25 May
2024
25 May
'24
11:12 p.m.
I may not be the first person in this group to notice similarities between
AMR and CG, but am now curious.
I stumbled onto a paper
https://aclanthology.org/W17-2315.pdf
Biomedical Event Extraction using Abstract Meaning Representation
which says - among other things:
AMR is a rooted, directed acyclic graph (DAG) that
captures the notion of
who did what to whom in text, in a way that sentences that have the same
basic meaning often have the same AMR. The nodes in the graph (also called
concepts) map to words in the sentence and the edges map to relations
between the words
Some AMR programs rely on Verbnet for their roles; some CG programs have
relied on Framenet for theirs.
My own interest lies in conceptual graphs for biomedical research.
Curious what others might see in connections between AMR and CG
Cheers
Jack