期刊名称：Conference on European Chapter of the Association for Computational Linguistics (EACL)
出版年度：2017
卷号：2017
页码：86-91
语种：English
出版社：ACL Anthology
摘要：There has recently been a lot of work trying to use images of referents of words for improving vector space meaning representations derived from text. We investigate the opposite direction, as it were, trying to improve visual word predictors that identify objects in images, by exploiting distributional similarity information during training. We show that for certain words (such as entry-level nouns or hypernyms), we can indeed learn better referential word meanings by taking into account their semantic similarity to other words. For other words, there is no or even a detrimental effect, compared to a learning setup that presents even semantically related objects as negative instances.
