WikiOntology Idea

I'm envisioning a web-deliverable system for the PropBank and FrameNet data that allows users to modify or ammend relations between the arguments for purposes of getting as many of these binary subpredicates into place as possible. Considering there's thousands, some sort of wiki-tech might be useful, allowing users to download the up-to-date dataset. Basically, there would be a UI that indicated the arguments for each n-ary predicate or frame and would allow users to ammend relationship types between them. Users would be able to use URI from other domains or create new ones onto the project's domain.

Given the sentence "The boy went to the store on his bike.", we might obtain from some parsers a predicate resembling "went(the boy, to the store on his bike)". The idea is to allow user input to get a dataset matching that sentence to a set of predicates also including "utilized(the boy, his bike, [to go] to the store)", "owns(the boy, [a] bike)". Some sort of XML output would capture this and a UI allowing pairwise connections between noun arguments would allow users to add all the knowledge contained in a sentence. Ideally, these predicates would be further simplied until only simple nouns were interrelated. The idea is to use wiki-collaboration to create a dataset for SRL algorithms.

Head-Driven Phrase Structure Grammar

I'm thinking that the PropBank style of parsing (redwoods treebank) is more readily converted to structured knowledge than part of speech tagging. However, looking over the initial results of some software, it appears that some style of recursion would be of use in capturing all the structure (substructure) of a sentence. Some arguments to the main predicate appear to have discernable structure remaining — if an argument to the predicate could be a predicate, then this would capture as much structure as possible. Also noticing the inability of this style of parser to capture parallel predicates with some sentences that use logical connectives. Different levels in the recursion should be able to reuse arguments from across the sentence. I may have to code up a prototype to obtain as much semantic structure as possible, possibly outputting a set of these parses that capture it in parallel.

Also looking into initializing this style of parser with the POS-style to discern the main verb and then the remainder in order. After entity recognition and string concatenation of multiword nouns, parsers seem to function more accurately. I'm going to look at the parse trees for verb hierarchy and SBAR information to construct recursive predicate structures, utilize the NP information to bootstrap entity recognition, and post here which code appears “easiest” to build from.

[1] Miyao, Y. and Tsujii, J. 2004. Deep linguistic analysis for the accurate identification of predicate-argument relations. In Proceedings of the 20th international Conference on Computational Linguistics (Geneva, Switzerland, August 23 - 27, 2004). International Conference On Computational Linguistics. Association for Computational Linguistics, Morristown, NJ, 1392.

[2] Towards Parsing Unrestricted Text into PropBank Predicate-Argument Structures