Publishing Partner: Cambridge University Press CUP Extra Wiley-Blackwell Publisher Login

FYI: GRE/Writing, Minority Lang, Lang Acquisition

Author: don powers

FYI Body: Dear Colleague:

We are seeking help with research we are conducting on behalf of the
Graduate Record Examinations (GRE) Board. Our research concerns the
automated (or computer) scoring of open-ended essay responses. In
particular, we are studying the feasibility of applying automated scoring
methods to the kinds of essays that will be written for the new GRE Writing
Assessment. As you probably know, the automated scoring of essay responses
is now becoming a realistic possibility.

Our "challenge" to you is to try to "beat" the current version of our
automated scoring system, or e-rater, as we call it. The "game," should
you choose to play, is to write essays that will be problematical for
e-rater. By "problematical" we mean essays that would get scores from
e-rater that are either too high or too low, relative to the scores
assigned by human readers. We hope to learn both (a) how robust e-rater is
to attempts to foil it, and (b) whether it undervalues certain kinds or
styles of writing. Ideally, our findings will enable us to distinguish
between failures that are easily correctable and ones that are more serious
because they stem from fundamental differences in the ways that humans and
computers understand language.

Although we can't compensate participants for their time, we hope we can
entice you by providing feedback on how successful your challenges were, as
well as a summary of the challenges made by other participants. (We'll
also award $250 to a writer whose essay is greatly undervalued by e-rater,
and $250 to another whose essay is greatly overrated.) If you are
interested in participating, please let us know as soon as you can
(, and we'll send further details. Thanks.


Don Powers
Principal Research Scientis
Educational Testing Service

Announcing a new ISCA SIG: SALTMIL

SALTMIL: "Speech And Language Technology for MInority Languages"

The start of the new academic year sees the start of the SALTMIL Special
Interest Group within ESCA (now ISCA [International Speech Communication
Association]). The group's initial activities are as follows:
more activities will ensue later.

1) Email discussion lis
- -----------------------

The first activity is an email discussion list. As a preliminary
measure, a new list has been created at the US website
There are two possible ways to subscribe to the SALTMIL list:

a) Point your web browser to
and follow the link to subscribe;
b) Send a blank email to
A message with further details will be automatically sent to you.

This list is free, but carries commercial advertising in a brief section
at the end of each message. However, until we can migrate to a
non-commercial server this will be adequate. The discussions can be
followed through email, and also through a Web browser at the Onelis

2) SALTMIL web page
- ------------------

The provisional SALTMIL website is currently a

Please send any material you would like to add to the web pages to:
This could include details of your work, or a link to your web pages.

We hope very much that many colleagues will join in the discussions and
share their knowledge and experience with others who are also working in
the field of speech and language technology for minority languages.

Briony Williams University of Edinburgh, UK
Climent Nadeu Universitat Politecnica de Catalunya, Spain
Donncha Ó'Cróinín Linguistics Institute of Ireland, Ireland

Perhaps in thinking about the nature and significance of language we
ought to reconsider something so familiar that we no longer mention it,
the acquisition of language by Helen Keller. For the relation between
this and the current intensive discussion of consciousness see

Robin Allott email:
tel/fax: +44 1323 492300

Back   FYI main page