Computing Semantic Relatedness Using Wikipedia-based Explicit Semantic Analysis

By Evgeniy Gabrilovich, Shaul Markovitch. 2007

2,388 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.

In Natural Language Processing

Citations in the corpus

Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval (2015, methodology): “, 1990), ESA (Gabrilovich and Markovitch, 2007), PCA (Karhunen, 1998), and non-linear kernel variants (Schölkopf et al.”
Joint Concept Learning and Semantic Parsing from Natural Language Explanations (2017, background): “• ESA: LR model over ESA (Explicit Semantic Analysis) representations of emails (Gabrilovich and Markovitch, 2007), which describe a text in terms of its Wikipedia topics.”
Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach (2019, background): “Regarding this label-fully-unseen evaluation, apart from our entailment models and three unsupervised baselines “Majority”, “Word2Vec” and “ESA”, we also report the following baseline: Wikipedia-based : We train a binary clas-siﬁer based on BERT on a dataset collected from Wikipedia.”
UNAL-NLP: Combining Soft Cardinality Features for Semantic Textual Similarity, Relatedness and Entailment (2014, methodology): “For this set of features we used the idea proposed by Gabrilovich and Markovitch (2007) of enriching the representation of a text by representing each word by its textual deﬁnition in a knowledge base, i.e. explicit semantic analysis (ESA).”
Tapping into knowledge base for concept feedback: leveraging conceptnet to improve search results for difficult queries (2012, background): “An edge between the two nodes represents a semantic relationship between thetwoconcepts.”
Concept-Based Information Retrieval Using Explicit Semantic Analysis (2011, methodology): “…applied to text categorization [Chang et al. 2008; Gabrilovich and Markovitch 2006; Gupta and Ratinov 2008], semantic relatedness calculation [Gabrilovich and Markovitch 2007; Gurevych et al. 2007], cross-language information retrieval [Potthast et al. 2008; Sorg and Cimiano 2008], and…”
An effective, low-cost measure of semantic relatedness obtained from Wikipedia links (2008, background): “Gabrilovich and Markovitch (2007) achieve extremely accurate results with ESA, a technique that is somewhat reminiscent of the vector space model widely used in information retrieval.”
Question Answering Using Enhanced Lexical Semantic Models (2013, methodology): “Among various word similarity models (Agirre et al., 2009; Reisinger and Mooney, 2010; Gabrilovich and Markovitch, 2007; Radinsky et al., 2011), the vector space models (VSMs) based on the idea of distributional similarity (Turney and Pantel, 2010) are often used as the core component.”
A Survey of Text Similarity Approaches (2013, methodology): “CL-ESA exploits a document-aligned multilingual reference collection such as Wikipedia to represent a document as a languageindependent concept vector.”
Local and Global Algorithms for Disambiguation to Wikipedia (2011, background): “, 2008), measuring semantic similarity between texts (Gabrilovich and Markovitch, 2007a), crossdocument co-reference resolution (Finin et al.”
Lump at SemEval-2017 Task 1: Towards an Interlingua Semantic Similarity (2017, methodology): “We compute the similarity between s and t by means of explicit semantic analysis (ESA) (Gabrilovich and Markovitch, 2007).”
From Word to Sense Embeddings: A Survey on Vector Representations of Meaning (2018, methodology): “SaSA follows Explicit Semantic Analysis (Gabrilovich & Markovitch, 2007, ESA) by representing a word using Wikipedia concepts.”
DKPro Similarity: An Open Source Framework for Text Similarity (2013, background): “3 By us-ing the common TextSimilarityMeasure interface, it is easy to replace Greedy String Tiling with any measure of choice, such as Latent Semantic Analysis (Landauer et al., 1998) or Explicit Semantic Analysis (Gabrilovich and Markovitch, 2007).”
Template-based question answering over RDF data (2012, methodology): “Examples for entities which do have a correspondent in the natural language input but are nevertheless hard to match are the following: • inhabitants , the correct property being prop:population or prop:populationTotal (question 9) • owns , the property speciﬁed in the Gold query being onto:keyPerso”
WikiRef: Wikilinks as a route to recommending appropriate references for scientific Wikipedia pages (2018, background): “…linking and disambiguation (Moro et al., 2014; Hachey et al., 2013; Cucerzan, 2007; Hoffart et al., 2011), named entity disambiguation (Cucerzan, 2007; Barrena et al., 2015), semantic similarity (Gabrilovich and Markovitch, 2007; Wu and Giles, 2015), information extraction (Wu and Weld, 2010) etc.”