Y. Attali, and J. Burstein. The Journal of Technology, Learning and Assessment (JTLA), (February 2006)
Abstract
E-rater has been used by the Educational Testing Service for automated essay scoring since 1999. This paper describes a new version of e-rater (V.2) that is different from other automated essay scoring systems in several important respects. The main innovations of e-rater V.2 are a small, intuitive, and meaningful set of features used for scoring; a single scoring model and standards can be used across all prompts of an assessment; modeling procedures that are transparent and flexible, and can be based entirely on expert judgment. The paper describes this new system and presents evidence on the validity and reliability of its scores.
%0 Journal Article
%1 Attali06jtla
%A Attali, Yigal
%A Burstein, Jill
%D 2006
%E Russell, Michael
%J The Journal of Technology, Learning and Assessment (JTLA)
%K E-NLP assesment automatic_essay_grading
%N 3
%T Automated Essay Scoring With e-rater® V.2
%U http://escholarship.bc.edu/jtla/vol4/3/
%V 4
%X E-rater has been used by the Educational Testing Service for automated essay scoring since 1999. This paper describes a new version of e-rater (V.2) that is different from other automated essay scoring systems in several important respects. The main innovations of e-rater V.2 are a small, intuitive, and meaningful set of features used for scoring; a single scoring model and standards can be used across all prompts of an assessment; modeling procedures that are transparent and flexible, and can be based entirely on expert judgment. The paper describes this new system and presents evidence on the validity and reliability of its scores.
@article{Attali06jtla,
abstract = {E-rater has been used by the Educational Testing Service for automated essay scoring since 1999. This paper describes a new version of e-rater (V.2) that is different from other automated essay scoring systems in several important respects. The main innovations of e-rater V.2 are a small, intuitive, and meaningful set of features used for scoring; a single scoring model and standards can be used across all prompts of an assessment; modeling procedures that are transparent and flexible, and can be based entirely on expert judgment. The paper describes this new system and presents evidence on the validity and reliability of its scores.},
added-at = {2007-11-06T08:45:07.000+0100},
author = {Attali, Yigal and Burstein, Jill},
biburl = {https://www.bibsonomy.org/bibtex/2a6df39d263c4b9ef7aa3f2df02c77140/dbernhar},
editor = {Russell, Michael},
interhash = {08a83aecfccdab4d42fe87aa67c4980e},
intrahash = {a6df39d263c4b9ef7aa3f2df02c77140},
journal = {The Journal of Technology, Learning and Assessment (JTLA)},
keywords = {E-NLP assesment automatic_essay_grading},
month = {February},
number = 3,
timestamp = {2007-11-06T08:45:07.000+0100},
title = {Automated Essay Scoring With e-rater® V.2},
url = {http://escholarship.bc.edu/jtla/vol4/3/},
volume = 4,
year = 2006
}