Adversarial Sets for Regularising Neural Link Predictors
Paper • 1707.07596 • Published
AI & ML interests
We do research in all core areas of natural language processing, including morphology, parsing, semantics, discourse, language generation, and machine translation. EdinburghNLP also has a strong track record of work at the interface of NLP with other areas, including speech technology, machine learning, computer vision, cognitive modeling, social media, information retrieval, robotics, bioinformatics, and educational technology.
Recent Activity
View all activity
Papers
Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered
VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models
pminervini
authored 20
papers 17 days ago
Extrapolation in NLP
Paper • 1805.06648 • Published
Jack the Reader - A Machine Reading Framework
Paper • 1806.08727 • Published
Towards Neural Theorem Proving at Scale
Paper • 1807.08204 • Published
Embedding Cardinality Constraints in Neural Link Predictors
Paper • 1812.06455 • Published
Neural Variational Inference For Estimating Uncertainty in Knowledge Graph Embeddings
Paper • 1906.04985 • Published
Differentiable Reasoning on Large Knowledge Bases and Natural Language
Paper • 1912.10824 • Published
Undersensitivity in Neural Reading Comprehension
Paper • 2003.04808 • Published
Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training
Paper • 2004.07790 • Published
Knowledge Graph Embeddings and Explainable AI
Paper • 2004.14843 • Published
WordCraft: An Environment for Benchmarking Commonsense Agents
Paper • 2007.09185 • Published
Don't Read Too Much into It: Adaptive Computation for Open-Domain Question Answering
Paper • 2011.05435 • Published
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Paper • 2101.00133 • Published
Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models
Paper • 2101.09688 • Published
Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning
Paper • 2102.04220 • Published
Combining Inductive and Deductive Reasoning for Query Answering over Incomplete Knowledge Graphs
Paper • 2106.14052 • Published
Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints
Paper • 2107.02102 • Published
Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations
Paper • 2110.02834 • Published
A Probabilistic Framework for Knowledge Graph Data Augmentation
Paper • 2110.13205 • Published
Differentiable Reasoning over Long Stories -- Assessing Systematic Generalisation in Neural Models
Paper • 2203.10620 • Published