Transforming Grammar Checking Technology into a Learning Environment for Second Language Writing

Ola Knutsson
IPLab, umerical Analysis
and Computer Science
Royal Institute of Technology
SE-100 44 Stockholm, Sweden
knutsson@nada.kth.se
Teresa Cerratto Pargman
K2LAB, Computer
and Systems Sciences
Stockholm University
SE-164 40 Kista, Sweden
tessy@dsv.su.se
Kerstin Severinson Eklundh
IPLab, Numerical Analysis
and Computer Science
Royal Institute of Technology
SE-100 44 Stockholm, Sweden
kse@nada.kth.se

Abstract
This paper focuses on the transformation of
grammar checking technology into a learning
environment for second language writing.
Our starting point is a grammar checker for
Swedish, called Granska. Two studies have
been conducted aimed at exploring the use of
computer support for writing in the context of
second language learning. In the first study, we
developed a methodology to study naturalistic
writing, and the impact of the grammar checker
on the writer’s text. In the second study, we
were interested in how the methodology developed
earlier would work in an educational
setting. The problems with false alarms and
limited recall are definitely a sensitive issue
in the context of second language learners and
educational settings. Both learners and teachers
are concerned about the false alarms, and
without perfectly working text analyzers, new
strategies for dealing with these problems have
to be further explored and developed together
with learners and teachers.
1 Introduction
Language technology programs have been widely discussed
as a potential candidate for a tool suitable for the
use in the context of second language writing (see e.g.
Chapelle (2001)). However, in this discussion an important
series of questions remain open as for example the
one regarding the impact of language technology on the
writing and learning activity. The uncertainty about the
role that language technology programs may play in educational
settings is in part related to two facts at least: the
existence of false alarms generated by the program and
the limited recall of important linguistic constructions in
the learners’ texts.
The interaction with false alarms can be highly confusing
in a second language learning context and might introduce
new language problems than the program is able
to detect and correct. Furthermore, the emergence of false
alarms during the use of language technology for writing
might make the learner shifts her attention from her text
to the alarms. In such situation, the learner might put
much energy in dealing with false alarms and eventually,
in correcting or reflecting on her text according to them
and therefore in getting a false conception of having reviewed
authentic language problems.
This paper focuses on the development and the use
of writing language tools in the context of second language.
The vision guiding our work is the idea of studying
and developing language tools that will be able to
help writers/learners to reflect on their own language and
not only help them to succeed in their revision tasks. In
this sense, we agree with Swain and Lapkin’s hypothesis
(1995):
“... in producing the L2, a learner will on occasion
become aware of (i.e. notice) a linguistic
problem brought to his/her attention
either by external feedback (e.g. clarification
requests or internal feedback). Noticing a problem
”pushes” the learner to modify his/her output.
In doing so, the learner may sometimes be
forced into a more syntactic processing mode
that might occur in comprehension” (p. 373
cited by Chapelle (2001)).
In the light of the limitations of text analysis programs’
recall and precision, we need to search for alternative
strategies to aid users to deal with false alarms and limited
feedback on serious linguistic constructions not identified
by the program. Even more important, it is necessary to
develop a tool that also supports the whole writing process,
and not only the revision process.
Our starting point is a grammar checker for Swedish,
called Granska (Domeij et al., 2000). We aim at developing
Granska further to a language learning environment
capable to support adequate functionality for secondlanguage
learning purpose. In order to develop such
functionality and support we have started to conduct user
studies in educational settings. The paper presents two
studies guided by the following questions:
• How should we go from grammar checker programs
further to learning environments for second language
writers?
• What kinds of functionality are necessary to support
in such learning environments?
• How should researchers and developers work together
with teachers and students in order to get a
chance to introduce computer-assisted learning in
second-language courses?
