Collaborative Research: Computational Modeling of the Internal Structure of Events

人类语言是一种强大的工具，可以在不同的具体层次上传达关于复杂、多方面的事件的信息：在呼吸的空间里，我们可以从谈论一个复杂事件的整体转向有针对性地讨论它的许多部分及其相互关系。了解我们如何使用语言传达如此复杂的信息不仅对提高我们对人类语言能力的科学理解至关重要，而且对人工智能系统从人类每天产生的大量文本中提取有关世界的知识的能力至关重要，并最终提高其服务人类需求的能力。为了实现这两个目标，该项目开发了基础资源和基于深度学习的尖端人工智能系统，以从这些资源中提取知识。为了实现这一目标，该项目开发了一种覆盖面广的自动方法，用于将事件的描述映射到事件各部分之间关系的丰富表示：事件结构。它有两个主要组成部分：（i）它收集行为数据和文本语料库注释，用于英语中动词，形容词和名词性谓词的事件结构的关键方面;（ii）它开发并实现了一个通用的基于深度学习的事件结构计算模型，使用这些数据进行训练。根据这一建议产生的词汇和语料库将被注释为事件的属性，这些属性在当前的时态，语法体和词汇体的语言学理论中处于中心地位：（i）事件是否有一个自然的终点（跑步）或没有（简单地跑来跑去）？(ii)事件是瞬间发生的（击球）还是随着时间的推移发生的（盖房子）;（iii）事件的先决条件和结果是什么？(iv)这些结果是永久的（杀死一只蚊子）还是暂时的（打开一扇门，然后再关上）？(v)它们是逐渐产生的（擦桌子）还是突然产生的（擦桌子）？(vi)活动是由不可分割的部分组成的（个人鼓掌）还是不组成（红色）？(vii)这些部分是相似的（敲击玻璃）还是不同的（购买衣服）;以及（viii）事件部分是否对应于参与者部分（写书）或不对应（组合成分）？在这些注释的基础上，将开发和实现一个计算模型，该模型共同归纳出：（a）谓词的不同含义（运行一场比赛与运行一家公司）;（B）与这些含义相关联的事件结构类;（c）与这些类相关联的事件结构属性;以及（d）从事件的部分到其参与者和时间/因果结构的映射。该模型将贝叶斯分层模型与深度学习的最新进展相结合，并将能够对替代理论假设进行明确的定量比较，例如必须假设的事件结构类和属性的数量，以最好地解释数据。该奖项反映了NSF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。

Human language is a powerful tool for conveying information about complex, multi-faceted events at different levels of specificity: in the space of a breath, we can move from talking about a complex event as a whole to a targeted discussion of its many parts and their inter-relationships. Understanding how we convey such complex information using language is critical to improving not only our scientific understanding of human linguistic capacities, but also the ability of artificial intelligence systems to extract knowledge about the world from the massive bodies of text humans generate every day, and ultimately to improve their ability to serve humanity's needs. With the goal of advancing both aims, this project develops foundational resources and cutting-edge deep learning-based artificial intelligence systems for extracting knowledge from those resources.To achieve that goal, the project develops a broad-coverage, automatic method for mapping a description of an event to a rich representation of the relationships among that event's parts: its event structure. It has two main components: (i) it collects behavioral data and text corpus annotations for key aspects of the event structure of verbal, adjectival, and nominal predicates in English; and (ii) it develops and implements a general deep learning-based computational model of event structure, trained using those data. The lexicon and corpus produced under this proposal will be annotated for properties of events that are central in current linguistic theories of tense, grammatical aspect, and lexical aspect: (i) does the event have a natural endpoint (running a race) or not (simply running around)?; (ii) does the event happen at an instant (hitting a ball) or over time (building a house); (iii) what are the event's preconditions and results?; (iv) are those results permanent (killing a mosquito) or transient (opening a door, which can be closed again)?; (v) do they come about gradually (cleaning a table) or abruptly (scuffing a table)?; (vi) does the event consist of indivisible parts (individual claps in applause) or not (being red)?; (vii) are those parts similar (tapping on glass) or dissimilar (shopping for clothes); and (viii) do event parts correspond to participant parts (writing a book) or not (combining ingredients)? On the basis of these annotations, a computational model will be developed and implemented that jointly induces (a) distinct senses of a predicate (running a race v. running a company); (b) the event structure class(es) associated with those senses; (c) the event structure properties associated with those classes; and (d) a mapping from the event's parts to its participants and temporal/causal structure. This model will integrate Bayesian hierarchical models with recent advances in deep learning and will enable explicit quantitative comparison of alternative theoretical assumptions, such as the number of event structure classes and properties that must be posited to best explain the data.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.