A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge.

By T. Landauer, Susan T. Dumais. 1997

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

Zero-Shot Learning Through Cross-Modal Transfer (2013, background): “These representations have proven very effective in natural language processing tasks such as sense disambiguation [30], thesaurus extraction [24, 8] and cognitive modeling [22].”
Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change (2016, methodology): “This SVD approach can be viewed as a generalization of Latent Semantic Analysis (Landauer and Dumais, 1997), where the term-document matrix is replaced with M PPMI .”
From Frequency to Meaning: Vector Space Models of Semantics (2010, methodology): “Landauer and Dumais (1997) evaluated this approach with 80 multiple-choice synonym questions from the Test of English as a Foreign Language (TOEFL), achieving human-level performance (64.4% correct for the word–context matrix and 64.5% for the average non-English US college applicant).”
SimLex-999: Evaluating Semantic Models With (Genuine) Similarity Estimation (2014, methodology): “While the NLM is the strongest performer on WS-353, LSA is the strongest performer on MEN.”
A semantic matching energy function for learning with multi-relational data (2013, methodology): “The application of SME to WSD is related to work on vector-based models of word meaning (Lund and Burgess 1996; Landauer and Dumais 1997) and neural language models (Bengio 2008; Collobert et al.”
Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors (2014, methodology): “Synonym detection The classic TOEFL (toefl) set was introduced by Landauer and Dumais (1997).”
Multimodal Distributional Semantics (2013, background): “…of the matrix containing the semantic vectors as rows can optionally be decreased by dimensionality reduction, that might provide beneficial smoothing by getting rid of noise components and/or allow more efficient storage and computation (Landauer & Dumais, 1997; Sahlgren, 2005; Schütze, 1997).”
My Computer Is an Honor Student - but How Intelligent Is It? Standardized Tests as a Measure of AI (2016, methodology): “Other groups have attempted higher level exams, e.g., the Tokyo Entrance Exam (Strickland, 2013), and more specialized psychometric tests e.g. SAT word analogies (Turney, 2006), GRE word antonyms (Mohammad et al., 2013), and TOEFL synonyms (Landauer and Dumais, 1997).”
A Structured Vector Space Model for Word Meaning in Context (2008, methodology): “These vectors are able to provide a robust model of semantic similarity that has been used in NLP (Salton et al., 1975; McCarthy and Carroll, 2003; Manning et al., 2008) and to model experimental results in cognitive science (Landauer and Dumais, 1997; McDonald and Ramscar, 2001).”
Multi-Step Regression Learning for Compositional Distributional Semantics (2013, methodology): “Extensive evidence suggests that dimensionality reduction does not affect, and might even improve the quality of lexical semantic vectors (Bullinaria and Levy, 2012; Landauer and Dumais, 1997; Sahlgren, 2006; Sch¨utze, 1997).”
A Survey of Cross-lingual Word Embedding Models (2017, methodology): “We can write their objective in our notation as the following: J = LLSA(Xs) + LLSA(Xt)︸︷︷︸ 1 + ΩCCA(X s,Xt,Ws→,Wt→)︸︷︷︸ 2 (19) Faruqui and Dyer propose to use the 80% projection vectors with the highest correlation.”