Developing a framework for the explanation of interlingual features for native and other language infuence detection

Authors

  • Krzysztof Kredens
  • Ria Perkins
  • Tim Grant

Abstract

This article demonstrates the benefit of taking an explanation-based approach in the development of features for computationally supported systems used for linguistic analysis in forensic contexts. As a focal point it considers Other
Language Infuence Detection (OLID) as well as its related field of Native Language Identifcation (NLI). An explanation-based approach allows the forensic linguist to understand the implications of the presence or absence of features as they vary across the contex ts and situations s/he might encounter. The authors present a qualitative framework for types of explanation and show how different types of explanations are needed to develop a full and rich language-influence feature set. The authors are not advocating a strict or inflexible typology of feature explanation but are seeking a richness of explanation at a variety of levels of analysis instead. This in turn can be developed into computational approaches, which the authors contend will therefore be stronger and more applicable to forensic casework contexts.

Published

04.02.2020