|Title||About the effects of using Anaphora Resolution in assessing free-text student answers|
|Publication Type||Conference Paper|
|Year of Publication||2005|
|Authors||Pérez D, Postolache O, Alfonseca E, Cristea D, Rodriguez P|
|Conference Name||Recent Advances in Natural Language Processing (RANLP)|
|Conference Location||Borovets, Bulgaria|
In this paper we present a possibility for integrating Anaphora Resolution (AR) in a system to automatically evaluate students’ free-text answers. An initial discussion introduces some of the several methods that can be tried out. The implementation makes use of the AR-Engine RARE (Cristea et al. 02), integrated into the free-text answers assessor Atenea (Alfonseca & Pérez 04) to test these methods. RARE has been applied to find coreferential chains, and it has been found useful to extend the set of reference answers used by Atenea, by generating automatically new correct answers.