Victoria Yaneva, Le An Ha, Richard Evans, Ruslan Mitkov
TL;DR利用眼动数据和词性标注器,并通过具有区分能力的特征表明解决代词消歧的方式可提高 it 自动分类的准确性。
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