Explaining human performance in psycholinguistic tasks with models of semantic similarity based on prediction and counting : A review and empirical validation
By Paweł Mandera, Emmanuel Keuleers, Marc Brysbaert. 2017
373 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Cognitive Neuroscience
View Paper: https://www.semanticscholar.org/paper/b60942cb57c11541b909ca82caf13a429ee49079
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
- Ivan Vulic
- Douwe Kiela
- Anna Korhonen
- Alessandro Lenci
- Yoed N. Kenett
- Sebastian Ruder
- Iryna Gurevych
- Mohit Bansal
In Cognitive Neuroscience
- Jiang Qiu
- Anna Korhonen
- Tengbin Huo
- Douwe Kiela
- Ivan Vulic
- Tingrui Yan
- Alessandro Lenci
- Rongcan Zeng
Citations in the corpus
- The relation between semantic memory structure, associative abilities, and verbal and figural creativity (2020, background): “However, the advent of text-based corpus analysis tools makes it possible for quantifying semantic distance between pairs of words within a high-dimensional semantic space (Green, 2016; Heinen & Johnson, 2018; Mandera et al., 2015, 2017).”
- Distributional Models of Word Meaning (2018, background): “Mandera et al. (2017) also show that count and prediction models produce very similar results.”
- Evaluation by Association: A Systematic Study of Quantitative Word Association Evaluation (2017, background): “To fill in this gap, recent work has proposed using subconscious cognitive measures of semantic connection instead, as a proxy for measuring the ability of statistical models to tackle various problems in human language understanding (Ettinger and Linzen, 2016; Søgaard, 2016; Mandera et al., 2017).”