Volume 135, Issue 1
  • ISSN 0019-0829
  • E-ISSN: 1783-1490
Buy:$35.00 + Taxes


Abstract This paper presents an investigation into the extent to which the lexical choices made by learners of a second language (L2) are distinctive. It follows on from an earlier paper by the same authors in which a neural network was successfully trained to mark a set of texts produced by L2 learners to the same standard, within broad categories, as had been awarded by experienced human markers. For this present paper, we examined a set of L2 texts and searched them for unique lexical choices (‘lexical signatures’). The results suggest a possible explanation for the success of the neural-network trial, and may have some practical implications for determining the levels of achievement reached by L2 learners.


Article metrics loading...

Loading full text...

Full text loading...


  1. HOLMES, D.I.
    (1994) : Authorship attribution. Computers and the Humanities, 28 (2), 87-106.
    [Google Scholar]
  2. MEARA, P.M. , RODGERS, C. and JACOBS, G.
    (2000) : Computational assessment of texts written by L2 speakers. System, 28, 345-354.
    [Google Scholar]
  • Article Type: Research Article
This is a required field
Please enter a valid email address
Approval was successful
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error