We investigate grounded language learning through real-world data, by modelling a teacher-learner dynamics through the natural interactions occurring between users and search engines; in particular, we explore the emergence of semantic generalization from unsupervised dense representations outside of synthetic environments. A grounding domain, a denotation function and a composition function are learned from user data only. We show how the resulting semantics for noun phrases exhibits compositional properties while being fully learnable without any explicit labelling. We benchmark our grounded semantics on compositionality and zero-shot inference tasks, and we show that it provides better results and better generalizations than SOTA non-grounded models, such as word2vec and BERT.

翻译：我们通过现实世界数据,通过用户和搜索引擎之间的自然互动模拟教师-远程动态,调查通过真实世界数据进行的基础语言学习;特别是,我们探索合成环境之外不受监督的密集表层出现的语义概括;仅从用户数据中学习一个基础域、分解函数和构成函数;我们展示了由此产生的名词词词语的语义如何体现组成特性,同时无需任何明确标签即可充分学习;我们以构成性和零发推论任务作为我们的基础语义的基准,我们显示它比SOTA的非立足模型,如Word2vec和BERT提供了更好的结果和更好的概括。