hmm i decided to utilize existing approaches in dependency parsing. 

to create the knowledge graph from reading to create the dependency graph based interpretation in neo4j using wikidata ontology and my new grammar ontology definition to outline these dependency graph in such new ontology definition. hmm .

hmm. I think i decided to go with initially following methodology:

i would create the dependency and span based graphs interpretations of paragraphs.

hmm i would also try to create a topological interpretation for verbs in the dependency graph. 

e.g. take verb.  could be considered as one topological space giving one constituent to another topological space unless they are not hausdorffly separated in the new topological space.

or for instance go verb: connected region in a topological space and a sequence like iterating subset in the topological space. 

so i would try to myself create topological ontological rdf definitions for all verbs and their additional meanings and synonyms would of course reuse existing definitions. 

So its not that complicated job thinking of Sumerian cuneiforms not so much language alphabet items but still having the representability power. I mean its common patterns of verbs are not a huge universal set but could be defined topologically.

so the ontological signature of those bindings: hmm topological rdf defintion would cover remap the dependency graph's verb and also other its such verb's ontological signature wise topological spaces could then be figured out with training. 

hmm of course there might be necessity to build word embeddings that e.g for ambiguity resolution in  a verb's subject/object's ontological signatures, such ontological frequentialist definitions surely could be prereadied. 

hmm this might be utilized with morphism training based neural networks later to predict also the topological definition,

hmm. i think i would first create the span analysis and dependency definition with a method like above paper, then would also have wiki ontology data be ready present as a graph db data. then, verbs i would try to recreate their topological rdf defintions. not an endless study it would be since the universal set is not infinite its finite. so in such rdf definition, there might be also heuristical natively defined intentionalities. so such method might also takes from emergentist approach beside essentialists/frequentialist approaches all together. hmm so not only ai would know the go word defintion but it would understand its understanding in topology rdf including not simple verbs like go but for instance: look after word: this means e.g. i look after my plant. it means a temporality knowledge and intentionality knowledge scope all along the simple look after verb. i mean there would be also temporal informnation a temporal representation for verb and also it could have heuristical intentionality knowledge on preset. 

so a verb's defintion which woukld be defined topology rdf wise, there would be also intentionality and temporal scope of such verbs' use cases. e,g, look after is not a instantenous activity, i look after to my plant for a time. (since i newly bought plants i give such example) but that be also having many possible temporal defintions at the same time. e..g e verb might have suych different possible representations and along wth grammar sense of verb we might have some more information or from the following sentence's temporarl definition. 

so seems as lots of tasks but interesting. hmm would need to whilst prepare the wikidata ontology knowledge db, and plus, the dependency extraction/span constituent analyser addition. then also verb's such mentioned topological definitions would be defined this would be by me unfortunatley but not an infinite verbs would be defined it would be a bounded set and would be extended by synonyms. later this topological defintiion creation part should be automatedly tried to be understood by examples from dictiopnary and plus defintiion of words. but an initial set of verbs would needed to be defined by me.

hmm so it would be a lot of tasks. but completeable. not an infinitely many tasks.