On the nature of explanation: An epistemological-linguistic perspective for explanation-based natural language inference
M Valentino, A Freitas - Philosophy & Technology, 2024 - Springer
One of the fundamental research goals for explanation-based Natural Language Inference
(NLI) is to build models that can reason in complex domains through the generation of …
(NLI) is to build models that can reason in complex domains through the generation of …
NLI4CT: Multi-evidence natural language inference for clinical trial reports
M Jullien, M Valentino, H Frost, P O'Regan… - arXiv preprint arXiv …, 2023 - arxiv.org
How can we interpret and retrieve medical evidence to support clinical decisions? Clinical
trial reports (CTR) amassed over the years contain indispensable information for the …
trial reports (CTR) amassed over the years contain indispensable information for the …
Few-shot out-of-domain transfer learning of natural language explanations in a label-abundant setup
Training a model to provide natural language explanations (NLEs) for its predictions usually
requires the acquisition of task-specific NLEs, which is time-and resource-consuming. A …
requires the acquisition of task-specific NLEs, which is time-and resource-consuming. A …
Improving semantic control in discrete latent spaces with transformer quantized variational autoencoders
Achieving precise semantic control over the latent spaces of Variational AutoEncoders
(VAEs) holds significant value for downstream tasks in NLP as the underlying generative …
(VAEs) holds significant value for downstream tasks in NLP as the underlying generative …
[PDF][PDF] Nellie: A neuro-symbolic inference engine for grounded, compositional, and explainable reasoning
Our goal is to develop a modern approach to answering questions via systematic reasoning
where answers are supported by human interpretable proof trees grounded in an NL corpus …
where answers are supported by human interpretable proof trees grounded in an NL corpus …
Reasoning with Natural Language Explanations
M Valentino, A Freitas - arXiv preprint arXiv:2410.04148, 2024 - arxiv.org
Explanation constitutes an archetypal feature of human rationality, underpinning learning
and generalisation, and representing one of the media supporting scientific discovery and …
and generalisation, and representing one of the media supporting scientific discovery and …
Leveraging Non-Parametric Reasoning with Large Language Models for Enhanced Knowledge Graph Completion
Y Zhang, YP Shen, G Xiao, JH Peng - IEEE Access, 2024 - ieeexplore.ieee.org
The completeness of knowledge graphs is critical to their effectiveness across various
applications. However, existing knowledge graph completion methods face challenges such …
applications. However, existing knowledge graph completion methods face challenges such …
[HTML][HTML] Case-Based Deduction for Entailment Tree Generation
Maintaining logical consistency in structured explanations is critical for understanding and
troubleshooting the reasoning behind a system's decisions. However, existing methods for …
troubleshooting the reasoning behind a system's decisions. However, existing methods for …
[PDF][PDF] Introductory Tutorial: Reasoning with Natural Language Explanations
M Valentino, A Freitas - Proceedings of the 2024 Conference on …, 2024 - aclanthology.org
Explanation constitutes an archetypal feature of human rationality, underpinning learning,
and generalisation, and representing one of the media supporting scientific discovery and …
and generalisation, and representing one of the media supporting scientific discovery and …
Scientific explanation and natural language: A unified epistemological-linguistic perspective for explainable ai
M Valentino, A Freitas - arXiv preprint arXiv:2205.01809, 2022 - arxiv.org
A fundamental research goal for Explainable AI (XAI) is to build models that are capable of
reasoning through the generation of natural language explanations. However, the …
reasoning through the generation of natural language explanations. However, the …