2 Background
The study of acquisition and development of Swedish
as a second language is a vast research area that goes
back to the early 70’s in Sweden. In this research
work, three main perspectives can be distinguished: linguistic,
socio-linguistic and pedagogical. Studies conducted
through these perspectives agree on viewing the
acquisition and development of second language as a
multifaceted process in which is necessary to combine
different foci. They have, however, most often focused
on the study of speech and the development of immigrants’
communicative competence (cf. Kotsinas (1985)).
Questions regarding the role of writing during the acquisition
and development of a second language have
usually been overlooked. Another common characteristic
of all three perspectives is that they have neglected
the question of the role of language tools in supporting
learning, and more in particular, in helping learners
to reflect on and develop awareness of the language
they produce. Furthermore, the use of CALL applications
in second-language education is still limited in
Sweden. The few educational institutions that have introduced
CALL applications in their curricula use mostly
email, chat or multimedia; programs that actually have
very little input from language technology research (cf.
Cerratto and Borin (2002)). In this sense, it should come
as no surprise that computer-assisted language learning
applied to Swedish as a second language rarely incorporates
features that are able to analyze learners’ written or
spoken productions (cf. Cerratto and Borin (2002)).
Unlike computer-assisted language learning in the context
of Swedish as a second language, language tools for
Swedish have an important place within the writing process
of native speakers. However, concentrated as they
have been on the development of robust and highly efficient
algorithms and rules that are able to correctly detect
and diagnose language errors, they have neglected the
pedagogical potential of such tools (Vernon, 2000). Developed
to support correct writing, they have often been
based on models of native writers neglecting then writers
who are learning Swedish as a second language.
2.1 Granska – a Swedish Grammar Checker
Granska is a grammar checker for Swedish developed at
the Royal Institute of Technology in Sweden (Domeij et
al., 2000). It is together with other language tools integrated
in a writing environment supporting different aspects
of the writing process. Granska combines probabilistic
and rule-based methods to achieve high efficiency
and robustness (see also Carlberger and Kann (1999)).
Using special error rules, the system can detect a number
of Swedish grammar problems and suggest corrections
for them that are presented to the user together with instructional
information. The current version of Granska,
used in this study, is designed for native Swedish writers.
The core of the Granska system is a statistical PoStagger,
a collection of phenomena-based grammar checking
rules, and a robust shallow parser. In the studies
presented in this paper, Granska was used with a web interface.
Granska’s web interface allowed the students to
use any word processor they liked on any platform.
Granska has been evaluated on five different text
genres including mostly texts from native speakers of
Swedish (Domeij et al., 2002). The recall was ranging
from 37% on student essays to 87% on texts from popular
science. The precision of the program was ranging
from 66% on student essays to 25% on text from international
news. The student essays is the text genre that
mostly resemble the text genre of the learners presented
in this study. To conclude, we can expect a quite good
precision, but a rather low recall on the second language
learners’ texts. An evaluation of the Swedish grammar
checker in Microsoft Word (Birn, 2000) shows a grammar
checker with better precision, but lower recall than
Granska. However, comparisons on the same text genres
remain to be done. One notable difference is that Word’s
grammar checker does not search for the complex error
type split compounds, which Granska does with some
loss in precision as a result.
2.2 Theoretical Framework
The perspective on written language as a tool is grounded
in the Socio-cultural perspective (cf. (Vygotsky, 1978;
Engestr¨om, 1987; Cole and Engestr¨om, 1993; Rabardel,
1995; Wertsch, 1998; Bliss and S¨alj¨o, 1999; B´eguin and
Rabardel, 2000)). According to this perspective, the most
important psychological tool is language, understood as
a semiotic resource providing signs that can be flexible,
and creatively used in social practices. One of the fundamental
notions is that there is a psychological relation
between user -learner- and object of activity -languagethrough
the use of a tool (Rabardel, 1995; Cerratto, 1999;
Cerratto Pargman, forthcoming). This notion inherited
from the cultural-historical school of Russian psychology
puts tools in the position of intermediators of human action.
