Recurrent neural networks (RNNs) sequentially process data by updating their state with
each new data point, and have long been the de facto choice for sequence modeling tasks …

Document-level relation extraction requires integrating information within and across
multiple sentences of a document and capturing complex interactions between inter …

Rapid progress in machine learning for natural language processing has the potential to
transform debates about how humans learn language. However, the learning environments …

Abstract Entities, as the essential elements in relation extraction tasks, exhibit certain
structure. In this work, we formulate such entity structure as distinctive dependencies …

In this paper, we present Hierarchical Graph Network (HGN) for multi-hop question
answering. To aggregate clues from scattered texts across multiple paragraphs, a …

Most research in reading comprehension has focused on answering questions based on
individual documents or even single paragraphs. We introduce a neural model which …

Multi-hop Reading Comprehension (RC) requires reasoning and aggregation across
several paragraphs. We propose a system for multi-hop RC that decomposes a …

Text-based question answering (TBQA) has been studied extensively in recent years. Most
existing approaches focus on finding the answer to a question within a single paragraph …

Much effort has been devoted to evaluate whether multi-task learning can be leveraged to
learn rich representations that can be used in various Natural Language Processing (NLP) …

One reason pretraining on self-supervised linguistic tasks is effective is that it teaches
models features that are helpful for language understanding. However, we want pretrained …