A Survey of Adversarial Defenses and Robustness in NLP
In the past few years, it has become increasingly evident that deep neural networks are not resilient enough to withstand adversarial perturbations in input data, leaving them vulnerable to attack. Various authors have proposed strong adversarial attacks
Balaraman Ravindran
exaly +2 more sources
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks [PDF]
How well can NLP models generalize to a variety of unseen tasks when provided with task instructions? To address this question, we first introduce Super-NaturalInstructions, a benchmark of 1,616 diverse NLP tasks and their expert-written instructions ...
Yizhong Wang +39 more
semanticscholar +1 more source
Are NLP Models really able to Solve Simple Math Word Problems? [PDF]
The problem of designing NLP solvers for math word problems (MWP) has seen sustained research activity and steady gains in the test accuracy. Since existing solvers achieve high performance on the benchmark datasets for elementary level MWPs containing ...
Arkil Patel +2 more
semanticscholar +1 more source
From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models [PDF]
Language models (LMs) are pretrained on diverse data sources—news, discussion forums, books, online encyclopedias. A significant portion of this data includes facts and opinions which, on one hand, celebrate democracy and diversity of ideas, and on the ...
Shangbin Feng +3 more
semanticscholar +1 more source
A Survey of Data Augmentation Approaches for NLP [PDF]
Data augmentation has recently seen increased interest in NLP due to more work in low-resource domains, new tasks, and the popularity of large-scale neural networks that require large amounts of training data.
Steven Y. Feng +6 more
semanticscholar +1 more source
MasakhaNER: Named Entity Recognition for African Languages
We take a step towards addressing the under- representation of the African continent in NLP research by bringing together different stakeholders to create the first large, publicly available, high-quality dataset for named entity recognition (NER) in ten
David Ifeoluwa Adelani +60 more
doaj +1 more source
Language (Technology) is Power: A Critical Survey of “Bias” in NLP [PDF]
We survey 146 papers analyzing “bias” in NLP systems, finding that their motivations are often vague, inconsistent, and lacking in normative reasoning, despite the fact that analyzing “bias” is an inherently normative process.
Su Lin Blodgett +3 more
semanticscholar +1 more source
Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning [PDF]
Despite their impressive performance, large language models (LMs) still struggle with reliably generating complex output structures when not finetuned to follow the required output format exactly. To address this issue, grammar-constrained decoding (GCD)
Sai-Bo Geng +3 more
semanticscholar +1 more source
Beyond Accuracy: Behavioral Testing of NLP Models with CheckList [PDF]
Although measuring held-out accuracy has been the primary approach to evaluate generalization, it often overestimates the performance of NLP models, while alternative approaches for evaluating models either focus on individual tasks or on specific ...
Marco Tulio Ribeiro +3 more
semanticscholar +1 more source
The State and Fate of Linguistic Diversity and Inclusion in the NLP World [PDF]
Language technologies contribute to promoting multilingualism and linguistic diversity around the world. However, only a very small number of the over 7000 languages of the world are represented in the rapidly evolving language technologies and ...
Pratik M. Joshi +4 more
semanticscholar +1 more source

