Multi Document Reading Comprehension

TL;DR

This paper reviews the evolution of Reading Comprehension in NLP, emphasizing multi-document understanding and analyzing the RE3QA model that combines retrieval, re-ranking, and reading components for improved answer accuracy.

Contribution

It provides a comprehensive overview of multi-document reading comprehension and analyzes the novel RE3QA model integrating retrieval, re-ranking, and reading modules.

Findings

Machines can surpass human performance on datasets like SQuAD.

Multi-document RC is built upon single-document RC as a foundational component.

RE3QA effectively combines retrieval, re-ranking, and reading for better answers.

Abstract

Reading Comprehension (RC) is a task of answering a question from a given passage or a set of passages. In the case of multiple passages, the task is to find the best possible answer to the question. Recent trials and experiments in the field of Natural Language Processing (NLP) have proved that machines can be provided with the ability to not only process the text in the passage and understand its meaning to answer the question from the passage, but also can surpass the Human Performance on many datasets such as Standford's Question Answering Dataset (SQuAD). This paper presents a study on Reading Comprehension and its evolution in Natural Language Processing over the past few decades. We shall also study how the task of Single Document Reading Comprehension acts as a building block for our Multi-Document Reading Comprehension System. In the latter half of the paper, we'll be studying about a recently proposed model for Multi-Document Reading Comprehension - RE3QA that is comprised of a Reader, Retriever, and a Re-ranker based network to fetch the best possible answer from a given set of passages.