Random indexing of text samples for latent semantic analysis

By Pentti Kanerva, Jan Kristoferson, Anders Holst. 2000

515 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/932c8b99ef910bedd0f49d889230aba308004e0a

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

In-memory hyperdimensional computing (2019, methodology): “Inference is then performed with a software encoder and using equation (3) for the AM search, in which all multiplication operations are performed in the analog domain (by exploiting Ohm’s law) on chip and the remaining operations are implemented in software (see Methods and Supplementary Note 1).”
Voice of airline passenger: A text mining approach to understand customer satisfaction (2019, background): “LSA is realised throughout the computation of high-dimensional semantic vectors, or context vectors of words from their co-occurrence statistics (Kanerva et al., 2000).”
Composition in Distributional Models of Semantics (2010, background): “Kanerva, Kristoferson, and Holst (2000) propose the use of random indexing as an alternative to the computationally costly singular value decomposition employed in LSA.”
Distributional Semantics Resources for Biomedical Text Processing (2013, methodology): “Random Indexing Random indexing (Kanerva et al., 2000) is a method for building a semantic word vector model in an incremental fashion.”
Evaluating Word Representation Features in Biomedical Named Entity Recognition Tasks (2014, methodology): “…can be divided into three categories: (1) clustering-based methods such as Brown clustering [27]; (2) distributional representations, such as LSA [23], LDA [24], and random indexing [25]; and (3) word embeddings (also called distributed representations), such as neural language models [28].”
Distributional Models of Word Meaning (2018, background): “The most famous DSM of this kind is random indexing (RI) (Kanerva et al. 2000, Sahlgren 2006), which accumulates distributional vectors in an online fashion.”
Diachronic word embeddings and semantic shifts: a survey (2018, methodology): “To alleviate this, Kulkarni et al. (2015) suggested that before calculating similarities, one should first align the models to fit them in one vector space, using linear transformations preserving general vector space structure. After that, cosine similarities across models become meaningful and can”
Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors (2009, background): “[20], the idea of which is discussed above.”
Deep learning meets ontologies: experiments to anchor the cardiovascular disease ontology in the biomedical literature (2018, background): “Random Indexing [23] has emerged as a promising alternative to LSA.”
Computational modeling of phonetic and lexical learning in early language acquisition: Existing models and future directions (2012, background): “, [10]), making it difficult to judge whether a model scales up to real world learning conditions in the human brain (but see [11]).”
Enhancing clinical concept extraction with distributional semantics (2011, methodology): “Recently, Random Indexing [4] emerged as promising alternative to the use of computationally expensive SVD for the dimension reduction step in the generation of word-by-context vectors.”