The contradiction relation is more useful than the neutral relation for measuring semantic diversity

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• What is the role of neutral NLI predictions in measuring semantic diversity?question0.798
  Motivates the creation of Neutral NLI Diversity as an ablation
• # Neutral shows weak correlation with diversity (ρ=0.05 decTest, ρ=-0.08 conTest)finding0.781
  Ablation result showing neutrals are not strong indicators of diversity
• # Contradiction is positively correlated with diversity (ρ=0.26 decTest, ρ=0.46 conTest)finding0.771
  Ablation result confirming that contradiction predictions indicate diversity
• Neutral NLI predictions may capture lexical rather than semantic diversityhypothesis0.771
  Hypothesis proposed to explain Neutral NLI Diversity's high performance on decTest but low on conTest
• Confidence NLI Diversity achieves state-of-the-art performance on measuring semantic diversityclaim0.770
  Main performance claim of the paper
• Diversity Threshold Generation increases semantic diversity with minimal loss in relevancyclaim0.761
  Central practical claim about the DTG procedure
• Larger numbers of entailment predictions indicate lack of diversity; larger numbers of contradiction predictions indicate higher diversityhypothesis0.758
  Design hypothesis for NLI scoring weights in Baseline NLI Diversity
• A concept should not attempt to serve two distinct purposes; this leads to conflicts and confusion.claim0.752
  No overloading criterion.