Decomposing and Recomposing Event Structure

Gantt, W. Horsley; Glass, Lelia; White, Aaron Steven

doi:10.1162/tacl_a_00445

Cited by 5 publications

(4 citation statements)

References 39 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…What are the implications of using one or the other for natural language judgments? Theories of causal abstraction and event representation provide a rich avenue for future work (Gantt, Glass, & White, 2022;Geiger, Potts, & Icard, 2023).…”

Section: Discussionmentioning

confidence: 99%

A Semantics for Causing, Enabling, and Preventing Verbs Using Structural Causal Models

Cao

Geiger²,

Kreiss³

et al. 2023

Preprint

View full text Add to dashboard Cite

When choosing how to describe what happened, we have a number of causal verbs at our disposal. In this paper, we develop a model-theoretic formal semantics for nine causal verbs that span the categories of CAUSE, ENABLE, and PREVENT. We use structural causal models (SCMs) to represent participants’ mental construction of a scene when assessing the correctness of causal expressions relative to a presented context. Furthermore, SCMs enable us to model events relating both the physical world as well as agents’ mental states. In experimental evaluations, we find that the proposed semantics exhibits a closer alignment with human evaluations in comparison to prior accounts of the verb families.

show abstract

Section: Discussionmentioning

confidence: 99%

A Semantics for Causing, Enabling, and Preventing Verbs Using Structural Causal Models

Cao

Geiger²,

Kreiss³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Pushing the envelope further are the Decompositional Semantics Initiative (White et al, 2016) and MegaAttitude project (White and Rawlins, 2016). 2 In these projects, annotating large-scale corpora with the phenomena that are posited to underly linguistic theories in question -such as Dowty (1991)'s proto-role properties, or entailments corresponding to negraising (An and White, 2020) and projection (White and Rawlins, 2018) -has facilitated insights regarding argument selection (Reisinger et al, 2015) and lexically-specified syntactic subcategorization rules (White, 2021), as well as automatically inducing lexicon-level ontologies of semantic roles (White et al, 2017) and event structure (Gantt et al, 2021) that are derived directly from the phenomena they are designed to explain.…”

Section: Decouple Data From Theorymentioning

confidence: 99%

Proceedings of the Big Picture Workshop

2023

View full text Add to dashboard Cite

A key contribution to being a successful researcher in natural language processing, as in any area, is having a clear overarching vision of what your body of research is trying to accomplish. Using my own 40-year career as an example, I will attempt to provide general advice on formulating and pursuing a coherent research vision. In particular, I will focus on formulating a unique, personal objective that exploits your specific talents, knowledge, and passions, and that is distinct from the current popular trends in the field. I will also focus on formulating a vision that bridges existing fields of study to produce an overarching agenda that unifies previously disparate ideas.

show abstract

“…Pushing the envelope further are the Decompositional Semantics Initiative and MegaAttitude project (White and Rawlins, 2016). 2 In these projects, annotating large-scale corpora with the phenomena that are posited to underly linguistic theories in question -such as Dowty (1991)'s proto-role properties, or entailments corresponding to negraising (An and White, 2020) and projection (White and Rawlins, 2018) -has facilitated insights regarding argument selection (Reisinger et al, 2015) and lexically-specified syntactic subcategorization rules (White, 2021), as well as automatically inducing lexicon-level ontologies of semantic roles (White et al, 2017) and event structure (Gantt et al, 2021) that are derived directly from the phenomena they are designed to explain.…”

Section: Decouple Data From Theorymentioning

confidence: 99%

The Case for Scalable, Data-Driven Theory: A Paradigm for Scientific Progress in NLP

Michael

2023

Proceedings of the Big Picture Workshop

View full text Add to dashboard Cite

I propose a paradigm for scientific progress in NLP centered around developing scalable, data-driven theories of linguistic structure. The idea is to collect data in tightly scoped, carefully defined ways which allow for exhaustive annotation of behavioral phenomena of interest, and then use machine learning to construct explanatory theories of these phenomena which can form building blocks for intelligible AI systems. After laying some conceptual groundwork, I describe several investigations into datadriven theories of shallow semantic structure using Question-Answer driven Semantic Role Labeling (QA-SRL), a schema for annotating verbal predicate-argument relations using highly constrained question-answer pairs. While this only scratches the surface of the complex language behaviors of interest in AI, I outline principles for data collection and theoretical modeling which can inform future scientific progress. This note summarizes and draws heavily on my PhD thesis (Michael, 2023).

show abstract

Decomposing and Recomposing Event Structure

Cited by 5 publications

References 39 publications

A Semantics for Causing, Enabling, and Preventing Verbs Using Structural Causal Models

A Semantics for Causing, Enabling, and Preventing Verbs Using Structural Causal Models

Proceedings of the Big Picture Workshop

The Case for Scalable, Data-Driven Theory: A Paradigm for Scientific Progress in NLP

Contact Info

Product

Resources

About