Linguistic Computing with UNIX Tools - Natural Language Processing and Text Mining - page 242

12.5 Larger Applications
In this section, we describe how these tools can be applied in language teaching and
language analysis. We draw on our experience using these tools at the University of
Aizu where Japanese students learn English as a foreign language. Of course, any
language teacher can modify the examples outlined here to fit a given teaching need.
The tools provide three types of assistance to language teachers: they can be used
for teaching, for language analysis to inform teaching, and for language analysis in
research. In teaching, the tools can be linked to an email program that informs
students about specific errors in their written texts; such electronic feedback for
low-level errors can be more effective than feedback from the teacher [43, 45]. The
tools can also help teachers identify what needs to be taught. From a database of
student writing, a teacher can identify systematic patterns of errors that need to be
addressed in class. In addition, one can isolate syntactic structures and lexical items
that the students either overuse or avoid using because of their complexity [27].
One can also use the tools to identify (or confirm) the features of expert texts
in different research genres. Such texts are organized along similar lines with four
sections- Introduction, Methods, Results, and Discussion; further, the Introduction
section can be divided into four Moves [42] that use different language structures
and lexis. Other features include the location of the thesis sentence [7], the use of
hedges such as “perhaps” and “could” [24], and the use of cohesive devices such as
repetition to make the text more readable [22]. Since most students are not familiar
with such devices, the teacher may need to examine expert texts and use the awk
and sed tools to locate similar strings in student writing.
Various commercial tools are currently available for language analysis; however,
many of them come in separate packages and are often expensive. Further, they
draw on million-word databases that provide accurate results but are overkill for
both teachers and students.
The following examples illustrate some of the capabilities of the techniques de-
veloped thus far.
12.5.1 Automated Feedback for Spelling and Punctuation
Some of the first mistakes a teacher of English to Japanese students meets are purely
mechanical: spelling and punctuation, especially when the students' writing is done
on computers with English keyboards (as is the case at the University of Aizu).
Japanese university students generally have little experience typing in English, and
mechanical mistakes are abundant.
Spelling errors can be identified with the UNIX spell program. In [39], we use
sed and awk to reformat the result of the spell check, which is sent back to the
student.
More di cult to correct and teach is English punctuation, the rules of which,
regarding spacing in particular, are different from Japanese. In fact, written Japanese
does not include spaces either between words or after (or before) punctuation marks.
At first, this problem may seem trivial. However, hours of class time spent discussing
punctuation and yet more hours of manually correcting persistent errors tend to wear
on teachers. Persistent errors in English punctuation have even been observed by
one of the authors in English printing done by the Japan Bureau of Engraving, the