Chris Mayer

Automated essay scoring (AES) is gaining increasing attention in the education sector as it significantly reduces the burden of manual scoring and allows ad hoc feedback for learners. Natural language processing based on machine learning has been shown to be particularly suitable for text classification and AES. While many machine-learning approaches for AES still rely on a bag of words (BOW) approach, we consider a transformer-based approach in this paper, compare its performance to a logistic regression model based on the BOW approach, and discuss their differences. The analysis is based on 2088 email responses to a problem-solving task that were manually labeled in terms of politeness. Both transformer models considered in the analysis outperformed without any hyperparameter tuning of the regression-based model. We argue that, for AES tasks such as politeness classification, the transformer-based approach has significant advantages, while a BOW approach suffers from not taking word order into account and reducing the words to their stem. Further, we show how such models can help increase the accuracy of human raters, and we provide a detailed instruction on how to implement transformer-based models for one’s own purposes.

The concept of noncombatant immunity prohibits the intentional targeting of noncombatants. The availability of nonlethal weapons (NLW) may weaken this prohibition, especially since using NLWs against noncombatants may, in some cases, actually save the noncombatants' lives. Given the advancement of NLWs, I argue that their probable appearance on the battlefield demands close scrutiny due to the moral problems associated with their use. In this paper, I examine four distinct cases and determine whether the use of NLWs is morally permissible. While it seems that the reduced harm caused by NLWs makes their use more acceptable, adhering to noncombatant immunity requires more than not killing noncombatants. It also requires that military forces treat noncombatants a certain way. In the cases I present, to use NLWs against noncombatants treats them as combatants and coerces them to do something against their will. While a consequentialist foundation for noncombatant immunity may permit this action, a rights-based concept of noncombatant immunity does not. I contend that only a rights-based concept of noncombatant immunity is viable, and that the availability of NLWs should not significantly alter the prohibitions prescribed by noncombatant immunity.