Tracing semantic change with latent semantic analysis

By Eyal Sagi, Stefan Kaufmann, B. Clark. 2011

94 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cultural Studies, Language and Linguistics, 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

1. Jure Leskovec
2. William L. Hamilton
3. Dan Jurafsky
4. Percy Liang
5. Yoshua Bengio
6. Stephan Mandt
7. R. Fern'andez
8. Marco Del Tredici

In Cultural Studies

1. Stephan Mandt
2. Robert Bamler
3. R. Fern'andez
4. Marco Del Tredici
5. Jure Leskovec
6. Dan Jurafsky
7. Martin Hilpert
8. Nick Haslam

In Language and Linguistics

1. J. Rhee
2. R. Fern'andez
3. Melanie J. McGrath
4. Jure Leskovec
5. Dan Jurafsky
6. Fabian Fabiano
7. Brodie C. Dakin
8. Morgan Weaving

In Natural Language Processing

1. Stephan Mandt
2. R. Fern'andez
3. Robert Bamler
4. Marco Del Tredici
5. Erik Velldal
6. Andrey Kutuzov
7. Lilja Øvrelid
8. Terrence Szymanski

Citations in the corpus

• Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change (2016, background): “Our work builds upon a wealth of previous research on quantitative approaches to semantic change, including prior work with distributional methods (Sagi et al., 2011; Wijaya and Yeniterzi, 2011; Gulordava and Baroni, 2011; Jatowt and Duh, 2014; Kulkarni et al., 2014; Xu and Kemp, 2015), as well as…”
• Diachronic word embeddings and semantic shifts: a survey (2018, methodology): “Two years later, Gulordava and Baroni (2011) used explicit count-based models, consisting of sparse co-occurrence matrices weighted by Local Mutual Information, while Sagi et al. (2011) turned to Latent Semantic Analysis (Deerwester et al., 1990).”
• Dynamic Word Embeddings via Skip-Gram Filtering (2017, background): “Several authors have analyzed different statistics of text data to analyze semantic changes of words over time (Mi-halcea & Nastase, 2012; Sagi et al., 2011; Kim et al., 2014; Kulkarni et al., 2015; Hamilton et al., 2016).”
• Change in modal meanings: Another look at the shifting collocates of may (2016, methodology): “This paper will build on that work, but will pursue a different, somewhat more general approach that draws on ideas that have been developed in Sagi et al. (2011).”
• Harm inflation: Making sense of concept creep (2020, methodology): “Vylomova et al. (2019) first evaluated the change in semantic breadth of the five terms using a count-based method developed by Sagi et al. (2011) that employs latent semantic analysis.”
• Semantic Variation in Online Communities of Practice (2018, methodology): “A variety of techniques have been explored: Latent Semantic Analysis (Sagi et al., 2011; Jatowt and Duh, 2014), topic clustering (Wijaya and Yeniterzi, 2011) and dynamic topic modelling (Frermann and Lapata, 2016).”
• Last Words: Computational Linguistics and Deep Learning (2015, unknown): “Sagi, Kaufmann, and Clark (2011)—actually using the more traditional method of Latent Semantic Analysis to generate distributed word representations—show how distributed representations can capture a semantic change: the broadening and narrowing of reference over time.”
• Dynamic Word Embeddings (2017, background): “Several authors have analyzed different statistics of text data to analyze semantic changes of words over time (Mihalcea & Nastase, 2012; Sagi et al., 2011; Kim et al., 2014; Kulkarni et al., 2015; Hamilton et al., 2016).”