Machine Reading Comprehension (MRC) is a challenging task and hot topic in Natural
Language Processing. The goal of this field is to develop systems for answering the …

We propose a novel data augmentation for labeled sentences called contextual
augmentation. We assume an invariance that sentences are natural even if the words in the …

Machine comprehension (MC), answering a query about a given context paragraph,
requires modeling complex interactions between the context and the query. Recently …

Enabling a computer to understand a document so that it can answer comprehension
questions is a central, yet unsolved goal of NLP. A key factor impeding its solution by …

In this paper we study the problem of answering cloze-style questions over documents. Our
model, the Gated-Attention (GA) Reader, integrates a multi-hop architecture with a novel …

Teaching a computer to read and answer general questions pertaining to a document is a
challenging yet unsolved problem. In this paper, we describe a novel neural network …

Several large cloze-style context-question-answer datasets have been introduced recently:
the CNN and Daily Mail news data and the Children's Book Test. Thanks to the size of these …

Many problems in NLP require aggregating information from multiple mentions of the same
entity which may be far apart in the text. Existing Recurrent Neural Network (RNN) layers are …

Abstract Machine learning models that take computer program source code as input typically
use Natural Language Processing (NLP) techniques. However, a major challenge is that …

We propose a data-to-text generation model with two modules, one for tracking and the
other for text generation. Our tracking module selects and keeps track of salient information …