This paper systematically explores how Large Language Models (LLMs) generate explanations of code examples of the type used in intro-to-programming courses. As we show, the nature of code explanations generated by LLMs varies considerably based on the wording of the prompt, the target code examples being explained, the programming language, the…

Large language models (LLMs), such as Codex, hold great promise in enhancing programming education by automatically generating feedback for students. We investigate using LLMs to generate feedback for fixing syntax errors in Python programs, a key scenario in introductory programming. More concretely, given a student's buggy program, our goal is…

Worked examples, which present an explained code for solving typical programming problems are among the most popular types of learning content in programming classes. Most approaches and tools for presenting these examples to students are based on line-by-line explanations of the example code. However, instructors rarely have time to provide…

The purpose of the present study is to find out the extent to which the real spoken language is reflected in TV series in terms of vocabulary. In accordance with this purpose, a corpus, named as the British TV Series Corpus (BTSC) was compiled for the present study using two British TV series, Sherlock and Doctor Who, and this corpus was compared…

Language learners are underserved if there are unlearned meanings of a word that they think they have already learned. For example, "circle" as a noun is well known, whereas its use as a verb is not. For artificial-intelligence-based support systems for learning vocabulary, assessing each learner's knowledge of such atypical but common…

Collaborative problem solving in computer-supported environments is of critical importance to the modern workforce. Coworkers or collaborators must be able to co-create and navigate a shared problem space using discourse and non-verbal cues. Analyzing this discourse can give insights into how consensus is reached and can estimate the depth of…

Different computational models for generating analogies of the form "A is to B as C is to D" have been proposed over the past 35 years. However, analogy generation is a challenging problem that requires further research. In this article, we present a new approach for generating analogies in Multiple Choice Question (MCQ) format that can be used…

This paper describes a computerized system for tagging language corpora that accommodates the special conditions in Bulgarian language research (notably, lack of advanced technology and corresponding user knowledge). SUPERLINGUA has been developed in the DOS environment with consideration for these conditions. Information on product use, users,…

The demand for extensive reusability of large language text collections for natural languages processing research requires development of standardized encoding formats. Such formats must be capable of representing different kinds of information across the spectrum of text types and languages, capable of representing different levels of…

An experiment compared the tagging of two languages: Czech, a highly inflected language with a high degree of ambiguity, and English. For Czech, the corpus was one gathered in the 1970s at the Czechoslovak Academy of Sciences; for English, it was the Wall Street Journal corpus. Results indicate 81.53 percent accuracy for Czech and 96.83 percent…

Trends and developments in computer applications in Chinese language research are described, focusing on these areas: input of Chinese characters and Chinese corpus; automatic segmentation of Chinese written text in corpus; development of a grammar knowledge base for Chinese words to be used as a resource for text segmentation and corpus…