N-Gram Similarity and Distance

357 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate (2023, methodology): “Automatic evaluation metrics based on n-grams, such as Rouge (Lin, 2004), BLEU (Papineni et al., 2002), and METEOR (Baner-jee & Lavie, 2005), have been proposed to tackle this issue (Kondrak, 2005).”
Robust named entity disambiguation with random walks (2018, methodology): “Thus we use four features, all of which are familiar in this research area: prior probability, context similarity, semantic relatedness, and name similarity which is measured by the NGram distance [18] between a mention and the canonical name of the entity.”
Accurate and Efficient Refactoring Detection in Commit History (2018, methodology): “The bigram similarity [49] (used by ChangeDistiller [23]) between statements D and 5 is equal to 0.3.”
Learning to Diagnose: Assimilating Clinical Narratives using Deep Reinforcement Learning (2017, background): “…distance, weighted Levenshtein distance, longest common subsequence, metric longest common subsequence (Bakkelund, 2009), N-gram similarity (Kondrak, 2005), optimal string alignment, Q-gram distance (Ukkonen, 1992), Sorensen-Dice coefﬁcient, and the relevance score returned from…”