The paper surveys evaluation methods of natural language generation (NLG) systems that
have been developed in the last few years. We group NLG evaluation methods into three …

When trained effectively, the Variational Autoencoder (VAE) can be both a powerful
generative model and an effective representation learning framework for natural language …

Autoregressive sequence models achieve state-of-the-art performance in domains like
machine translation. However, due to the autoregressive factorization nature, these models …

High-level musical qualities (such as emotion) are often abstract, subjective, and hard to
quantify. Given these difficulties, it is not easy to learn good feature representations with …

Autoregressive models for text sometimes generate repetitive and low-quality output
because errors accumulate during the steps of generation. This issue is often attributed to …

Paraphrase generation is a longstanding important problem in natural language processing.
Recent progress in deep generative models has shown promising results on discrete latent …

To build an interpretable neural text classifier, most of the prior work has focused on
designing inherently interpretable models or finding faithful explanations. A new line of work …

Dependency parse trees are helpful for discovering the opinion words in aspect-based
sentiment analysis (ABSA). However, the trees obtained from off-the-shelf dependency …

Distant supervision is widely used in relation classification in order to create large-scale
training data by aligning a knowledge base with an unlabeled corpus. However, it also …

The neural attention model has achieved great success in data-to-text generation tasks.
Though usually excelling at producing fluent text, it suffers from the problem of information …