Classifying Referential and Non-referential It Using Gaze

TL;DR

This paper leverages eye-tracking data to improve automatic classification of the pronoun 'it' into referential and non-referential uses, revealing insights into human processing and achieving high classification accuracy.

Contribution

It introduces a novel approach combining gaze data and POS tagging to classify 'it' with accuracy comparable to linguistic methods, and explores gaze features' role in understanding human pronoun processing.

Findings

Gaze data significantly improves classification accuracy.

Specific gaze features reveal human processing strategies.

Method outperforms baseline models.

Abstract

When processing a text, humans and machines must disambiguate between different uses of the pronoun it, including non-referential, nominal anaphoric or clause anaphoric ones. In this paper, we use eye-tracking data to learn how humans perform this disambiguation. We use this knowledge to improve the automatic classification of it. We show that by using gaze data and a POS-tagger we are able to significantly outperform a common baseline and classify between three categories of it with an accuracy comparable to that of linguisticbased approaches. In addition, the discriminatory power of specific gaze features informs the way humans process the pronoun, which, to the best of our knowledge, has not been explored using data from a natural reading task.