Considered as intermediators, tools in use are far
from being transparent. Just as language carries ideology
within it, so too do language tools (Haas, 1996).
Focus on the Writing Process
Our interest in writing relies on the central place that
writing occupies in the development of language and
thinking processes (Vygotsky, 1962; Vygotsky, 1978),
(Luria, 1946, cited by Downing (1987)). ”Cognitive processes
and structures are transformed significantly by the
acquisition of our best-recognized cultural (and intellectual)
tool, namely, writing” (Olson (1995), p. 96). Both
Vygotsky and Luria suggested that writing not only allowed
one to do new things but more importantly, turned
speech and language into objects of reflection and analysis
(cf. Olson (1995)). From this perspective, writing is
of utmost importance as it affects consciousness and cognition
through providing a model for speech and a theory
for thinking about what is said. It is in fact this new consciousness
of language that is central to the conceptual
implications of writing. ”Far from transcribing speech,
writing creates the categories in terms of which we become
consciousness of speech” (Olson (1995), p. 119).
Language Tools are Viewed as Cognitive Partners
Few are the studies paying attention to the question
of the role of language tools in supporting learning, and
more in particular, in thinking development in order to
help learners reflect on and develop awareness of the language
they produce. According to S¨alj¨o (1996), the role
of tools – psychological as well as technical – and the
concept of mediation play a fundamental role in the understanding
of human thinking and learning. Quoting
Wertsch (1998), he emphasizes that ”in contrast to many
contemporary analyses of language which focus on the
structure of the sign systems independent of any mediating
role they might play, a sociocultural interpretation
presupposes that one conceives of language and other
sign systems in terms of how they are part of and mediate
human action” (S¨alj¨o (1996), p. 84–85) ”... By acquiring
concepts and discursive tools, we appropriate ways of
understanding reality that have developed within particular
discursive practices in different sectors in a complex
society”(S¨alj¨o (1996) p. 87).
According to this view on language and tools, the use
of language tools may alter second-language learning and
writing processes.
3 Naturalistic Studies on the Use of a
Swedish Language Tool
We conducted two studies, first a pilot study and then a
more systematic study called study 1. In the pilot study
conducted, we aimed at developing and testing a methodology
for data collection in the context of second language
learners using Granska. We were also interested in
the impact of the grammar checker on the writers’ texts,
and how the users have adapted the tool to their writing
purposes. In the second study we were interested in how
the methodology developed in the pilot study would work
in an educational setting. What we found from the empirical
studies resulted in a shift of focus. In fact, we became
more interested in developing new functionality for
a whole second language-learning environment allowing
to take account of students, teachers, and their relation
with computers; instead of concentrating us on the development
of a robust grammar checker for second-language
writers.
3.1 Pilot Study
The aim pursued in this study was to further explore the
relation between second language writers’ needs and the
possibilities of a language tool such as Granska. The
pilot study investigated the use of the language tool by
three-second language writers working as researchers at
a Swedish University (Knutsson et al., 2002). This study
focused more on the texts (users’ products) than on the
process of writing second language with the help of a language
tool. The study showed that the writers followed
the advice provided by the language tool. In particular,
they found detection and correction feedback more helpful
than the diagnosis feature. The analysis of the writers’
texts comprising 2700 words contained totally 223 errors.
Focused on the errors found, we discovered that the language
tool detected 36,8% of all errors and proposed corrections
for about 34,1% of all errors. The writers detected
a few of the errors without requiring the language
tool’s advice and repaired some of the errors where the
language tool provided detection and diagnosis. About
15 false alarms occurred and they were mostly due to the
program’s limited knowledge of idiomatic expressions.
None of these alarms caused the writers to make changes
in their texts. When looking at the writers’ comments
they seem to convey a sense of getting annoyed when
the program continues to detect and provide diagnosis on
sentences without for example, finite verbs. The context
in which we conducted this study was a naturalistic academic
working place and that represented a compromise.
