Collaborative Research: The MegaAttitude Project: Investigating selection and polysemy at the scale of the lexicon

这个项目研究了人类如何从成千上万的英语谓语中得出复杂的推论，这些谓语与从句结合在一起——“think”、“know”、“say”、“tell”、“remember”、“forget”等——当它们结合在一起的从句的结构特征不同时。例如，句子“约翰忘了他买了牛奶”与句子“约翰忘了买牛奶”类似；但从第一句话，听者推断约翰买了牛奶，而从第二句，听者推断他没有买牛奶。这种推理模式只是英语中众多推理模式中的一种；然而，尽管存在这种变化，谓词和从句结构之间似乎存在实质性的规律，而以前的工作只是触及了表面。研究人类如何计算这些推理模式的系统性，揭示了人类认知系统如何从更简单的部分构建复杂的含义，并支持智能计算系统的发展，以类似人类的方式理解和推理自然语言。目前的项目分为两部分进行调查。首先，它基于心理语言学的实验方法，开发并部署了多个可扩展的、众包的注释协议，以收集由数千个英语谓语与从句结合引发的各种推断模式的数据。其次，它利用多任务机器学习的最新进展来建立一个统一的计算模型，该模型是在这些数据上训练的，该模型包含这些谓词、它们的从句的结构以及它们触发的推论之间的关系。这个模型不仅有助于揭示人类如何计算感兴趣的推理模式的系统性；它也可以直接集成到用于自然语言理解的应用技术中。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

This project addresses how humans draw complex inferences from the thousands of English predicates that combine with subordinate clauses -- "think", "know", "say", "tell", "remember", "forget", etc. -- when the structural characteristics of the clauses they combine with vary. For example, the sentence "John forgot that he bought milk" is similar to the sentence "John forgot to buy milk"; but from the first sentence, a listener infers that John bought milk, while from the second, a listener infers that he didn't. This inference pattern is only one among many such patterns in English; yet, in spite of this variety, there appears to be substantial regularities across predicates and subordinate clause structures that prior work has only scratched the surface of. Investigating the systematicities in how humans compute these inference patterns sheds light on how the human cognitive system constructs complex meanings from simpler parts and supports the development of intelligent computational systems for comprehending and reasoning about natural language in human-like ways.The current project approaches this investigation in two parts. First, it develops and deploys multiple scalable, crowd-sourced annotation protocols, based on experimental methodologies from psycholinguistics, in order to collect data about a wide variety of inference patterns triggered by all of the thousands of English predicates that combine with subordinate clauses. Second, it leverages recent advances in multi-task machine learning to build a unified computational model of the relationship between such predicates, the structure of their subordinate clauses, and the inferences that they trigger, which is trained on these data. This model not only helps to reveal systematicities in how humans compute the inference patterns of interest; it can also be straightforwardly incorporated into applied technologies for natural language understanding.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.