Exploiting latent semantic information in statistical language modeling

By Jerome R. Bellegarda. 2000

402 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

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

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Unbounded cache model for online language modeling with open vocabulary (2017, background): “Bellegarda [5] and Coccaro and Jurafsky [14] use latent semantic analysis to adapt their models to current context.”
A bit of progress in language modeling (2001, methodology): “There has been essentially no work comparing hard clustering to soft clustering, but several soft-style techniques, including the work of Bengio et al. (2000) and of Bellegarda (2000) have had good success, hinting that these techniques may be more effective.”
Mathematical Foundations for a Compositional Distributional Model of Meaning (2010, background): “Examples include lexicon acquisition [16, 26], word sense discrimination and disambiguation [36, 28], text segmentation [5], language modelling [2], and notably document retrieval [35].”
Context dependent recurrent neural network language model (2012, result): “Similar in spir it to the cache based models are the latent semantic analysis (LSA) based approaches of [12, 13].”
An overview of the literature on technology roadmapping (TRM): Contributions and trends (2013, background): “It is possible to complement a bibliometric study by using semantic analysis, which captures information to quantify sequences of words, modeling a related language [16].”
Polarity Inducing Latent Semantic Analysis (2012, background): “, 2009; Reisinger and Mooney, 2010) and for language modeling (Bellegarda, 2000; Coccaro and Jurafsky, 1998).”
Contextual Language Model Adaptation for Conversational Agents (2018, neutral): “Alternatively, clustered models are created either based on latent semantic analysis [9], k-means clustering [10] or through topic clusters computed by Latent Dirichlet Allocation (LDA) [11].”
Computational Approaches to Sentence Completion (2012, methodology): “This is done as follows (Deer-wester et al., 1990; Bellegarda, 2000), again with the objective of minimizing the reconstruction error.”
Statistical language model adaptation: review and perspectives (2004, methodology): “Thereafter, any new word and/or document is itself mapped into a point in the LSA space, and then compared to other words/documents in the space using a simple similarity measure ( Bellegarda, 2000b ).”
Composition in Distributional Models of Semantics (2010, methodology): “, see Bellegarda, 2004). For example, Kuhn and de Mori (1990) proposed interpolating the unadapted model with a model derived from a cache of recently observed words from the test corpus.”