Contextual correlates of semantic similarity

By George A. Miller, W. Charles. 1991

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

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

In Representation & Self-Supervised Learning

Citations in the corpus

GloVe: Global Vectors for Word Representation (2014, background): “These include WordSim-353 (Finkelstein et al., 2001), MC (Miller and Charles, 1991), RG (Rubenstein and Goodenough, 1965), SCWS (Huang et al., 2012), and RW (Luong et al., 2013).”
WordNet: A Lexical Database for English (1995, background): “Miller and Charles [ 5 ] proposed that a contextual representation associated with each sense characterizes sentential contexts in which a given word can be used to express that sense.”
Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech (2018, positive): “We used 13 benchmarks [30] to measure word similarity, including WS-353 [31], WS-353-REL [32], WS-353-SIM , MC-30 [33], RG-65 [34], Rare-Word [35], MEN [36], MTurk-287 [37], MTurk-771 [38], YP-130 [31], SimLex-999 [39], Verb-143 [40], and SimVerb-3500 [41].”
Word Representations via Gaussian Embedding (2014, methodology): “We evaluate the embeddings on seven different standard word similarity benchmarks (Rubenstein & Goodenough, 1965; Szumlanski et al., 2013; Hill et al., 2014; Miller & Charles, 1991; Bruni et al., 2014; Yang & Powers, 2006; Finkelstein et al., 2001).”
Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors (2014, background): “A long tradition in computational linguistics has shown that contextual information provides a good approximation to word meaning, since semantically similar words tend to have similar contextual distributions (Miller and Charles, 1991).”
Cheap and Fast – But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks (2008, methodology): “As in the previous task we evaluate our nonexpert annotations by averaging the numeric responses from each possible subset of n annotators and computing the interannotator agreement with respect to the gold scores reported in (Miller and Charles, 1991).”
Multimodal Distributional Semantics (2013, background): “The claim has multiple theoretical roots in psychology, structuralist linguistics , lexicography and possibly even in the later writings of Wittgenstein (Firth, 1957; Harris, 1954; Miller & Charles, 1991; Wittgenstein, 1953).”
Improving Vector Space Word Representations Using Multilingual Correlation (2014, background): “The second and third benchmarks are the RG-65 (Rubenstein and Goodenough, 1965) and the MC-30 (Miller and Charles, 1991) datasets that contain 65 and 30 pairs of nouns respectively and have been given similarity rankings by humans.”
Using Information Content to Evaluate Semantic Similarity in a Taxonomy (1995, methodology): “An experiment by Miller and Charles [1991] provided appropriate human subject data for the task.”
Deep Neural Networks for Learning Graph Representations (2016, methodology): “…2013) on 4 datasets, including the popular WordSim353 (Finkelstein et al. 2001), WordSim Similarity (Zesch, Müller, and Gurevych 2008) and WordSim Relatedness (Agirre et al. 2009) and MC (Miller and Charles 1991), as used in (Pennington, Socher, and Manning 2014; Levy, Goldberg, and Dagan 2015).”
A Survey of Cross-lingual Word Embedding Models (2017, methodology): “The most commonly used ones of these human judgement datasets are: a) the RG dataset (Rubenstein & Goodenough, 1965); b) the MC dataset (Miller & Charles, 1991); c) the WordSim-353 dataset (Finkelstein, Gabrilovich, Matias, Rivlin, Solan, Wolfman, & Ruppin, 2002), a superset of MC; and d) the…”
An Approach for Measuring Semantic Similarity between Words Using Multiple Information Sources (2003, methodology): “The similarities between words were also rated on the scale of 0.0 to 4.0 for “semantically unrelated” to “highly synonymous.” The Miller-Charles experiment was carried out 25 years later than Rubenstein-Goodenough’s, but correlation coefficient between the two sets of ratings is 0.97 [ 14 ].”
Estimating Linear Models for Compositional Distributional Semantics (2010, methodology): “Lexical distributional semantics has been largely used to model word meaning in many ﬁelds as computational linguistics (McCarthy and Carroll, 2003; Manning et al., 2008), linguistics (Harris, 1964), corpus linguistics (Firth, 1957), and cognitive research (Miller and Charles, 1991).”
Better Word Representations with Recursive Neural Networks for Morphology (2013, methodology): “To avoid overfitting our models to a single dataset, we benchmark our models on a variety of others including MC (Miller and Charles, 1991), RG (Rubenstein and Goodenough, 1965), SCWS∗11 (Huang et al.”
An Intrinsic Information Content Metric for Semantic Similarity in WordNet (2004, background): “84 between human and machine similarity judgments on the dataset of Miller and Charles [12], which is suggestively close to the upper-bound of 0.”
Parallelizing Word2Vec in Shared and Distributed Memory (2016, background): “These word representations are learned based on the distributional hypothesis [20], which assumes that words with similar context tend to have a sim-”