Weisfeiler-Leman in the Bamboo: Novel AMR Graph Metrics and a Benchmark for AMR Graph Similarity
Several metrics have been proposed for assessing the similarity of (abstract) meaning
representations (AMRs), but little is known about how they relate to human similarity ratings …
representations (AMRs), but little is known about how they relate to human similarity ratings …
Text generation from discourse representation structures
We propose neural models to generate text from formal meaning representations based on
Discourse Representation Structures (DRSs). DRSs are document-level representations …
Discourse Representation Structures (DRSs). DRSs are document-level representations …
A Survey of Meaning Representations–From Theory to Practical Utility
Z Sadeddine, J Opitz, F Suchanek - … of the 2024 Conference of the …, 2024 - aclanthology.org
Symbolic meaning representations of natural language text have been studied since at least
the 1960s. With the availability of large annotated corpora, and more powerful machine …
the 1960s. With the availability of large annotated corpora, and more powerful machine …
Metrics of Graph-Based Meaning Representations with Applications from Parsing Evaluation to Explainable NLG Evaluation and Semantic Search
J Opitz - 2024 - archiv.ub.uni-heidelberg.de
" Who does what to whom?" The goal of a graph-based meaning representation (in short:
MR) is to represent the meaning of a text in a structured format. With an MR, we can …
MR) is to represent the meaning of a text in a structured format. With an MR, we can …
Anchor and Broadcast: An Efficient Concept Alignment Approach for Evaluation of Semantic Graphs
In this paper, we present AnCast, an intuitive and efficient tool for evaluating graph-based
meaning representations (MR). AnCast implements evaluation metrics that are well …
meaning representations (MR). AnCast implements evaluation metrics that are well …
Character-based Neural Semantic Parsing
R van Noord - 2021 - research.rug.nl
Humans and computers do not speak the same language. A lot of day-to-day tasks would be
vastly more efficient if we could communicate with computers using natural language …
vastly more efficient if we could communicate with computers using natural language …
Cross-Level Typing the Logical Form for Open-Domain Semantic Parsing
İA Öztürel - 2022 - open.metu.edu.tr
This thesis presents a novel approach to assigning types to expressive Discourse
Representation Structure (DRS) meaning representations. In terms of linguistic analysis, our …
Representation Structure (DRS) meaning representations. In terms of linguistic analysis, our …
Understanding and generating language with discourse representation structures
J Liu - 2021 - era.ed.ac.uk
Natural Language is a way for humans to understand what is happening in the world.
However, machines with intelligence prefer symbolic representations that explicitly …
However, machines with intelligence prefer symbolic representations that explicitly …