Gerard de Melo

Data Augmentation for Multiclass Utterance Classification – A Systematic Study

2020

Utterance classification is a key component in many conversational systems. However, classifying real-world user utterances is challenging, as people may express their ideas and thoughts in manifold ways, and the amount of training data for …

NL-Augmenter 🦎 → 🐍 A Framework for Task-Sensitive Natural Language Augmentation

2023 · Northern European Journal of Language Technology

Data augmentation is an important method for evaluating the robustness of and enhancing the diversity of training data for natural language processing (NLP) models. In this paper, we present NL-Augmenter, a new participatory Python-based natural …

Efficient Parallelization Layouts for Large-Scale Distributed Model Training

2023 · arXiv (Cornell University)

Efficiently training large language models requires parallelizing across hundreds of hardware accelerators and invoking various compute and memory optimizations. When combined, many of these strategies have complex interactions regarding the final training efficiency. Prior work …

Pretrained LLMs Learn Multiple Types of Uncertainty

2025 · arXiv (Cornell University)

Large Language Models are known to capture real-world knowledge, allowing them to excel in many downstream tasks. Despite recent advances, these models are still prone to what are commonly known as hallucinations, causing them to …

Relation Classification via Multi-Level Attention CNNs

2016

Relation classification is a crucial ingredient in numerous information extraction systems seeking to mine structured facts from text. We propose a novel convolutional neural network architecture for this task, relying on two levels of attention …

Reinforcement Knowledge Graph Reasoning for Explainable Recommendation

2019

Recent advances in personalized recommendation have sparked great interest in the exploitation of rich structured information provided by knowledge graphs. Unlike most existing approaches that only focus on leveraging knowledge graphs for more accurate recommendation, …

CAFE

2020

Recent research explores incorporating knowledge graphs (KG) into e-commerce recommender systems, not only to achieve better recommendation performance, but more importantly to generate explanations of why particular decisions are made. This can be achieved by …