Distributional semantics in linguistic and cognitive research

315 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Unsupervised learning for text-to-speech synthesis (2013, methodology): “For example, Li and McCallum (2005) apply Brown clusters (as one of their unsupervised features) once again to POS tagging, and in Koo et al.”
Understanding Natural Language Understanding Systems. A Critical Analysis (2023, background): “Therefore, linguistic co-occurrences, like the ones used by foundation models, do shape our meanings, alongside other types of multimodal experiences (Lenci 2008, Lupyan and Lewis 2019).”
Gender stereotypes are reflected in the distributional structure of 25 languages (2019, methodology): “This relationship was not reliable for the Wikipedia corpus (r(20) = −0.”
Applying LDA Topic Modeling in Communication Research: Toward a Valid and Reliable Methodology (2018, background): “However, by discarding word order, specific local context information on semantic relations between words is lost, which otherwise might help interpret deeper meanings and solve ambiguities (Lenci, 2008, p. 21).”
SemEval-2018 Task 11: Machine Comprehension Using Commonsense Knowledge (2018, background): “Traditionally, Natural Language Understanding (NLU) systems have resolved ambiguities using information from the textual context (e.g. neighboring words and sentences), for example via distributional methods (Lenci, 2008).”