ComQA:Compositional Question Answering via Hierarchical Graph Neural Networks

TL;DR

This paper introduces ComQA, a large-scale dataset for compositional question answering, and proposes a hierarchical graph neural network model to assemble discontiguous evidence for accurate, compositional answers.

Contribution

The paper presents a new large-scale dataset for compositional QA and a hierarchical graph neural network model that effectively integrates evidence from multiple document levels.

Findings

Model outperforms previous machine reading comprehension methods.

Hierarchical graph neural networks improve compositional answer accuracy.

Pre-training tasks enhance model performance.

Abstract

With the development of deep learning techniques and large scale datasets, the question answering (QA) systems have been quickly improved, providing more accurate and satisfying answers. However, current QA systems either focus on the sentence-level answer, i.e., answer selection, or phrase-level answer, i.e., machine reading comprehension. How to produce compositional answers has not been throughout investigated. In compositional question answering, the systems should assemble several supporting evidence from the document to generate the final answer, which is more difficult than sentence-level or phrase-level QA. In this paper, we present a large-scale compositional question answering dataset containing more than 120k human-labeled questions. The answer in this dataset is composed of discontiguous sentences in the corresponding document. To tackle the ComQA problem, we proposed a hierarchical graph neural networks, which represents the document from the low-level word to the high-level sentence. We also devise a question selection and node selection task for pre-training. Our proposed model achieves a significant improvement over previous machine reading comprehension methods and pre-training methods. Codes and dataset can be found at \url{https://github.com/benywon/ComQA}.