Doctoral Dissertation Research: Compositional Linguistic Generalization in Human and Machine Learning

复合性，即一个复杂表达的意义是从其各部分的意义中构建出来的原则，是人类语言的核心。这种特性使我们能够通过组合我们已经知道的部分来产生和理解我们以前从未遇到过的新颖表达。例如，一个说英语的人被告知句子“The blick saw the cat”的意思是什么（让我们说“blick”是一只黑色的鸭子），可以很容易地将他们的理解概括为一个新的句子“The cat saw the blick”，而无需明确地被告知它的意思。这个项目的目标是采取一个步骤，阐明的机制，由组合性的原则促进泛化。这一目标将通过人类和机器学习研究的结合来实现。该项目将鼓励人类和机器学习研究之间的方法转移，并促进语言学学者和工业实验室语言研究人员之间的合作。这项研究对人工智能（AI）具有潜在的意义--具有更好泛化能力的计算模型可以帮助解决现有模型的缺点，如鲁棒性和数据效率。当代神经模型--一个基于生物神经回路启发的大规模并行计算的模型家族，极大地推动了AI的进展--在组合泛化方面只取得了部分成功。特别是，先前的工作表明，神经模型需要对已知结构进行新的组合（结构泛化）。结构泛化的一个例子是将一个只在宾语位置上看到的修饰语泛化到主语位置上。例如，如果一个模型可以为“the girl saw a cat on the mat”分配正确的含义，那么它也可以为“the girl on the mat saw a cat”分配正确的含义吗？神经模型中有限的结构泛化激发了本项目的两个主要研究问题。首先，人类学习者的结构概括能力和局限性是什么？第二，从实现部分合成成功的神经模型的内部工作中可以学到什么，以及对这些模型的哪些修改将促进更像人类的泛化？第一个问题将通过与人类受试者（英语母语者）的人工语言学习研究进行探索，第二个问题将通过神经网络的计算建模研究进行探索。这项研究将促进我们对神经网络中出现类似人类的合成泛化的充分条件的理解。此外，人体实验将填补一个重要的空白，在文献中测试结构概括在一个受控的实验。该奖项反映了NSF的法定使命，并已被认为是值得支持的，通过评估使用基金会的智力价值和更广泛的影响审查标准。

Compositionality, the principle that the meaning of a complex expression is built from the meanings of its parts, is central to human language. This property enables us to produce and comprehend novel expressions that we have never encountered before, by composing the parts that we already know. For example, an English speaker who is told what the meaning of the sentence 'The blick saw the cat' is (let's say 'blick' is a black duck), can easily generalize their understanding to a novel sentence 'The cat saw the blick' without explicitly being told what it means. The goal of this project is to take a step towards elucidating the mechanism underlying generalization facilitated by the principle of compositionality. This goal will be undertaken through a combination of human and machine learning studies. This project will encourage methodological transfer between human and machine learning research, as well as promoting collaboration between scholars in Linguistics and researchers working on language in industrial labs. This research has potential implications for Artificial Intelligence (AI)—computational models with better generalization capacity can help address shortcomings of existing models, such as robustness and data efficiency.Contemporary neural models—a family of models that is based on massive parallel computation inspired by biological neural circuits, and has greatly advanced the progress in AI—only achieve partial success in compositional generalization. In particular, prior work has shown that neural models struggle with generalizations that require novel composition of known structures (structural generalization). An instance of a structural generalization is generalizing a modifier only seen in object position to subject position. For example, if a model can assign the correct meaning to 'the girl saw a cat on the mat', can it also assign correct meaning to 'the girl on the mat saw a cat'? Limited structural generalization in neural models motivates the two main research questions of this project. First, what are the capabilities and limitations of structural generalization in human learners? Second, what can be learned from the inner workings of neural models that achieve partial compositional success, and what revisions to these models would facilitate more human-like generalization? The first question will be explored through an artificial language learning study with human subjects (native English speakers), and the second question, via a computational modeling study with neural networks. This research will advance our understanding of the sufficient conditions for human-like compositional generalization to arise in neural networks. Furthermore, the human experiments will fill an important gap in the literature by testing structural generalization in a controlled experimentThis 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.