arXiv research

Partial-input models fail to detect dataset artifacts, even when they perform poorly.

In this paper, we propose Dynamic Self-Attention (DSA), a new self-attention mechanism for sentence embedding. We design DSA by modifying dynamic routing in capsule network (Sabouretal.,2017) for natural language processing. DSA attends to informative words with a dynamic weight vector. We achieve new state-of-the-art …

The paper improves NLI models' robustness by adding external knowledge to the attention mechanism.

LPL optimizes embeddings to align local neighborhoods, improving cross-lingual word alignment.

Sparse text alignments learned via optimal transport improve model explainability.

AFLite filters dataset biases to improve model generalization.

The task of Natural Language Inference (NLI) is widely modeled as supervised sentence pair classification. While there has been a lot of work recently on generating explanations of the predictions of classifiers on a single piece of text, there have been no attempts to generate explanations of classifiers operating on …

Adversarial examples are inputs to machine learning models designed to cause the model to make a mistake. They are useful for understanding the shortcomings of machine learning models, interpreting their results, and for regularisation. In NLP, however, most example generation strategies produce input text by using kno…

Levenshtein VAE prevents posterior collapse in text generation models.

Learning a deep neural network requires solving a challenging optimization problem: it is a high-dimensional, non-convex and non-smooth minimization problem with a large number of terms. The current practice in neural network optimization is to rely on the stochastic gradient descent (SGD) algorithm or its adaptive var…

ALI-G optimizes deep learning by interpolating data, improving generalization and ease of tuning.