Enhancing Structured Meaning Representations with Aspect Classification

TL;DR

This paper introduces a new annotated dataset and baseline models for predicting aspectual information in semantic representations, enhancing the encoding of temporal event structures in meaning representations.

Contribution

The paper presents a novel dataset with aspect annotations for UMR in AMR graphs, along with annotation guidelines and baseline models for automatic aspect prediction.

Findings

Established initial benchmarks for UMR aspect prediction

Developed a consistent annotation pipeline with adjudication

Demonstrated baseline model performance for automatic aspect classification

Abstract

To fully capture the meaning of a sentence, semantic representations should encode aspect, which describes the internal temporal structure of events. In graph-based meaning representation frameworks such as Uniform Meaning Representations (UMR), aspect lets one know how events unfold over time, including distinctions such as states, activities, and completed events. Despite its importance, aspect remains sparsely annotated across semantic meaning representation frameworks. This has, in turn, hindered not only current manual annotation, but also the development of automatic systems capable of predicting aspectual information. In this paper, we introduce a new dataset of English sentences annotated with UMR aspect labels over Abstract Meaning Representation (AMR) graphs that lack the feature. We describe the annotation scheme and guidelines used to label eventive predicates according to the UMR aspect lattice, as well as the annotation pipeline used to ensure consistency and quality across annotators through a multi-step adjudication process. To demonstrate the utility of our dataset for future automation, we present baseline experiments using three modeling approaches. Our results establish initial benchmarks for automatic UMR aspect prediction and provide a foundation for integrating aspect into semantic meaning representations more broadly.