The users were primarily doing their work and not testing
a tool in a controlled context, they were writing under
stress, disposing of little time to systematically save their
drafts or evaluate the language tool in use. Their principal
goal of their activity was not learning about the language
tool and their errors but rather to be able to communicate
written information as proper as possible. The collection
of data was difficult to gather systematically and that
lead us to explore the information collected rather than to
conduct comparisons or more refined analysis. Based on
these preliminary results, we decided to conduct a study
in another naturalistic context with a easier access to the
data. Study 1 was conducted with a group of students
attending an advanced course in ”Writing Swedish as a
Foreign Language” at the Stockholm University.
3.2 Study 1
The study focused on the process of second-language
writing with a language tool. In particular, we aim at
analyzing the use of the same language tool by a larger
number of writers who were focused more on the process
of language learning than on delivering a text. The
contact with the National Program ”Swedish as a Foreign
Language” at the department of Scandinavian languages,
Stockholm University, made possible the study of the use
of Granska by a group of 20 students. Of the initial 20
students 7 accepted to participate in the study and 5 have
actually completed it.
The research questions guiding this study were:
• What do second-language writers need from a language
tool?
• Which types of mistakes do second language writers
often commit? Which are the ones that the language
tool better support?
• How do second language writers handle false alarms
generated by the program?
• How much data is it necessary to analyze when
studying the use of language tool in a second language
learning environment?
• How does the teacher regard the use of the language
tool in her classroom?
Naturalistic Task
We had access to the writers’ texts that were part of the
regular course on writing Swedish as a second-language.
The texts consisted of different genres of texts (argumentative
texts, letters, descriptions, essays etc.) and on different
subjects. The learners composed all texts at home and
discussed them at the university. The teacher reviewed
their texts and graded them.
About the Users
All the users were in their third and final semester of
the language-learning program ”Svenska som fr¨ammande
spr°ak” – Swedish as a foreign language – This program
prepares learners to pass the TISUS (Test I Svenska f¨or
Universitets- och h¨ogskoleStudier) a test that is equivalent
to the TOEFL (Test Of English as a Foreign Language).
All the participants had in average resided in
Sweden for a period of three years. They come from different
parts of the world: Spain, Germany, Russia, Poland
and Philippines, see table 1. They presented mixed background
although all had received university education in
their mother tongues. They also presented diverse degrees
of familiarity with computers. All the participants
succeeded the course.
Method and Data Collection
Study 1 was conducted in the context of a secondlanguage
course. To study the use of a language tool in
a real setting entails, first of all, to introduce the tool into
the new context. This task requires a lot of effort and
entails different steps in a complex process:
1. Establishing contact with the teacher. Learning
about the course, its goals, its participants, and its
tasks.
2. Introducing ourselves and the research project to the
course.
3. Presenting and explaining the instructions to use and
judge Granska. Choosing together with the teacher
the text to be revised by the learners using the tool.
4. Distributing the consents forms and the prequestionnaires
to those willing to participate in the
study.
5. Observing the learners using Granska while they revised
their texts at the computer lab at the university.
Providing help if needed. Collecting their drafts.
6. Checking if the students had problems when interacting
with the tool. Providing help if needed.
7. Collecting their final versions and interviewing the
learners and the teacher.
Establishing and developing a relationship with the
teacher was fundamental in order to gain her confidence
and thus have the chance to introduce the tool into the
classroom. It is the teacher who actually decides on the
advantages to let the students use a computer program
in their composition tasks. Planning together with the
teacher the introduction of the computer program into the
classroom entailed choosing the class, the writing task
and the time of the year in which the language tool could
be presented to the students.
We collected data through: participant observation,
students’ texts, judgment procedure, questionnaires and
interviews. In this study, we especially encouraged
writers to use the language tool outside the class. The
prerequisite announced for the users was the following:
”use the language tool whenever you want and when you
feel it will help you”. The control of the data collection
was thus left to the users. According to the instructions
the user should save the original text scrutinized with
Granska and also the final version, written after the revision
aided by Granska.
