Contextualized Word Representations for Reading Comprehension
This addresses reading comprehension for natural language processing applications, but is incremental as it builds on existing neural architectures.
The paper tackled the problem of reading comprehension by evaluating the importance of context when processing questions and documents independently, and achieved dramatic improvements with performance comparable to state-of-the-art on the SQuAD dataset.
Reading a document and extracting an answer to a question about its content has attracted substantial attention recently. While most work has focused on the interaction between the question and the document, in this work we evaluate the importance of context when the question and document are processed independently. We take a standard neural architecture for this task, and show that by providing rich contextualized word representations from a large pre-trained language model as well as allowing the model to choose between context-dependent and context-independent word representations, we can obtain dramatic improvements and reach performance comparable to state-of-the-art on the competitive SQuAD dataset.