Advanced

Evaluating stages of development in second language French: A machine-learning approach

Granfeldt, Jonas LU and Nugues, Pierre LU (2007) NODALIDA 2007 In NODALIDA 2007 PROCEEDINGS
Abstract
This paper describes a system to define and

evaluate development stages in second language

French. The identification of such

stages can be formulated as determining the

frequency of some lexical and grammatical

features in the learners’ production and how

they vary over time. The problems in this

procedure are threefold: identify the relevant

features, decide on cutoff points for the

stages, and evaluate the degree of success of

the model.

The system addresses these three problems.

It consists of a morphosyntactic analyzer

called Direkt Profil and a machine-learning

module connected to it. We first describe... (More)
This paper describes a system to define and

evaluate development stages in second language

French. The identification of such

stages can be formulated as determining the

frequency of some lexical and grammatical

features in the learners’ production and how

they vary over time. The problems in this

procedure are threefold: identify the relevant

features, decide on cutoff points for the

stages, and evaluate the degree of success of

the model.

The system addresses these three problems.

It consists of a morphosyntactic analyzer

called Direkt Profil and a machine-learning

module connected to it. We first describe the

usefulness and rationale behind its development.

We then present the corpus we used

to develop the analyzer. Finally, we present

new and substantially improved results on

training machine-learning classifiers compared

to previous experiments (Granfeldt et

al., 2006). We also introduce a method to

select attributes in order to identify the most

relevant grammatical features. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
NODALIDA 2007 PROCEEDINGS
editor
Nivre, Joakim; Kalep, Heiki-Jaan; Muischnek, Kadri and Koit, Mare
publisher
University of Tartu
conference name
NODALIDA 2007
ISBN
978-9985-4-0514-7
project
Direkt Profil
language
English
LU publication?
yes
id
72fc99e3-5b69-45eb-a3ba-4fc732e66291 (old id 539348)
date added to LUP
2007-09-18 09:33:54
date last changed
2016-04-16 09:41:35
@misc{72fc99e3-5b69-45eb-a3ba-4fc732e66291,
  abstract     = {This paper describes a system to define and<br/><br>
evaluate development stages in second language<br/><br>
French. The identification of such<br/><br>
stages can be formulated as determining the<br/><br>
frequency of some lexical and grammatical<br/><br>
features in the learners’ production and how<br/><br>
they vary over time. The problems in this<br/><br>
procedure are threefold: identify the relevant<br/><br>
features, decide on cutoff points for the<br/><br>
stages, and evaluate the degree of success of<br/><br>
the model.<br/><br>
The system addresses these three problems.<br/><br>
It consists of a morphosyntactic analyzer<br/><br>
called Direkt Profil and a machine-learning<br/><br>
module connected to it. We first describe the<br/><br>
usefulness and rationale behind its development.<br/><br>
We then present the corpus we used<br/><br>
to develop the analyzer. Finally, we present<br/><br>
new and substantially improved results on<br/><br>
training machine-learning classifiers compared<br/><br>
to previous experiments (Granfeldt et<br/><br>
al., 2006). We also introduce a method to<br/><br>
select attributes in order to identify the most<br/><br>
relevant grammatical features.},
  author       = {Granfeldt, Jonas and Nugues, Pierre},
  editor       = {Nivre, Joakim and Kalep, Heiki-Jaan and Muischnek, Kadri and Koit, Mare},
  isbn         = {978-9985-4-0514-7},
  language     = {eng},
  publisher    = {ARRAY(0xa813498)},
  series       = {NODALIDA 2007 PROCEEDINGS},
  title        = {Evaluating stages of development in second language French: A machine-learning approach},
  year         = {2007},
}