An Improved Model of Semantic Similarity Based on Lexical Co-Occurrence

By Douglas L. T. Rohde, David C. Plaut. 2005

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

GloVe: Global Vectors for Word Representation (2014, methodology): “A number of techniques exist that addresses this shortcoming of HAL, such as the COALS method (Rohde et al., 2006), in which the co-occurrence matrix is ﬁrst transformed by an entropy-or correlation-based normalization.”
Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition, 2nd Edition (2000, unknown): “From Rohde et al. (2006).”
An Introduction to Neural Information Retrieval (2018, unknown): “, HAL [Lund and Burgess, 1996], COALS [Rohde et al., 2006], and [Bullinaria and Levy, 2007]), and neighbouring words with distance (e.”
Skip-Gram − Zipf + Uniform = Vector Additivity (2017, background): “In more sophisticated methods co-occurrences are reweighed to suppress the effect of more frequent words (Rohde et al., 2006) and/or to emphasize pairs of words whose co-occurrence frequency maximally deviates from the independence assumption (Church and Hanks, 1990).”
RAND-WALK: A Latent Variable Model Approach to Word Embeddings (2015, background): “Some reweightings are nonlinear; e.g., taking the square root of co-occurrence counts (Rohde et al., 2006), or the logarithm , or the related pairwise mutual information (PMI) (Church and Hanks, 1990).”
A Latent Variable Model Approach to PMI-based Word Embeddings (2015, methodology): “Some reweighting methods are nonlinear, which include taking the square root of co-occurrence counts (Rohde et al., 2006), or the logarithm, or the related Pointwise Mu-tual Information (PMI) (Church and Hanks, 1990).”