66 citations · 95 across the 11 of their papers we have counts for
18 papers
CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation
Abhilasha Ravichander, Matt Gardner, Ana Marasović
The full power of human language-based communication cannot be realized without negation. All human languages have some form of negation. Despite this, negation remains a challengi…
Does Self-Rationalization Improve Robustness to Spurious Correlations?
Alexis Ross, Matthew E. Peters, Ana Marasović
Rationalization is fundamental to human reasoning and learning. NLP models trained to produce rationales along with predictions, called self-rationalization models, have been inves…
Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contest
Jack Hessel, Ana Marasović, Jena D. Hwang +5
Large neural networks can now generate jokes, but do they really "understand" humor? We challenge AI models with three tasks derived from the New Yorker Cartoon Caption Contest: ma…
On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization
Shruti Palaskar, Akshita Bhagia, Yonatan Bisk +3
Combining the visual modality with pretrained language models has been surprisingly effective for simple descriptive tasks such as image captioning. More general text generation ho…
Few-Shot Self-Rationalization with Natural Language Prompts
Ana Marasović, Iz Beltagy, Doug Downey +1
Self-rationalization models that predict task labels and generate free-text elaborations for their predictions could enable more intuitive interaction with NLP systems. These model…
Effective Attention Sheds Light On Interpretability
Kaiser Sun, Ana Marasović
An attention matrix of a transformer self-attention sublayer can provably be decomposed into two components and only one of them (effective attention) contributes to the model outp…
Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing
Sarah Wiegreffe, Ana Marasović
Explainable NLP (ExNLP) has increasingly focused on collecting human-annotated textual explanations. These explanations are used downstream in three ways: as data augmentation to i…
Promoting Graph Awareness in Linearized Graph-to-Text Generation
Alexander Hoyle, Ana Marasović, Noah Smith
Generating text from structured inputs, such as meaning representations or RDF triples, has often involved the use of specialized graph-encoding neural networks. However, recent ap…
Explaining NLP Models via Minimal Contrastive Editing (MiCE)
Alexis Ross, Ana Marasović, Matthew E. Peters
Humans have been shown to give contrastive explanations, which explain why an observed event happened rather than some other counterfactual event (the contrast case). Despite the i…
Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs
Ana Marasović, Chandra Bhagavatula, Jae Sung Park +3
Natural language rationales could provide intuitive, higher-level explanations that are easily understandable by humans, complementing the more broadly studied lower-level explanat…
Easy, Reproducible and Quality-Controlled Data Collection with Crowdaq
Qiang Ning, Hao Wu, Pradeep Dasigi +5
High-quality and large-scale data are key to success for AI systems. However, large-scale data annotation efforts are often confronted with a set of common challenges: (1) designin…
Measuring Association Between Labels and Free-Text Rationales
Sarah Wiegreffe, Ana Marasović, Noah A. Smith
In interpretable NLP, we require faithful rationales that reflect the model's decision-making process for an explained instance. While prior work focuses on extractive rationales (…
Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI
Alon Jacovi, Ana Marasović, Tim Miller +1
Trust is a central component of the interaction between people and AI, in that 'incorrect' levels of trust may cause misuse, abuse or disuse of the technology. But what, precisely,…
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
Suchin Gururangan, Ana Marasović, Swabha Swayamdipta +4
Language models pretrained on text from a wide variety of sources form the foundation of today's NLP. In light of the success of these broad-coverage models, we investigate whether…
Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning
Pradeep Dasigi, Nelson F. Liu, Ana Marasović +2
Machine comprehension of texts longer than a single sentence often requires coreference resolution. However, most current reading comprehension benchmarks do not contain complex co…
SRL4ORL: Improving Opinion Role Labeling using Multi-task Learning with Semantic Role Labeling
Ana Marasović, Anette Frank
For over a decade, machine learning has been used to extract opinion-holder-target structures from text to answer the question "Who expressed what kind of sentiment towards what?".…
A Mention-Ranking Model for Abstract Anaphora Resolution
Ana Marasović, Leo Born, Juri Opitz +1
Resolving abstract anaphora is an important, but difficult task for text understanding. Yet, with recent advances in representation learning this task becomes a more tangible aim.…
Multilingual Modal Sense Classification using a Convolutional Neural Network
Ana Marasović, Anette Frank
Modal sense classification (MSC) is a special WSD task that depends on the meaning of the proposition in the modal's scope. We explore a CNN architecture for classifying modal sens…