Geometric lexical representative perspectives: The impact of threshold values through #LancsBox software

Abstract

This paper is an investigation of the impact of threshold values in geometric representations of lexical plots. The study uses MI-scores to test lexical representations in the Household Building Corpus (KPMR) data. MI-scores are a form of collocation of the assessment of lexical co-occurrence with values of > 3.0. However, changes in threshold values can provide an additional representative value to the nodes involved. The findings show that the threshold effect can contribute to lexical presence such as hapaxes as lexical density. Rational lexical expressions can be evaluated and viewed through the impact of its lexical wealth, in addition to examining the capabilities of #LancsBox 4.5 as a machine learning processer.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 1 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.