Search Results for author:
Found 12 papers, 11 papers with code
Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods
Saliency maps can explain a neural model's predictions by identifying important input features.
Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools
To facilitate research, we present Thermostat which consists of a large collection of model explanations and accompanying analysis tools.
Defx at SemEval-2020 Task 6: Joint Extraction of Concepts and Relations for Definition Extraction
Definition Extraction systems are a valuable knowledge source for both humans and algorithms.
Efficient Explanations from Empirical Explainers
Amid a discussion about Green AI in which we see explainability neglected, we explore the possibility to efficiently approximate computationally expensive explainers.
Pattern-Guided Integrated Gradients
In this work, we combine the two methods into a new method, Pattern-Guided Integrated Gradients (PGIG).
Evaluating German Transformer Language Models with Syntactic Agreement Tests
Most of the studies were conducted for the English language, however.
Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling
The results of our models are compared to a baseline and the state-of-the-art models on the CNN/Daily Mail dataset.
Layerwise Relevance Visualization in Convolutional Text Graph Classifiers
Representations in the hidden layers of Deep Neural Networks (DNN) are often hard to interpret since it is difficult to project them into an interpretable domain.
Neural Vector Conceptualization for Word Vector Space Interpretation
Distributed word vector spaces are considered hard to interpret which hinders the understanding of natural language processing (NLP) models.
Train, Sort, Explain: Learning to Diagnose Translation Models
Evaluating translation models is a trade-off between effort and detail.
Learning Explanations from Language Data
PatternAttribution is a recent method, introduced in the vision domain, that explains classifications of deep neural networks.
Cube-Cut: Vertebral Body Segmentation in MRI-Data through Cubic-Shaped Divergences
The Cube-Cut algorithm generates a directed graph with two terminal nodes (s-t-network), where the nodes of the graph correspond to a cubic-shaped subset of the image's voxels.
