Alert button
Picture for Ana Marasović

Ana Marasović

Alert button

Whispers of Doubt Amidst Echoes of Triumph in NLP Robustness

Nov 16, 2023
Ashim Gupta, Rishanth Rajendhran, Nathan Stringham, Vivek Srikumar, Ana Marasović

Viaarxiv icon

How Much Consistency Is Your Accuracy Worth?

Oct 20, 2023
Jacob K. Johnson, Ana Marasović

Viaarxiv icon

CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation

Nov 01, 2022
Abhilasha Ravichander, Matt Gardner, Ana Marasović

Figure 1 for CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation
Figure 2 for CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation
Figure 3 for CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation
Figure 4 for CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation
Viaarxiv icon

Does Self-Rationalization Improve Robustness to Spurious Correlations?

Oct 24, 2022
Alexis Ross, Matthew E. Peters, Ana Marasović

Figure 1 for Does Self-Rationalization Improve Robustness to Spurious Correlations?
Figure 2 for Does Self-Rationalization Improve Robustness to Spurious Correlations?
Figure 3 for Does Self-Rationalization Improve Robustness to Spurious Correlations?
Figure 4 for Does Self-Rationalization Improve Robustness to Spurious Correlations?
Viaarxiv icon

Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contest

Sep 13, 2022
Jack Hessel, Ana Marasović, Jena D. Hwang, Lillian Lee, Jeff Da, Rowan Zellers, Robert Mankoff, Yejin Choi

Figure 1 for Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contest
Figure 2 for Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contest
Figure 3 for Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contest
Figure 4 for Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contest
Viaarxiv icon

Few-Shot Self-Rationalization with Natural Language Prompts

Nov 16, 2021
Ana Marasović, Iz Beltagy, Doug Downey, Matthew E. Peters

Figure 1 for Few-Shot Self-Rationalization with Natural Language Prompts
Figure 2 for Few-Shot Self-Rationalization with Natural Language Prompts
Figure 3 for Few-Shot Self-Rationalization with Natural Language Prompts
Figure 4 for Few-Shot Self-Rationalization with Natural Language Prompts
Viaarxiv icon

Effective Attention Sheds Light On Interpretability

May 18, 2021
Kaiser Sun, Ana Marasović

Figure 1 for Effective Attention Sheds Light On Interpretability
Figure 2 for Effective Attention Sheds Light On Interpretability
Figure 3 for Effective Attention Sheds Light On Interpretability
Figure 4 for Effective Attention Sheds Light On Interpretability
Viaarxiv icon

Teach Me to Explain: A Review of Datasets for Explainable NLP

Mar 01, 2021
Sarah Wiegreffe, Ana Marasović

Figure 1 for Teach Me to Explain: A Review of Datasets for Explainable NLP
Figure 2 for Teach Me to Explain: A Review of Datasets for Explainable NLP
Figure 3 for Teach Me to Explain: A Review of Datasets for Explainable NLP
Figure 4 for Teach Me to Explain: A Review of Datasets for Explainable NLP
Viaarxiv icon

Promoting Graph Awareness in Linearized Graph-to-Text Generation

Dec 31, 2020
Alexander Hoyle, Ana Marasović, Noah Smith

Figure 1 for Promoting Graph Awareness in Linearized Graph-to-Text Generation
Figure 2 for Promoting Graph Awareness in Linearized Graph-to-Text Generation
Figure 3 for Promoting Graph Awareness in Linearized Graph-to-Text Generation
Figure 4 for Promoting Graph Awareness in Linearized Graph-to-Text Generation
Viaarxiv icon