Deep Understanding based Multi-Document Machine Reading Comprehension

TL;DR

This paper introduces a deep understanding model for multi-document machine reading comprehension that emphasizes semantic understanding and cue identification, achieving state-of-the-art results on major benchmarks.

Contribution

The proposed model incorporates three cascaded deep understanding modules focusing on semantics, interactions, and supporting cues, addressing limitations of previous models.

Findings

Achieves state-of-the-art results on TriviaQA Web and DuReader datasets.

Demonstrates the effectiveness of deep understanding modules in MRC.

Outperforms existing models in multi-document comprehension tasks.

Abstract

Most existing multi-document machine reading comprehension models mainly focus on understanding the interactions between the input question and documents, but ignore following two kinds of understandings. First, to understand the semantic meaning of words in the input question and documents from the perspective of each other. Second, to understand the supporting cues for a correct answer from the perspective of intra-document and inter-documents. Ignoring these two kinds of important understandings would make the models oversee some important information that may be helpful for inding correct answers. To overcome this deiciency, we propose a deep understanding based model for multi-document machine reading comprehension. It has three cascaded deep understanding modules which are designed to understand the accurate semantic meaning of words, the interactions between the input question and documents, and the supporting cues for the correct answer. We evaluate our model on two large scale benchmark datasets, namely TriviaQA Web and DuReader. Extensive experiments show that our model achieves state-of-the-art results on both datasets.