Explanation Generation
61 papers with code • 5 benchmarks • 9 datasets
Benchmarks
These leaderboards are used to track progress in Explanation Generation
Libraries
Use these libraries to find Explanation Generation models and implementationsDatasets
VCR
e-SNLI-VE
E-KAR
CLEVR-X
SuMe
WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images
ExPUNations
E-ReDial
SpanEX
Most implemented papers
Explainable Automated Fact-Checking for Public Health Claims
neemakot/Health-Fact-Checking
•
•
EMNLP 2020
We present the first study of explainable fact-checking for claims which require specific expertise.
AR-BERT: Aspect-relation enhanced Aspect-level Sentiment Classification with Multi-modal Explanations
We propose AR-BERT, a novel two-level global-local entity embedding scheme that allows efficient joint training of KG-based aspect embeddings and ALSC models.
TE2Rules: Explaining Tree Ensembles using Rules
Tree Ensemble (TE) models, such as Gradient Boosted Trees, often achieve optimal performance on tabular datasets, yet their lack of transparency poses challenges for comprehending their decision logic.
Explaining Patterns in Data with Language Models via Interpretable Autoprompting
csinva/imodelsX
•
•
Large language models (LLMs) have displayed an impressive ability to harness natural language to perform complex tasks.
Explaining black box text modules in natural language with language models
csinva/imodelsX
•
•
Here, we ask whether we can automatically obtain natural language explanations for black box text modules.
Red Dragon AI at TextGraphs 2019 Shared Task: Language Model Assisted Explanation Generation
The TextGraphs-13 Shared Task on Explanation Regeneration asked participants to develop methods to reconstruct gold explanations for elementary science questions.
QED: A Framework and Dataset for Explanations in Question Answering
A question answering system that in addition to providing an answer provides an explanation of the reasoning that leads to that answer has potential advantages in terms of debuggability, extensibility and trust.
Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?
peterbhase/LAS-NL-Explanations
•
•
Findings of the Association for Computational Linguistics 2020
We provide code for the experiments in this paper at https://github. com/peterbhase/LAS-NL-Explanations
Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification
Much of modern-day text simplification research focuses on sentence-level simplification, transforming original, more complex sentences into simplified versions.
Towards Interpretable Natural Language Understanding with Explanations as Latent Variables
JamesHujy/ELV
•
•
NeurIPS 2020
In this paper, we develop a general framework for interpretable natural language understanding that requires only a small set of human annotated explanations for training.
