The Evaluation of Sentence Similarity Measures

253 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.

Representation learning for very short texts using weighted word embedding aggregation (2016, background): “Such an embedding is a distributed vector representation of a single word in a ﬁxed-dimensional semantic space, as opposed to term tf-idf vectors, in which a word is represented by a one-hot vector (Achananuparp et al. (2008); Manning et al. (2009)).”
Defining and Evaluating Fair Natural Language Generation (2020, background): “r et al., 2007). For example, one possible measure is the Jaccard similarity coefﬁcient, which can be deﬁned in the context of text similarity by representing a text as an unordered set of its words (Achananuparp et al., 2008). However, purely lexical measures of similarity often fall short of captu”
Learning Semantic Similarity for Very Short Texts (2015, background): “Tf-idf is an example of a traditional and very popular representation to compare texts, such as news articles, with each other [1], [2].”