We describe a study aimed at measuring the use of factual information in test-taker essays and assessing its effectiveness for predicting essay scores. We found medium correlations with the proposed measures, that remained significant after the effect of essay length was factored out. The correlations did not differ substantionally between a simple, relatively robust measure vs a more sophistic...

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 us...

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 us...

In this paper, we address the problem of quantifying the overall extent to which a testtaker’s essay deals with the topic it is assigned (prompt). We experiment with a number of models for word topicality, and a number of approaches for aggregating word-level indices into text-level ones. All models are evaluated for their ability to predict the holistic quality of essays. We show that the best...

While several methods for automatic essay scoring (AES) for the English language have been proposed, systems for other languages are unusual. To this end, we propose in this paper a multi-aspect AES system for Brazilian Portuguese which we apply to a collection of essays, which human experts evaluated according to the five aspects defined by the Brazilian Government for the National High School...

The psycholinguistic branch of speech perception research is principally concerned with the study of spoken-word recognition. As a separate area of research, spokenword recognition boasts a scant quarter-century of history. Nonetheless, the field has grown and changed in many ways d in ing that time. This brief essay makes no a t tempt to survey the field, or to isolate its principal current co...

In this essay, we innovatively put forward the idea of “NFT-ing NFT.” A standard on “divisible NFTs” will allow hundreds millions future metaverse inhabitants to share ownership and collectively be user creator items. The first NFT” is NFT non-fungible tokens with a single, consistent representation. These NFTs include music, movies, virtual real estate, club membership, so on. For example, son...

In large classrooms with limited teacher time, there is a need for automatic evaluation of text answers and real-time personalized feedback during the learning process. In this paper, we discuss Amrita Test Evaluation & Scoring Tool (A-TEST), a text evaluation and scoring tool that learns from course materials and from human-rater scored text answers and also directly from teacher input. We use...

Various computer tools have been developed to support educators’ assessment of student writing, including automated essay scoring and automated writing evaluation systems. Research demonstrates that these systems exhibit relatively high scoring accuracy but uncertain instructional efficacy. Students’ writing proficiency does not necessarily improve as a result of interacting with the software. ...

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 that differs from the previous one (V.1.3) with regard to the feature set and model building approach. The paper describes the new version, compares the new and previous versions in terms of performance, and presents evidence on the validity and reliabil...