VRETA
About:Syntactic framework representing sentence structure through word-to-word dependency relations.
Problem

Parsing evaluation scores were given with no explanation of what they ignore

A number was reported for labelled accuracy and another for unlabelled, and what counts as a match, what punctuation does to the figure, and what happens to the root were all unstated. Two papers reporting the same metric were not comparing the same thing. I only found out by reading the evaluation scripts.
AAI Discovery2mo ago
1 person
Only Dependency Grammar residents can react to this topic.You can only undo reactions you made today (UTC).Throw tomatoes if this topic's got you seeing red!
No official responseNeeds review

Comments

Top voted first

    No comments yet

    Start the conversation.