Related papers: Transfer Learning for Automated Feedback Generatio…
In multi-stage processes, decisions happen in an ordered sequence of stages. Many of them have the structure of dual funnel problem: as the sample size decreases from one stage to the other, the information increases. A related example is a…
Training large-scale question answering systems is complicated because training sources usually cover a small portion of the range of possible questions. This paper studies the impact of multitask and transfer learning for simple question…
Neural conversation models have shown great potentials towards generating fluent and informative responses by introducing external background knowledge. Nevertheless, it is laborious to construct such knowledge-grounded dialogues, and…
We present a method to control a text-to-image generative model to produce training data useful for supervised learning. Unlike previous works that employ an open-loop approach and pre-define prompts to generate new data using either a…
This study illustrates how incorporating feedback-oriented annotations into the scoring pipeline can enhance the accuracy of automated essay scoring (AES). This approach is demonstrated with the Persuasive Essays for Rating, Selecting, and…
This study investigates the use of generative AI and multi-agent systems to provide automatic feedback in educational contexts, particularly for student constructed responses in science assessments. The research addresses a key gap in the…
Effective and timely feedback in educational assessments is essential but labor-intensive, especially for complex tasks. Recent developments in automated feedback systems, ranging from deterministic response grading to the evaluation of…
High-quality instruction-tuning data is crucial for developing Large Language Models (LLMs) that can effectively navigate real-world tasks and follow human instructions. While synthetic data generation offers a scalable approach for…
Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks. For example in speech recognition, an acoustic model trained for one language can be used to recognize speech in…
In this paper, we demonstrate the efficacy of transfer learning and continuous learning for various automatic speech recognition (ASR) tasks. We start with a pre-trained English ASR model and show that transfer learning can be effectively…
Humans can learn from very few samples, demonstrating an outstanding generalization ability that learning algorithms are still far from reaching. Currently, the most successful models demand enormous amounts of well-labeled data, which are…
In this paper, we present strong baselines for the task of Feedback Comment Generation for Writing Learning. Given a sentence and an error span, the task is to generate a feedback comment explaining the error. Sentences and feedback…
Parameter-Efficient Transfer Learning (PETL) aims at efficiently adapting large models pre-trained on massive data to downstream tasks with limited task-specific data. In view of the practicality of PETL, previous works focus on tuning a…
Today, most large-scale conversational AI agents (e.g. Alexa, Siri, or Google Assistant) are built using manually annotated data to train the different components of the system. Typically, the accuracy of the ML models in these components…
Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled datasets that are relevant for a downstream task. We propose…
Given the increasing availability of RNA-seq data and its complex and heterogeneous nature, there has been growing interest in applying AI/machine learning methodologies to work with such data modalities. However, because omics data is…
Transfer learning, also referred as knowledge transfer, aims at reusing knowledge from a source dataset to a similar target one. While many empirical studies illustrate the benefits of transfer learning, few theoretical results are…
Current natural language processing models work well on a single task, yet they often fail to continuously learn new tasks without forgetting previous ones as they are re-trained throughout their lifetime, a challenge known as lifelong…
High-quality computer science education is limited by the difficulty of providing instructor feedback to students at scale. While this feedback could in principle be automated, supervised approaches to predicting the correct feedback are…
The structure of the majority of modern deep neural networks is characterized by uni- directional feed-forward connectivity across a very large number of layers. By contrast, the architecture of the cortex of vertebrates contains fewer…