One important part of the data collection consisted of
text material. This material consisted of the output from
Granska, the final version of text, and user judgments on
the alarms from Granska.
Judgment procedure
The judgment procedure was developed in the pilot
study. The purpose of the judging procedure was to track
the users’ decision when prompted with alarms from
Granska. The users were instructed to use the following
grading scale:
• Grade 5. Excellent – I understand exactly what
Granska suggests.
• Grade 4. Good – Granska is a quite good help for
me.
• Grade 3. Acceptable – It is hard for me to make up
my mind on what Granska says, but I take a chance
that Granska is right.
• Grade 2. Bad – It is hard for me to make up my mind
on what Granska says, I have to look in my grammar
book. With the help of the book I can decide if I
should follow Granska or not.
• Grade 1. Incomprehensible – I do not understand
what Granska says. I have to ask the teacher or
some other competent person for help.
The users were requested to use the grading scale in
order to judge the detections, diagnoses and correction
proposals from Granska. Definitions of detections, diagnoses
and corrections were given. Every scrutinized text
was supposed to be annotated with user judgments on the
alarms from the program. The annotations should preferably
be made electronically, but it was also possible for
the users to print out the output from Granska, and make
their annotations on paper.
3.3 Data Analysis
About the texts and the errors
The texts collected were limited in size, although we
could identify some tendencies in the texts. The texts
were not full of errors. The clauses and sentences were
very often quite well formed, and in most cases, they have
a subject and main verb structure; in other words, they are
quite close to the norm. One finding was that the group
of learners chosen, constituted a adequate target group for
the use of language tools such as Granska.
Granska detected about 35% of all errors. An error
typology together with Granska’s detections, diagnoses
and corrections is presented in table 2.
Most of the undetected errors were syntactical errors.
These syntactical errors were mostly word order errors,
missing words, or problems with choice of preposition
in certain verb frames. Granska’s recall on target errors
was quite good, so the main focus for our future efforts
should contain methods for the detection of currently unrecognized
errors, and to support the user when she tries
to incorporate Granska’s advice into her writing process.
One serious problem was collecting the final versions
of students’ texts. The final text version actually tracks
the user decisions when prompted with Granska’s alarms.
Even students that did not participate in the study were
very glad about the judgment procedure; but they were
not willing to give us the final versions of their texts.
Maybe they thought that the final version was something
between them and the teacher.
Another problem was the authentic value of the texts.
A large amount of data seemed when analyzed to be false;
one writer has copied a lot of text from a book. This
made us of aware of the fact that only personal, often argumentative
texts could be part of these kinds of studies.
The results presented in this study consist mostly of argumentative
texts.
Regarding the judgment procedure, we observed that
the user judgments gave important cues to the understanding
of the user’s needs during the revision process
and seemed not to disturb the user too much. Instead, the
users seemed to appreciate this task (see interviews). See
table 3 for some results on the user judgments.
The analysis of the interviews
The analysis of the participants’ answers allowed us
to better understand how they experienced the use of the
language tool in their learning contexts.
The participants observed presented mixed levels of
familiarity with computers programs. Some were keen
about using computers and showed experience in using
Microsoft Word, e-mail programs while others presented
problems in attaching texts to mails or saving files in
other formats. The heterogeneity of their computer literacy
made it clear the necessity to introduce a course on
basic knowledge about using computers.
Participants found it difficult to interact with the program
due to:
– false alarms,
– the number and type of language explanations to select
when correcting a language error,
– misunderstandings about error indication provided by
the program,
– lack of experience in working with more than one window
open on the computer,
– changing formats and sending documents by e-mail.
Participants enjoyed using the program due to:
– the different colors indicating different steps in the revision
of the language,
– the possibility to get access to different explanations,
– the linguistic terms that the program employs, although
some of them resulted difficult to fully understand.
