MetaSRL++: A Uniform Scheme for Modelling Deeper Semantics
This addresses the problem of meaning and understanding in NLP, but it appears incremental as it builds on existing semantic graph approaches without demonstrating broad SOTA impact.
The paper tackles the lack of a common deep semantic representation scheme in NLP by introducing MetaSRL++, a uniform, language- and modality-independent modelling scheme based on Semantic Graphs, and provides concrete examples and comparisons to existing work.
Despite enormous progress in Natural Language Processing (NLP), our field is still lacking a common deep semantic representation scheme. As a result, the problem of meaning and understanding is typically sidestepped through more simple, approximative methods. This paper argues that in order to arrive at such a scheme, we also need a common modelling scheme. It therefore introduces MetaSRL++, a uniform, language- and modality-independent modelling scheme based on Semantic Graphs, as a step towards a common representation scheme; as well as a method for defining the concepts and entities that are used in these graphs. Our output is twofold. First, we illustrate MetaSRL++ through concrete examples. Secondly, we discuss how it relates to existing work in the field.