sequence. Unsupervised dependency parsing aims to develop parsing methods without a gold standard during model training. In human languages, an unsupervised parser can be evaluated because some gold standard is usually available or can be created. For other species, a gold standard is unknown. Thus one may conclude that it is impossible to determine the accuracy of an unsupervised parser and, consequently, dependency parsing is unfeasible in other species. However, here we apply recent advances in network science to demonstrate
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 50%stanfordnlp/stanza →
- PossiblePossibly related (embedding) · 49%chrisliu298/awesome-llm-unlearning →
- LinkedLinked via arxiv author · 85%Ramon Ferrer-i-Cancho →
“On the feasibility of dependency parsing of non-human sequences without a gold standard. Is evaluation possible in other”
- LinkedLinked via arxiv author · 85%Catherine Hobaiter →
“On the feasibility of dependency parsing of non-human sequences without a gold standard. Is evaluation possible in other”
- LinkedLinked via arxiv author · 85%Thore Bergman →
“On the feasibility of dependency parsing of non-human sequences without a gold standard. Is evaluation possible in other”
- LinkedLinked via arxiv author · 85%Morgan Gustison →
“On the feasibility of dependency parsing of non-human sequences without a gold standard. Is evaluation possible in other”