A Survey of Meaning Representation – From Theory to Practical Utility

Anonymous

TL;DR: A survey on meaning representation, which proposes an overview of the whole field and outlook on its future in the LLM era.

Abstract: 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 learning tools, the field has recently seen several new developments. In this survey, we study today's most prominent Meaning Representations Frameworks. We shed light on both their theoretical properties and on their practical research environment, which includes datasets, parsers, applications, and future challenges.

Paper Type: long

Research Area: Semantics: Sentence-level Semantics, Textual Inference and Other areas

Contribution Types: Surveys, Theory

Languages Studied: English