Sentence Meaning Representations across Languages: What Can We Learn from Existing Frameworks?

Authors

Abstract

This article gives an overview of how sentence meaning is represented in a dozen of deep syntactic frameworks, ranging from those based on linguistic theories elaborated for decades to rather lightweight NLP-motivated approaches. We outline most important characteristics of each framework and then discuss how particular language phenomena are treated across those frameworks, while trying to shed light on commonalities as well as differences.

Author Biography

  • Daniel Zeman, Charles University, Faculty of Mathematics and Physics
    Senior researcher at the Institute of Formal and Applied Linguistics.

Published

2024-12-05

Issue

Section

Special Issue: Multilingual and Interlingual Semantic Representations for Natural Language Processing