SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable AMR Meaning Features. (arXiv:2206.07023v1 [cs.CL])

Metrics for graph-based meaning representations (e.g., Abstract Meaning
Representation, AMR) can help us uncover key semantic aspects in which two
sentences are similar to each other. However, such metrics tend to be slow,
rely on parsers, and do not reach state-of-the-art performance when rating
sentence similarity. On the other hand, models based on large-pretrained
language models, such as S(entence)BERT, show high correlation to human
similarity ratings, but lack interpretability.

In this paper, we aim at the best of these two …

amr arxiv features meaning studies