Bridging Information-Seeking Human Gaze and Machine Reading Comprehension

TL;DR

This paper explores how human gaze patterns during reading can inform machine reading comprehension, introducing a new eye-tracking dataset and a human-inspired approach that improves question-answering performance.

Contribution

It presents a novel eye-tracking dataset and a method that mimics human gaze behavior to enhance machine reading comprehension accuracy.

Findings

Human gaze focuses on relevant text parts during comprehension.

Incorporating gaze-inspired behavior improves model performance.

The approach outperforms baseline models on multiple choice questions.

Abstract

In this work, we analyze how human gaze during reading comprehension is conditioned on the given reading comprehension question, and whether this signal can be beneficial for machine reading comprehension. To this end, we collect a new eye-tracking dataset with a large number of participants engaging in a multiple choice reading comprehension task. Our analysis of this data reveals increased fixation times over parts of the text that are most relevant for answering the question. Motivated by this finding, we propose making automated reading comprehension more human-like by mimicking human information-seeking reading behavior during reading comprehension. We demonstrate that this approach leads to performance gains on multiple choice question answering in English for a state-of-the-art reading comprehension model.