We consider the problem of multi-objective (MO) blackbox optimization using expensive function evaluations, where the goal is to approximate the true Pareto set ...
Missing: url | Show results with:url
In this paper, we present TextFooler, a simple but strong baseline to generate adversarial text. By applying it to two fundamental natural language tasks, text ...
Missing: 6561 | Show results with:6561
Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 7383-7390. https://doi.org/10.1609/aaai.v34i05.6233. More Citation Formats. ACM · ACS ...
Missing: 6561 | Show results with:6561
In this paper, we evaluate the cross-lingual effectiveness of representations from the encoder of a massively multilingual NMT model on 5 downstream ...
Missing: 6561 | Show results with:6561
Getting Closer to AI Complete Question Answering: A Set of ...
aaai.org › ojs › AAAI › article › view
We present QuAIL, the first RC dataset to combine text-based, world knowledge and unanswerable questions, and to provide question type annotation that would ...
Missing: 6561 | Show results with:6561
In this work, we present a systematic and quantitative study on the over-smoothing issue of GNNs. First, we introduce two quantitative metrics, MAD and MADGap, ...
Missing: 6561 | Show results with:6561
DOI: https://doi.org/10.1609/aaai.v34i03.5689. Abstract. This paper presents the first use of graph neural networks (GNNs) for higher-order proof search and ...
Missing: 6561 | Show results with:6561
The HSIC bottleneck is an alternative to the conventional cross-entropy loss and backpropagation that has a number of distinct advantages. It mitigates ...
Missing: url 6561