Recurrent neural networks (RNNs) are capable of learning features and long term
dependencies from sequential and time-series data. The RNNs have a stack of non-linear …

Over the past few years, neural networks have re-emerged as powerful machine-learning
models, yielding state-of-the-art results in fields such as image recognition and speech …

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 …

Continuous word representations, trained on large unlabeled corpora are useful for many
natural language processing tasks. Popular models that learn such representations ignore …

We describe a simple neural language model that relies only on character-level inputs.
Predictions are still made at the word-level. Our model employs a convolutional neural …

We present UDify, a multilingual multi-task model capable of accurately predicting universal
part-of-speech, morphological features, lemmas, and dependency trees simultaneously for …

We introduce a globally normalized transition-based neural network model that achieves
state-of-the-art part-of-speech tagging, dependency parsing and sentence compression …

We introduce a model for constructing vector representations of words by composing
characters using bidirectional LSTMs. Relative to traditional word representation models that …

Bidirectional long short-term memory (bi-LSTM) networks have recently proven successful
for various NLP sequence modeling tasks, but little is known about their reliance to input …

Nearly all previous work on neural machine translation (NMT) has used quite restricted
vocabularies, perhaps with a subsequent method to patch in unknown words. This paper …