An Information-Theoretic Definition of Similarity

By Dekang Lin. 1998

How researchers see this paper

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

In Information Theory

Citations in the corpus

From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions (2014, background): “lexical similarities of words, either via the cosine of the angle between them, or via other, more complex metrics (Lin, 1998).”
Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics (2013, positive): “We consider three different kinds of lexical similarities: the WordNet-based Lin similarity (Lin, 1998) (σ Lin ), a distributional similarity metric (σ D ), and a novel alignment-based Framing Image Description as a Ranking Task similarity metric (σ A ), which takes advantage of the fact that each…”
Parsing Algebraic Word Problems into Equations (2015, methodology): “These include binary features like whether one Qset’s container property matches the other Qset’s entity (a strong indicator of multiplication), or the distance between the verbs associated with each set based upon their Lin Similarity.”
Learning to Solve Arithmetic Word Problems with Verb Categorization (2014, methodology): “We compute the similarity between two senses using linear similarity (Lin, 1998).”
SemEval-2014 Task 10: Multilingual Semantic Textual Similarity (2014, methodology): “…classifier uses a combination of features, such as those derived from traditional knowledge-based ((Leacock and Chodorow, 1998; Wu and Palmer, 1994; Lin, 1998), and others) and corpus-based metrics (LSA (Landauer et al., 1997)), paired with lexical features (such as Dice-Similarity,…”
GOATOOLS: A Python library for Gene Ontology analyses (2018, methodology): “The DAG data structure allows traversal of terms along the hierarchy for tasks such as determination of level or depth, retrieval of parent or child terms, and calculation of semantic similarities (e.g. Resnik’s score 13 and Lin’s score 14 ) between terms.”
SemEval-2016 Task 1: Semantic Textual Similarity, Monolingual and Cross-Lingual Evaluation (2016, methodology): “Surface Lexical Similarity Our surface form selection heuristic uses an information theoretic measure based on unigram overlap (Lin, 1998).”
Evaluation of output embeddings for fine-grained image classification (2014, methodology): “In this case, the distance between nodes is measured using semantic similarity metrics [24, 30, 32, 44].”
Towards a theory of semantic communication (2011, methodology): “Some promising candidates include Lin’s similarity measure [40] and Normalized Compression Distance [58].”
Outlier Analysis (2013, background): “Other measures which uses functions of both matches and mismatches on different attribute values are proposed in [42, 303, 411].”
Link Prediction in Complex Networks: A Survey (2010, background): “The algorithms’ performance can be effectively enhanced by considering some external information, like the attributes of nodes [35].”
Learning to map between ontologies on the semantic web (2002, background): “In [ 19 ] the authors propose an information-theoretic notion of similarity that is based on the joint distribution.”
Analysis of multiplex gene expression maps obtained by voxelation (2008, unknown): “Lin method [16] is used to calculate function distance, i.”
ITNLP-AiKF at SemEval-2017 Task 1: Rich Features Based SVR for Semantic Textual Similarity Computing (2017, background): “Lin similarity (Lin, 1998) considers the similarity depending on the commonality and differences of the information contained in the different meaning concepts.”
Measuring the Semantic Similarity of Texts (2005, methodology): “The next measure we use in our experiments is the metric introduced by Lin (Lin, 1998), which builds on Resnik’s measure of similarity, and adds a normalization factor consisting of the information content of the two input concepts:”
Explanations of recommendations (2007, unknown): “We compared human judgements of similarity with Lin’s taxonomybased measure [12] and the WASP measure that uses annotated corpus data [11].”