Decomposing and Recomposing Event Structure

@article{Gantt2022DecomposingAR,
  title={Decomposing and Recomposing Event Structure},
  author={William Gantt and Lelia Glass and Aaron Steven White},
  journal={Transactions of the Association for Computational Linguistics},
  year={2022},
  volume={10},
  pages={17-34}
}
We present an event structure classification empirically derived from inferential properties annotated on sentence- and document-level Universal Decompositional Semantics (UDS) graphs. We induce this classification jointly with semantic role, entity, and event-event relation classifications using a document-level generative model structured by these graphs. To support this induction, we augment existing annotations found in the UDS1.0 dataset, which covers the entirety of the English Web… 
What does BERT know about distributivity?
TLDR
The goal is to test whether transformer models are able to encode event structural information in their representations of sentences and it is found that BERT may encode information about distributivity in later layers but it can still find a signal as early as layer 1.
Argument Linking: A Survey and Forecast
TLDR
This paper surveys the literature on argument linking and identifies several notable shortcomings of existing approaches that indicate the paths along which future research effort could most profitably be spent.

References

SHOWING 1-10 OF 87 REFERENCES
Integrating Generative Lexicon Event Structures into VerbNet
TLDR
Modifications to the semantic representations associated with classes of verbs in the English lexical resource VerbNet incorporate the Generative Lexicon’s event structure, allowing for greater flexibility in representing complex events.
Universal Conceptual Cognitive Annotation (UCCA)
TLDR
UCCA is presented, a novel multi-layered framework for semantic representation that aims to accommodate the semantic distinctions expressed through linguistic utterances and its relative insensitivity to meaning-preserving syntactic variation is demonstrated.
Word Meaning and Montague Grammar: The Semantics of Verbs and Times in Generative Semantics and in Montague’s PTQ, volume 7, Springer Science & Business Media
  • 1979
Automatic prediction of aspectual class
  • 2014
English web treebank
  • Linguistic Data Consortium, Philadelphia, PA
  • 2012
Semantic protoroles
  • Transactions of the Association for Computational Linguistics, 3:475–488. https://
  • 2015
Joint Universal Syntactic and Semantic Parsing
TLDR
This work analyzes the behavior of a joint model of syntax and semantics, finding patterns supported by linguistic theory at the syntax–semantics interface, and investigates to what degree joint modeling generalizes to a multilingual setting, where it finds similar trends across 8 languages.
Natural Language Inference with Mixed Effects
TLDR
It is demonstrated that this method, which generalizes the notion of a mixed effects model by incorporating annotator random effects into any existing neural model, improves performance over models that do not incorporate such effects.
Joint Constrained Learning for Event-Event Relation Extraction
TLDR
This work proposes a joint constrained learning framework for modeling event-event relations that enforces logical constraints within and across multiple temporal and subevent relations by converting these constraints into differentiable learning objectives.
A Broad-Coverage Deep Semantic Lexicon for Verbs
TLDR
COLLIE-V is developed, a deep lexical resource for verbs, with the coverage of WordNet and syntactic and semantic details that meet or exceed existing resources.
...
...