Corpus-based and Knowledge-based Measures of Text Semantic Similarity

By Rada Mihalcea, Courtney Corley, Carlo Strapparava. AAAI Conference on Artificial Intelligence, 2006

1,431 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/6633814eb1e066d146bdae16d0c1c8344c60778c

How researchers see this paper

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

Citations in the corpus

Learning to Grade Short Answer Questions using Semantic Similarity Measures and Dependency Graph Alignments (2011, methodology): “Following Mihalcea et al. (2006) and Mohler and Mihalcea (2009), we use eight knowledgebased measures of semantic similarity: shortest path [PATH], Leacock & Chodorow (1998) [LCH], Lesk (1986), Wu & Palmer(1994) [WUP], Resnik (1995) [RES], Lin (1998), Jiang & Conrath (1997) [JCN], Hirst & St. Onge…”
DKPro Similarity: An Open Source Framework for Text Similarity (2013, methodology): “The aggregation for the complete texts can for example be done using the strategy by Mihalcea et al. (2006).”
BIT at SemEval-2017 Task 1: Using Semantic Information Space to Evaluate Semantic Textual Similarity (2017, background): “Generally, STS systems could be divided into two categories: One kind is unsupervised systems (Li et al., 2006; Mihalcea et al., 2006; Is-lam and Inkpen, 2008; Han et al., 2013; Sultan et al., 2014b; Wu and Huang, 2016), some of which are appeared for a long time when there wasn’t enough training…”
DLS@CU: Sentence Similarity from Word Alignment and Semantic Vector Composition (2015, background): “Early work on sentence similarity (Corley and Mi-halcea, 2005; Mihalcea et al., 2006; Li et al., 2006; Islam and Inkpen, 2008) established the basic procedural framework under which most modern algorithms operate: computing sentence similarity as a mean of word similarities across the two input…”
ITNLP-AiKF at SemEval-2017 Task 1: Rich Features Based SVR for Semantic Textual Similarity Computing (2017, methodology): “Text similarity measures (Mihalcea et al., 2006) two sentences similarity uses the following formula as Eq 11: IDF W2V similarity and Freq W2V similarity represent sentence vector with word embedding, word frequency and word tf-idf.”
From Word Embeddings to Document Similarities for Improved Information Retrieval in Software Engineering (2016, background): “Finally, the symmetric similarity sim(T, S) between two bagsof-words T and S is defined in [28] as the sum of the two asymmetric similarities:”
Recursive deep learning for natural language processing and computer vision (2014, methodology): “Several approaches overcome this problem by using Wordnet- and corpus-based semantic similarity measures (Mihalcea et al., 2006; Islam and Inkpen, 2007).”
Discriminative Improvements to Distributional Sentence Similarity (2013, methodology): “This can be accomplished by factoring a matrix or tensor of term-context counts (Turney and Pan-tel, 2010); proximity in the induced latent space has been shown to correlate with semantic similarity (Mihalcea et al., 2006).”
Modelling input texts: from Tree Kernels to Deep Learning (2015, methodology): “[86] is applied to scale the measure from pairs of words to sentences.”
UKP: Computing Semantic Textual Similarity by Combining Multiple Content Similarity Measures (2012, methodology): “In order to scale the resulting pairwise word similarities to the text level, we applied the aggregation strategy by Mihalcea et al. (2006): The sum of the idf -weighted similarity scores of each word with the best-matching counterpart in the other text is computed in both directions, then averaged.”
Syntactic/Semantic Structures for Textual Entailment Recognition (2010, background): “In other words, the LSA similarity is computed in a lower dimensional space, in which second-order relations among words and documents are exploited (Mihalcea et al., 2006).”
A Comparison of Vector-based Representations for Semantic Composition (2012, methodology): “Several approaches used WordNet in conjunction with distributional similarity in an attempt to detect meaning conveyed by synonymous words (Islam and Inkpen, 2007; Mihalcea et al., 2006; Fernando and Stevenson, 2008).”
A Survey of Text Similarity Approaches (2013, methodology): “Eight semantic similarity measures were tested in [26].”
Structured Lexical Similarity via Convolution Kernels on Dependency Trees (2011, background): “Given two text fragments d 1 and d 2 ∈ D (the text fragment set), a general lexical kernel (Basili et al., 2005) deﬁnes their similarity as: where ω 1 and ω 2 are the weights of the words (features) w 1 and w 2 in the documents d 1 and d 2 , respectively, and σ is a term similarity function, e.g. (P”
Using Summarization to Discover Argument Facets in Online Idealogical Dialog (2017, methodology): “Facet induction is more similar to work on STS (Mihalcea et al., 2006; Yeh et al., 2009; Agirre et al., 2012; Han et al., 2013; Jurgens et al., 2014).”
Content-based visual search learned from social media (2012, methodology): “To address the issue, we adopt a similarity measure intended for two short text snippets [83], and derive our semantic-based relevance estimator as”
Wikipedia-based Semantic Interpretation for Natural Language Processing (2009, background): “The above-mentioned based techniques are inherently limited to individual words, and their adaptation for comparing longer texts requires an extra level of complexity (Mihalcea et al., 2006).”