Pasquale Minervini
8 papers in the PaperMetrix corpus
Papers by this author
-
NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
2019 · arXiv (Cornell University)
Rule-based models are attractive for various tasks because they inherently lead to interpretable and explainable decisions and can easily incorporate prior knowledge. However, such systems are difficult to apply to problems involving natural language, due …
-
Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions
2021 · arXiv (Cornell University)
Combining discrete probability distributions and combinatorial optimization problems with neural network components has numerous applications but poses several challenges. We propose Implicit Maximum Likelihood Estimation (I-MLE), a framework for end-to-end learning of models combining discrete …
-
Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Models
2022 · arXiv (Cornell University)
Current Natural Language Inference (NLI) models achieve impressive results, sometimes outperforming humans when evaluating on in-distribution test sets. However, as these models are known to learn from annotation artefacts and dataset biases, it is unclear …
-
Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domain
2023 · arXiv (Cornell University)
Adapting pretrained language models to novel domains, such as clinical applications, traditionally involves retraining their entire set of parameters. Parameter-Efficient Fine-Tuning (PEFT) techniques for fine-tuning language models significantly reduce computational requirements by selectively fine-tuning small …
-
Answerability in Retrieval-Augmented Open-Domain Question Answering
2024 · arXiv (Cornell University)
The performance of Open-Domain Question Answering (ODQA) retrieval systems can exhibit sub-optimal behavior, providing text excerpts with varying degrees of irrelevance. Unfortunately, many existing ODQA datasets lack examples specifically targeting the identification of irrelevant text …
-
Edinburgh Clinical NLP at SemEval-2024 Task 2: Fine-tune your model unless you have access to GPT-4
2024 · arXiv (Cornell University)
The NLI4CT task assesses Natural Language Inference systems in predicting whether hypotheses entail or contradict evidence from Clinical Trial Reports. In this study, we evaluate various Large Language Models (LLMs) with multiple strategies, including Chain-of-Thought, …
-
Enhancing neural link predictors for temporal knowledge graphs with temporal regularisers
2025
The problem of link prediction in temporal knowledge graphs (TKGs) consists of finding missing links in the knowledge base under temporal constraints.Recently, [4] and [8] proposed a solution to the problem inspired by the canonical …
-
Adversarially Regularising Neural
2018
Adversarial examples are inputs to machine learning models designed to cause the model to make a mistake. They are useful for understanding the shortcomings of machine learning models, interpreting their results, and for regularisation. In …