565 citations · 1.2k across the 68 of their papers we have counts for
7 papers · 2 filters
ParsiNLU: A Suite of Language Understanding Challenges for Persian
Daniel Khashabi, Arman Cohan, Siamak Shakeri +22
Despite the progress made in recent years in addressing natural language understanding (NLU) challenges, the majority of this progress remains to be concentrated on resource-rich l…
UnQovering Stereotyping Biases via Underspecified Questions
Tao Li, Tushar Khot, Daniel Khashabi +2
While language embeddings have been shown to have stereotyping biases, how these biases affect downstream question answering (QA) models remains unexplored. We present UNQOVER, a g…
Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models
Tushar Khot, Daniel Khashabi, Kyle Richardson +2
We propose a general framework called Text Modular Networks(TMNs) for building interpretable systems that learn to solve complex tasks by decomposing them into simpler ones solvabl…
Temporal Common Sense Acquisition with Minimal Supervision
Ben Zhou, Qiang Ning, Daniel Khashabi +1
Temporal common sense (e.g., duration and frequency of events) is crucial for understanding natural language. However, its acquisition is challenging, partly because such informati…
UnifiedQA: Crossing Format Boundaries With a Single QA System
Daniel Khashabi, Sewon Min, Tushar Khot +4
Question answering (QA) tasks have been posed using a variety of formats, such as extractive span selection, multiple choice, etc. This has led to format-specialized models, and ev…
More Bang for Your Buck: Natural Perturbation for Robust Question Answering
Daniel Khashabi, Tushar Khot, Ashish Sabharwal
While recent models have achieved human-level scores on many NLP datasets, we observe that they are considerably sensitive to small changes in input. As an alternative to the stand…
Evaluating Models' Local Decision Boundaries via Contrast Sets
Matt Gardner, Yoav Artzi, Victoria Basmova +23
Standard test sets for supervised learning evaluate in-distribution generalization. Unfortunately, when a dataset has systematic gaps (e.g., annotation artifacts), these evaluation…