Related papers: Mining patterns in syntax trees to automate code r…
As text and code resources have expanded, large-scale pre-trained models have shown promising capabilities in code generation tasks, typically employing supervised fine-tuning with problem statement-program pairs. However, increasing model…
Post-training (via supervised fine-tuning) improves instruction-following, but often induces semantic mode collapse by biasing models toward low-entropy fine-tuning data at the expense of the high-entropy pretraining distribution.…
Automated grading systems, or auto-graders, have become ubiquitous in programming education, and the way they generate feedback has become increasingly automated as well. However, there is insufficient evidence regarding auto-grader…
In essence, embedding algorithms work by optimizing the distance between a word and its usual context in order to generate an embedding space that encodes the distributional representation of words. In addition to single words or word…
With the surging inclination towards carrying out tasks on computational devices and digital mediums, any method that converts a task that was previously carried out manually, to a digitized version, is always welcome. Irrespective of the…
The assessment of program functionality can generally be accomplished with straight-forward unit tests. However, assessing the design quality of a program is a much more difficult and nuanced problem. Design quality is an important…
A major challenge in the field of Text Generation is evaluation: Human evaluations are cost-intensive, and automated metrics often display considerable disagreement with human judgments. In this paper, we propose a statistical model of Text…
The most common method to auto-grade a student's submission in a CS1 or a CS2 course is to run it against a pre-defined test suite and compare the results against reference results. However, this technique cannot be used if the correctness…
This paper presents a case study to examine the affinity of the code review process among young developers in an academic setting. Code review is indispensable considering the positive outcomes it generates. However, it is not an individual…
Code super-optimization is the task of transforming any given program to a more efficient version while preserving its input-output behaviour. In some sense, it is similar to the paraphrase problem from natural language processing where the…
Sequence-to-sequence learning involves a trade-off between signal strength and annotation cost of training data. For example, machine translation data range from costly expert-generated translations that enable supervised learning, to weak…
Retrieval-based conversation systems generally tend to highly rank responses that are semantically similar or even identical to the given conversation context. While the system's goal is to find the most appropriate response, rather than…
In this paper, we introduce a collaborative and modern annotation tool for audio and speech: audino. The tool allows annotators to define and describe temporal segmentation in audios. These segments can be labelled and transcribed easily…
Measuring user satisfaction level is a challenging task, and a critical component in developing large-scale conversational agent systems serving the needs of real users. An widely used approach to tackle this is to collect human annotation…
Auto-annotation by ensemble of models is an efficient method of learning on unlabeled data. Wrong or inaccurate annotations generated by the ensemble may lead to performance degradation of the trained model. To deal with this problem we…
This project examines the prospect of using AI-generated feedback as suggestions to expedite and enhance human instructors' feedback provision. In particular, we focus on understanding the teaching assistants' perspectives on the quality of…
In large organisations, identifying experts on a given topic is crucial in leveraging the internal knowledge spread across teams and departments. So-called enterprise expert retrieval systems automatically discover and structure employees'…
Recent advances in Large Language Models (LLMs) have shown promise in automating discourse annotation for conversations. While manually designing tree annotation schemes significantly improves annotation quality for humans and models, their…
Active learning algorithms automatically identify the most informative samples from large amounts of unlabeled data and tremendously reduce human annotation effort in inducing a machine learning model. In a conventional active learning…
Student repetition in secondary education imposes significant resource burdens, particularly in resource-constrained contexts. Addressing this challenge, this study introduces a unified machine learning framework that simultaneously…