research
∙
11/01/2022
CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation
The full power of human language-based communication cannot be realized ...
share
research
∙
10/24/2022
Does Self-Rationalization Improve Robustness to Spurious Correlations?
Rationalization is fundamental to human reasoning and learning. NLP mode...
research
∙
05/24/2022
On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization
Integrating vision and language has gained notable attention following t...
research
∙
11/16/2021
Few-Shot Self-Rationalization with Natural Language Prompts
Self-rationalization models that predict task labels and generate free-t...
research
∙
05/18/2021
Effective Attention Sheds Light On Interpretability
An attention matrix of a transformer self-attention sublayer can provabl...
research
∙
04/18/2021
Documenting the English Colossal Clean Crawled Corpus
As language models are trained on ever more text, researchers are turnin...
research
∙
02/24/2021
Teach Me to Explain: A Review of Datasets for Explainable NLP
Explainable NLP (ExNLP) has increasingly focused on collecting human-ann...
research
∙
12/31/2020
Promoting Graph Awareness in Linearized Graph-to-Text Generation
Generating text from structured inputs, such as meaning representations ...
research
∙
12/27/2020
Explaining NLP Models via Minimal Contrastive Editing (MiCE)
Humans give contrastive explanations that explain why an observed event ...
research
∙
10/24/2020
Measuring Association Between Labels and Free-Text Rationales
Interpretable NLP has taking increasing interest in ensuring that explan...
research
∙
10/15/2020
Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs
Natural language rationales could provide intuitive, higher-level explan...
research
∙
10/15/2020
Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI
Trust is a central component of the interaction between people and AI, i...
research
∙
10/06/2020
Easy, Reproducible and Quality-Controlled Data Collection with Crowdaq
High-quality and large-scale data are key to success for AI systems. How...
research
∙
04/23/2020
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
Language models pretrained on text from a wide variety of sources form t...
research
∙
08/16/2019
Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning
Machine comprehension of texts longer than a single sentence often requi...
research
∙
11/02/2017
SRL4ORL: Improving Opinion Role Labelling using Multi-task Learning with Semantic Role Labeling
For over 12 years, machine learning is used to extract opinion-holder-ta...
research
∙
06/07/2017
A Mention-Ranking Model for Abstract Anaphora Resolution
Resolving abstract anaphora is an important, but difficult task for text...
research
∙
08/18/2016