We introduce a multi-task setup of identifying and classifying entities, relations, and
coreference clusters in scientific articles. We create SciERC, a dataset that includes …

Neural networks are a family of powerful machine learning models and this book focuses on
their application to natural language data. The first half of the book (Parts I and II) covers the …

Multi-task learning (MTL) in deep neural networks for NLP has recently received increasing
interest due to some compelling benefits, including its potential to efficiently regularize …

Our goal is to combine the rich multistep inference of symbolic logical reasoning with the
generalization capabilities of neural networks. We are particularly interested in complex …

We describe DyNet, a toolkit for implementing neural network models based on dynamic
declaration of network structure. In the static declaration strategy that is used in toolkits like …

We decompose multimodal translation into two sub-tasks: learning to translate and learning
visually grounded representations. In a multitask learning framework, translations are …

Learning attention functions requires large volumes of data, but many NLP tasks simulate
human behavior, and in this paper, we show that human attention really does provide a …

Accurately detecting hate speech using supervised classification is dependent on data that
is annotated by humans. Attaining high agreement amongst annotators though is difficult …

A lack of corpora has so far limited advances in integrating human gaze data as a
supervisory signal in neural attention mechanisms for natural language processing (NLP) …

We recorded and preprocessed ZuCo 2.0, a new dataset of simultaneous eye-tracking and
electroencephalography during natural reading and during annotation. This corpus contains …