While large language models (LLMs) continue to grow in scale and gain new zero-shot capabilities, their performance for languages beyond English increasingly lags behind. This gap is due to the "curse of multilinguality," where multilingual language models perform worse on individual languages than a monolingual model trained on that…

The essence of human intelligence lies in its ability to learn continuously, accumulating past knowledge to aid in future learning and problem-solving endeavors. In contrast, the current machine learning paradigm often operates in isolation, lacking the capacity for continual learning and adaptation. This deficiency becomes apparent in the face of…

Exam evaluations are essential to assessing students' knowledge and progress in a subject or course. To meet learning objectives and assess student performance, questions must be themed. Automatic Question Generation (AQG) is our novel approach to this problem. A comprehensive process for autonomously generating Bahasa Indonesia text questions is…

Automatic essay scoring (AES) is an essential educational application in natural language processing. This automated process will alleviate the burden by increasing the reliability and consistency of the assessment. With the advances in text embedding libraries and neural network models, AES systems achieved good results in terms of accuracy.…

The idea that a vocabulary is a network of words is one that has become a common theme of the second language (L2) vocabulary research literature. However, not many people have considered the wider implications of this powerful metaphor. This paper is the first in a series of workshops that examines some of these implications. In this first…

ChatGPT, as an example of generative artificial intelligence, possesses high-level conversational and problem-solving capabilities supported by powerful computational models and big data. However, the powerful performance of ChatGPT might enhance learner dependency. Although it has not yet been confirmed, many teachers and scholars are also…

While investigating plagiarism is relevant in different fields, verification of original authorship has also attracted attention in academia and L2 learning and assessment contexts. Generally associated with academic misconduct and dishonesty, plagiarism in writing can take many shapes and be hard to detect. In addition to being a very…

Text comprehension is an essential skill in today's information-rich world, and self-explanation practice helps students improve their understanding of complex texts. This study was centered on leveraging open-source Large Language Models (LLMs), specifically FLAN-T5, to automatically assess the comprehension strategies employed by readers while…

Large language models such as ChatGPT can be seen as a major threat to reliable assessment in higher education. In this point of departure, I argue that these tools are a major game changer for society at large. Many of the jobs we now consider highly skilled are based on pattern recognition that can much more reliably be carried by fine-tuned…

This study explores the use of Large Language Models (LLMs), specifically GPT-4, in analysing classroom dialogue--a key task for teaching diagnosis and quality improvement. Traditional qualitative methods are both knowledge- and labour-intensive. This research investigates the potential of LLMs to streamline and enhance this process. Using…

Decades of psycholinguistics research have shown that human sentence processing is highly incremental and predictive. This has provided evidence for expectation-based theories of sentence processing, which posit that the processing difficulty of linguistic material is modulated by its probability in context. However, these theories do not make…

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…

The thriving developer community has a significant impact on the widespread use of R software. To better understand this community, we conducted a study analyzing all R packages available on CRAN. We identified the most popular topics of R packages by text mining the package descriptions. Additionally, using network centrality measures, we…

Purpose: ParAlg (Paraphasia Algorithms) is a software that automatically categorizes a person with aphasia's naming error (paraphasia) in relation to its intended target on a picture-naming test. These classifications (based on lexicality as well as semantic, phonological, and morphological similarity to the target) are important for…

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…