When asking participants about how we could improve
the presentation of the program to other groups of students,
they said that we should consider to:
– include more computer training at the beginning of the
study
– give a more active role to the teacher before and during
the study,
– remind participants on their duty to send their material,
– challenge participants as much as possible.
4 Discussion
Preliminary results obtained from naturalistic studies
conducted in working and educational contexts, can be
summarized in the following thoughts:
From grammar checkers to second-language learning
environment
First, we think that given the unpredictability of the
grammatical forms that a learner may produce, it seems
inaccurate to write a program that will recognize the
learner’s language. As Chapelle writes ”the question for
computer aided second-language is not whether or not the
computational grammar is a good theoretical account of
the language within a particular domain, but instead is
whether or not the program is able to interact with the
learner in a way that is useful relative to its purpose”
(Chapelle (2001), p. 36). Second, we understand that
a more adequate way to help second language writers
in their learning purpose is to support the resources that
they develop when composing and revising a text. By
resources, we mean those second-language writers build
during the acquisition of the target language. We refer to
for example linguistic strategies put in use for the recognition
of errors. We think that instead of imposing ”correct
Swedish” to succeed composing a text, we should
innovate ways in order to help second-language writers
reason about language.
Focus on linguistic form
We believe that new ways to support reasoning about
language is to concentrate efforts on helping learners to
notice and attend to linguistic form for acquisition. Some
researchers refer to ”focus on form” that is about how the
learner’s focal attentional resources are allocated. ”Focus
on form often consists of a shift of attention to linguistic
code features – by the teachers and/or one or more
students – triggered by perceived problems with comprehension
or production Long and Robinson (1998 cited by
Chapelle (2001) p. 47). We think that language tools
could play a role in this process of helping learners to
focus on form.
The implementation of Writing Tools in Educational
Settings
As second language learners are a heterogeneous
group of learners it is difficult to study them without
identifying a suitable user group capable to interact
with writing tools and with a certain level of language
knowledge. The context of an undergraduate course in
Swedish as a foreign language gave then us control of the
user’s language competence.
The educational setting also provided us information
on grammatical knowledge and terms developed in the
course. It is crucial for future applications to converge
to grammatical knowledge and terms that the users
are learning. But as this will probably consolidate the
learners trust in the program, with the teacher’s grammatical
terms echoing in the feedback from program, the
effects of false alarms and limited recall will probably
become an even more intricate question to be studied.
Acknowledgements
We thank teachers and users who have participated in the
studies. The work has been funded by the Swedish Research
Council (VR).
References
J. Birn. 2000. Detecting grammar errors with lingsoft’s
Swedish grammar checker. In T. Nordg°ard, editor,
Nodalida ’99 Proceedings from the 12th Nordiske
datalingvistikkdager, pages 28–40. Department of Linguistics,
University of Trondheim.
J. Bliss and R. S¨alj¨o. 1999. The human - technological
dialectic. In J. Bliss, R. S¨alj¨o, and P. Light, editors,
Learning sites. Social and Technological resources for
learning, pages 1–13. Pergamon.
P. B´eguin and P. Rabardel. 2000. Designing for
instrument-mediated activity. Scandinavian Journal of
information Systems, pages 173–190.
J. Carlberger and V. Kann. 1999. Implementing an efficient
part-of-speech tagger. Software - Practice and
Experience, 29(9):815–832.
T. Cerratto and L. Borin. 2002. Swedish as a second
language and computer aided learning language. Overview
of the research area. Technical Report TRITANA-
P0206, Department of Numerical Analysis and
Computer Science, Royal Institute of Technology,
Stockholm, Sweden.
T. Cerratto Pargman. forthcoming. Collaborating with
writing tools: an instrumental perspective on the problem
of computer support for collaborative activities.
Interacting with Computers: the Interdisciplinary
Journal of Human-Computer Interaction.
T. Cerratto. 1999. Activit´e collaborative sur r´eseau. Une
approche instrumentale de l’ ´ecriture en collaboration.
