On the computational basis of learning and cognition: Arguments from LSA

By T. Landauer. 2002

202 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cultural Studies, Developmental and Educational Psychology

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 Cultural Studies

In Developmental and Educational Psychology

Citations in the corpus

Multi-Relational Latent Semantic Analysis (2013, methodology): “When used to compare words, one well-known limitation of LSA is that the score captures the general notion of semantic similarity, and is unable to distinguish fine-grained word relations, such as antonyms (Landauer and Laham, 1998; Landauer, 2002).”
Domain and Function: A Dual-Space Model of Semantic Relations and Compositions (2012, background): “owever boat house and house boat would be represented by the same average vector, yet they have diﬀerent meanings. Composition by averaging does not deal with the order sensitivity of phrase meaning. Landauer (2002) estimates that 80% of the meaning of English text comes from word choice and the rem”
From Frequency to Meaning: Vector Space Models of Semantics (2010, background): “” The term statistical semantics appeared in the work of Furnas, Landauer, Gomez, and Dumais (1983), but it was not defined there.”
How to Generate a Good Word Embedding (2015, methodology): “In terms of aspect (ii), the models use four different types of methods.”
Handbook of latent semantic analysis (2007, background): “Many factors contribute to coherence, but Foltz, Kintsch, and Landauer (1998) found that by taking the mean of the cosines of the LSA vectors representing successive sentences in a text, one could approximate empirical data on coherence.”
Mining Text Data (2012, methodology): “Machine learning approaches to summarization offer great freedom because the number of indicators of importance is practically endless [40, 70, 104, 44, 27, 37, 99, 51].”
Polarity Inducing Latent Semantic Analysis (2012, background): “However, as noted by (Landauer and Laham, 1998; Landauer, 2002), there is no notion of antonymy; words with low or negative cosine scores are simply unrelated.”
Language comprehension is both embodied and symbolic (2008, methodology): “The use of these [embodiment] ideas to oppose [hyperspace analogue to language (HAL)] and LSA is a case of what Dennett calls an ‘intuition pump’, pushing the introspective mystery of a mental phenomenon to discredit a mechanistic explanation (Landauer 2002, p. 66–7).”