Manually scoring and revising student essays has long been a time-consuming task for educators. With the rise of natural language processing techniques, automated essay scoring (AES) and automated essay revising (AER) have emerged to alleviate this burden. However, current AES and AER models require large amounts of training data and lack…

Automated scoring of student responses to open-ended questions, including short-answer questions, has great potential to scale to a large number of responses. Recent approaches for automated scoring rely on supervised learning, i.e., training classifiers or fine-tuning language models on a small number of responses with human-provided score…

Corpus-based studies have offered the domain definition inference for test developers. Yet, corpus-based studies on temporal fluency measures (e.g., speech rate) have been limited, especially in the context of academic lecture settings. This made it difficult for test developers to sample representative fluency features to create authentic…

Studies on automatic scoring systems in writing assessments have also evaluated the relationship between human and machine scores for the reliability of automated essay scoring systems. This study investigated the magnitudes of indices for inter-rater agreement and discrepancy, especially regarding human and machine scoring, in writing assessment.…

In Automated Essay Scoring (AES) systems, many previous works have studied group fairness using the demographic features of essay writers. However, individual fairness also plays an important role in fair evaluation and has not been yet explored. Initialized by Dwork et al., the fundamental concept of individual fairness is "similar people…

This study explores using transfer learning in machine learning for natural language processing (NLP) to create generic automated essay scoring (AES) models, providing instant online scoring for statewide writing assessments in K-12 education. The goal is to develop an instant online scorer that is generalizable to any prompt, addressing the…

This study explores the effectiveness of using ChatGPT, an Artificial Intelligence (AI) language model, as an Automated Essay Scoring (AES) tool for grading English as a Foreign Language (EFL) learners' essays. The corpus consists of 50 essays representing various types including analysis, compare and contrast, descriptive, narrative, and opinion…

Automated assessment using Natural Language Processing (NLP) has the potential to make English speaking assessments more reliable, authentic, and accessible. Yet without careful examination, NLP may exacerbate social prejudices based on gender or native language (L1). Current NLP-based assessments are prone to such biases, yet research and…

The advent of artificial intelligence (AI), particularly large language models (LLMs) like ChatGPT and Gemini, has significantly impacted the educational landscape, offering unique opportunities for learning and assessment. In the realm of written assessment grading, traditionally viewed as a laborious and subjective process, this study sought to…

As a spoken word unfolds over time, similar sounding words ("cap" and "cat") compete until one word "wins". Lexical competition becomes more efficient from infancy through adolescence. We examined one potential mechanism underlying this development: lexical inhibition, by which activated candidates suppress…

VocQGen is an automated tool designed to generate multiple-choice cloze (MCC) questions for vocabulary assessment in second language learning contexts. It leverages several natural language processing (NLP) tools and OpenAI's GPT-4 model to produce MCC items quickly from user-specified word lists. To evaluate its effectiveness, we used the first…

This study investigates whether re-thinking the separation of lexis and grammar in language testing could lead to more valid inferences about proficiency across modes. As argued by Römer, typical scoring rubrics ignore important information about proficiency encoded at the lexis-grammar interface, in particular how the co-selection of lexical and…

The present study investigated the speaking module of TOEFL iBT with an emphasis on the dichotomy of independent and integrated tasks. The potential differences between the two speaking conditions were intended to be explored based on the oral performance elicited from a group of Iranian test takers. To collect the required data, a simulated…

It has long been debated whether the Open-Book-Open-Web exam was useful and efficient as the traditional closed book exams. Some scholars and practitioners have doubted the efficiency and the possibility of cheating in the OBOW as it is not directly monitored. This paper tends to investigate the effectiveness of OBOW exams by comparing them with…

A key piece of a validity argument for a language assessment tool is clear overlap between assessment tasks and the target language use (TLU) domain (i.e., the domain description inference). The TOEFL 2000 Spoken and Written Academic Language (T2K-SWAL) corpus, which represents a variety of academic registers and disciplines in traditional…