WordICA—emergence of linguistic representations for words by independent component analysis

By Timo Honkela, Aapo Hyvärinen, Jaakko J. Väyrynen. 2010

32 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal 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. Francesco Locatello
2. Bernhard Schölkopf
3. Luigi Gresele
4. Paul K. Rubenstein
5. Joseph P. Levy
6. John A. Bullinaria
7. Oliver Watts
8. Arash Mehrjou

In Signal Processing

1. Francesco Locatello
2. Bernhard Schölkopf
3. Joseph P. Levy
4. John A. Bullinaria
5. Oliver Watts
6. Arash Mehrjou
7. Luigi Gresele
8. Paul K. Rubenstein

Citations in the corpus

• The Incomplete Rosetta Stone problem: Identifiability results for Multi-view Nonlinear ICA (2019, background): “Its applications are ubiquitous, including neuroimaging [28], signal processing [34], text mining [17], astronomy [31] and financial time series analysis [32].”
• Extracting semantic representations from word co-occurrence statistics: stop-lists, stemming, and SVD (2012, background): “These early ideas continue to be refined and extended to produce increasingly sophisticated semantic representations (e.g., Baroni & Lenci, 2010; Griffiths, Steyvers, & Tenenbaum, 2007; Honkela et al. 2010; Jones & Mewhort, 2007; Zhao, Li, & Kohonen, 2011).”
• Unsupervised learning for text-to-speech synthesis (2013, background): “] the latent concept space is difficult to understand by humans (Honkela et al., 2010).”