Hervé Jeǵou

Gradient-based Adversarial Attacks against Text Transformers

2021 · arXiv (Cornell University)

We propose the first general-purpose gradient-based attack against transformer models. Instead of searching for a single adversarial example, we search for a distribution of adversarial examples parameterized by a continuous-valued matrix, hence enabling gradient-based optimization. …

Word Translation Without Parallel Data

2017 · arXiv (Cornell University)

State-of-the-art methods for learning cross-lingual word embeddings have relied on bilingual dictionaries or parallel corpora. Recent studies showed that the need for parallel data supervision can be alleviated with character-level information. While these methods showed …

Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion

2018

Continuous word representations learned separately on distinct languages can be aligned so that their words become comparable in a common space. Existing works typically solve a quadratic problem to learn a orthogonal matrix aligning a …

Efficient softmax approximation for GPUs

2017 · International Conference on Machine Learning

We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies. Our approach, called adaptive softmax, circumvents the linear dependency on the vocabulary size by exploiting the unbalanced word …