hmm yesterday started to get my self introduce to NLP/Linguistic topics. e.g. before Part of Speech tags I had slightly known but now learning more details. 

And started to setup machine learning library dependencies to start running the constituency parsers and dependency extractors and parse tree conceptual constructs/concepts. 

Hmm specifically the PTB dependency constructs are interesting to check and to later transform to the RDF with topographic definitions. 

hmm so today's task set would be continueing NLP/Linguistics study most and initiation of design of translated RDF design. of topological RDF definition of language constructs. and also to tie the wikidata ontological definitions to topological RDF definitions. hmm then this would be like stored in mainly in neo4j i think. all of these. then there might i also create query language format to neo4j other than its usual sql alike query interface but specific to inference capabilities from this multitude of RDFs and topological RDF representations. 

hmm for two days I would investigate the dependency graph linkages. e.g. one paragraph being created dependency graph and constituency information then how to tie to that for another paragraph. 

and creation of outlining RDFs for the various rdf definitions.

then this would be like a static intelligence that is not with neuroplasticity.

there the neuroplasticity factors of other inference capabilities based on topological constructs would be defined by later after 0.1 versions.

0.1 version would be a mere inference capability having static intelligence having interpreter ai. 

but then the generative inference capabilities would be added after 0.1 version.

so 0.1's goal is to be able to interpret paragraphs articles in its topological RDF based representations. but this would be like encyclopedic intelligence and with lacking neuroplasticity. that is further study after 0.1 version specific math grammars and inference capabilities with maths topological definitions and followingly other such futures would be added in 0.2 0.3 version. hmm but 1.0 version would be fully capable of doing generative inference system by then. this be the feature map of agile product iterations of this ai project. 

---------------------------------------------------------------------------------

hmm so lots of works this weekend. first learning about more the PTB and linguistics algorithms/theories along with the neural network based libraries for those.

then at the same time to use some topology tools to define initial language constituency and dependency graph informations to some universal type topological RDF definition. I think I would start this RDF definition by then. 

so the original neural networks might then craft a dependency graph and constituency data, then the to be coded translator would convert this graph to its topological translation of interpreted knowledge. 

so this weekend would be also alot topology studies. (hmm there is also holiday on monday). 

hmm so by end of today to be reached goals:

learning alot about linguistic theories regarding constituency information/dependency graphs and essentialist language theories on those graphs/algorithms for those. 

then in tandem applying /analysing those libraries with neural networks or not to generate such data.

then tomorrows goal would be revisiting topology study and to start crafting topology RDF. and start conversion logic of those parsed information to topological RDF definitions and then crafting some query language to do inferences on those topology knowledge graphs(interpreted knowledge graphs). 

Then i guess this would be 0.1 ai version right? some thing that has static intelligence and can do ifnerence (not exactly like apache jena's inference engine either). It would be rather topological based inference system and a query language that would be like defined with antlr to do effectively query /do inferences on interpreted knowledge graphs. i mean neither alike jena's inference engine nor neo4j's sql like query syntax, but more about topological reasoning type inference query language would be crafted. than when those all ready 0.1 version would be ready.  then after that neuroplasticity study starts. and more maths topologies definitions and inherent inference systems then last, design of generative inference systems.