(Collaborative networked activities. An instrumental
approach to collaborative writing). Ph.D. thesis, University
of Paris VIII-St. Denis, Paris, France.
C. A. Chapelle. 2001. Computer Applications in Second
Language Acquistion. Foundations for teching, testing
and research. Cambridge University Press, UK.
M. Cole and Y. Engestr¨om. 1993. A cultural-historical
approach to distributed cognition. In G. Salomon, editor,
Distributed Cognitions, pages 1–47. Cambridge
University Press.
R. Domeij, O. Knutsson, J. Carlberger, and V. Kann.
2000. Granska – an efficient hybrid system for
Swedish grammar checking. In T. Nordg°ard, editor,
Nodalida ’99 Proceedings from the 12th Nordiske
datalingvistikkdager, pages 28–40. Department of Linguistics,
University of Trondheim.
R. Domeij, O. Knutsson, and K. Severinson Eklundh.
2002. Different ways of evaluating a Swedish grammar
checker. In Proc. 3rd Int. Conf. Language Resources
and Evaluation (LREC 2002), Las Palmas,
Spain.
J. Downing. 1987. Comparative perspectives on world
literacy. In D. Wagner, editor, The future of literacy in
a changing world, pages 25–47. Pergamon Press.
Y. Engestr¨om. 1987. Learning by expanding: an activity
theoretical approach to developmental research. Technical
report, Orienta-Konsultit oy, Helsinki.
C. Haas. 1996. Writing technology. Studies in the materiality
of literacy. LEA.
O. Knutsson, T. Cerratto Pargman, and K. Severinson
Eklundh. 2002. Computer support for second language
learners’ free text production - initial studies. In
Proceedings of ICL2002, 5th International Workshop
on Interactive Computer Aided Learning, Villach, Austria.
U-B. Kotsinas. 1985. Invandrare talar svenska. Liber.
D. Olson. 1995. Writing and the mind. In J. Wertsch,
P. Del Rio, and A. Alvarez, editors, Sociocultural
Studies of Mind, pages 95–123. Cambridge University
Press.
P. Rabardel. 1995. Les activit´es avec instruments. Colin.
R. S¨alj¨o. 1996. Mental and physical artifacts in cognitive
practices. In P. Reimann and H. Spada, editors,
Learning in humans and machines. Towards an interdisciplinary
learning science. Pergamon.
A. Vernon. 2000. Computerized gammar checkers 2000:
Capabilities, limitations, and pedagogical possibilities.
Computers and Composition, pages 329–349.
L. Vygotsky. 1962. Thought and language. MIT Press.
L. Vygotsky. 1978. Mind and Society : The development
of higher psychological processes. Harvard University
Press.
J. V. Wertsch. 1998. Mind as action. Oxford University
Press.
User Native Language Graded Texts Final version No. of Words Interview
A Russian and Belrussian 1 0 71 Y es
B German 1 1 270 Y es
C Polish 1 1 517 Y es
D English, Filipino (Tagalog dialect) 1 1 8438 Y es
E Russian 0 0 0 Y es
F Russian 0 0 0 Y es
G Spanish 2 2 503 Y es
Table 1: User data.
Error type Errors Detections and Diagnoses Corrections
Typographical 1 0 0
Orthographical 1 1 1
Syntactical 45 18 13
Semantical 7 0 0
Total 54 19 (35%) 14 (26%)
Table 2: Error typology. Number of errors, and Granska’s detections, diagnoses and corrections.
Error type Detections Diagnoses Corrections
#judgments Mean value #judgments Mean value #judgments Mean value
Typographical 0 − 0 − 0 − Orthographical 1 5.0 1 4.0 1 2.0
Syntactical 14 3.7 14 3.4 14 3.4
Semantical 0 − 0 − 0 − Total 16 3.8 16 3.2 16 3.1
Table 3: Users’ judgments with mean values of grades. Number of judged detections, diagnoses and corrections from
Granska.