Novice programmers frequently struggle with compilation errors, and providing precise and targeted feedback in the IDE still remains a challenge. Although prior studies have established a foundation for error taxonomies, existing frameworks have been constrained by limited category granularity or the reliance on expert annotation. We address these limitations by introducing a novel hybrid labeling methodology based on the large-scale IBM Code Net dataset. Our approach utilizes Large Language Models (LLMs) to significantly reduce human annotation efforts while providing comprehensive categories that enable our classifier to distinguish between unintentional mistakes and knowledge gaps. This granular classification is crucial for downstream tasks, allowing feedback to focus on the root cause of compile errors. Subsequently, we evaluated several pretrained language models to identify the most effective classifier architecture. Ultimately, this work lays the foundation for intelligent tutoring systems capable of delivering precise, targeted, and real-time interaction with novice programmers.

Novice programmers often get stuck while programming and debugging. They would turn to AI tools like ChatGPT for help when instructors or teaching assistants (TA) are unavailable. However, conventional AI tools give away answers too easily, which undermines the learning process. This project aims to solve the lack of guided support for novice programmers by developing a learning-centered intelligent tutoring system. This system mimics human TAs by asking guiding questions to build problem solving skills and deeper understanding. Integrated into an online IDE, this AI tutor leverages error categories to deliver context-sensitive feedback in real time to keep students engaged. To ensure accessibility and control, the system uses smaller, locally deployable models rather than relying solely on proprietary services. By avoiding overreliance on AI-generated solutions, the system aims to sustain engagement, reduce frustration, and foster independent learning.

In recent years, Conditional Random Fields (CRFs) have been examined as a statistical model for speech recognition. In this paper, we explore the use of features derived via CRFs as inputs to a Tandem-style HMM ASR system (that is, a Crandem system). We present a model for deriving frame-level posterior features via CRFs to use in Crandem modeling and additionally provide experimental results that show the Crandem system can slightly significantly outperform both a comparable Tandem system and a comparable CRF system on the task of phone recognition.

Conditional random fields (CRFs) are a statistical framework that has recently gained in popularity in both the automatic speech recognition (ASR) and natural language processing communities because of the different nature of assumptions that are made in predicting sequences of labels compared to the more traditional hidden Markov model (HMM). In the ASR community, CRFs have been employed in a method similar to that of HMMs, using the sufficient statistics of input data to compute the probability of label sequences given acoustic input. In this paper, we explore the application of CRFs to combine local posterior estimates provided by multilayer perceptrons (MLPs) corresponding to the frame-level prediction of phone classes and phonological attribute classes. We compare phonetic recognition using CRFs to an HMM system trained on the same input features and show that the monophone label CRF is able to achieve superior performance to a monophone-based HMM and performance comparable to a 16 Gaussian mixture triphone-based HMM; in both of these cases, the CRF obtains these results with far fewer free parameters. The CRF is also able to better combine these posterior estimators, achieving a substantial increase in performance over an HMM-based triphone system by mixing the two highly correlated sets of phone class and phonetic attribute class posteriors.

In our prior work with conditional random fields (CRFs), we have shown that it is possible to achieve results in the phonetic recognition task with a CRF that approach the results of a similarly trained HMM system (but with many fewer parameters), and we have shown that using two different feature sets that are supposedly redundant gives an improvement in the performance of the CRF. In this paper, we explore two new areas with our CRF model. First, we show that by using two feature sets that are just transforms of each other, we achieve an improvement of results in the CRF model. Second, we show that by adding a single pass of realignment to our CRF model training, we achieve an accuracy result in the phone recognition task that is superior to that of an HMM system trained with triphone labels, despite only training the CRF on monophone labels with no explicit triphonic context.

We present methods of detector design in the Automatic Speech Attribute Transcription project. This paper details the results of a student-led, cross-site collaboration between Georgia Institute of Technology, The Ohio State University and Rutgers University. The work reported in this paper describes and evaluates the detection-based ASR paradigm and discusses phonetic attribute classes, methods of detecting framewise phonetic attributes and methods of combining attribute detectors for ASR. We use Multi-Layer Perceptrons, Hidden Markov Models and Support Vector Machines to compute confidence scores for several prescribed sets of phonetic attribute classes. We use Conditional Random Fields (CRFs) and knowledge-based rescoring of phone lattices to combine framewise detection scores for continuous phone recognition on the TIMIT database. With CRFs, we achieve a phone accuracy of 70.63%, outperforming the baseline and enhanced HMM systems, by incorporating all of the attribute detectors discussed in the paper

A Conditional Random Field is a mathematical model for sequences that is similar in many ways to a Hidden Markov Model, but is discriminative rather than generative in nature. In this paper, we explore the application of the CRF model to ASR processing of discriminative phonetic features by building a system that performs first-pass phonetic recognition using discriminatively trained phonetic features. With this system, we show that this CRF model achieves an accuracy level in a phone recognition task that is superior to a similarly trained HMM model. Index Terms: speech recognition, conditional random fields.

We present a storage-efficient and computationally fast method for rapid navigation/browsing through large image repositories and for content-based image retrieval. In the developed system, multiple resolution, orientation achromatic, and opponent chromatic channels are sequentially encoded by a maximal information sensory encoding model, which conveniently and effectively indexes the images into a binary tree data structure. Content-based image retrieval, database navigation, and image browsing are done very efficiently and rapidly by manipulating the n-bit binary keys in the binary tree data structure. We present experimental results to demonstrate the effectiveness of our method.