Hi Kasun, On 3/16/15 7:28 AM, kasun perera wrote: > Hi Marco > > After going through the Warm-up tasks I have started writing the GSOC > proposal. But going through the code-repo and Warm-up tasks I see > current code take as input a Wikipedia corpus and perform the following > steps: > > 1. Verb extraction and ranking > 2. Frame Classifier Training > 3. Frame Extraction > > But in project idea 5.1. it says these steps are to be implemented > during the GSOC period. But I see above steps are already implemented in > the current fact-extractor code right? The implementation is far from complete, the current codebase is more the first step from ideas to code. > So what are the project > expectations during the GSOC period? please clarify. To implement a text extractor to be included in the DBpedia Extraction Framework. > > > On Wed, Mar 4, 2015 at 1:59 PM, [email protected] > <mailto:[email protected]> <[email protected] > <mailto:[email protected]>> wrote: > > Hi Kasun, > > The sentence substrings identified via entity linking will be the fe > candidates. > Then I think you got the idea behind the verb ranking step. > > Cheers! > > ----- Reply message ----- > Da: "kasun perera" <[email protected] > <mailto:[email protected]>> > A: "Marco Fossati" <[email protected] <mailto:[email protected]>> > Cc: "dbpedia-gsoc" <[email protected] > <mailto:[email protected]>> > Oggetto: GSOC_2015 Fact Extraction from Wikipedia Text > Data: mer, mar 4, 2015 07:08 > > > Hi Marco > > On Mon, Mar 2, 2015 at 5:23 PM, Marco Fossati <[email protected] > <mailto:[email protected]>> wrote: > > > > 2- Also it mentioned the use of NLP techniques to process > Wikipedia > text. Does this means extraction of Dependency relationships > to get the > frame elements (FE) and lexical unit(LU)? > > Dependency parsing may not be needed, since entity linking can > be applied to fulfill the task. > > > I'm not clear what you mean by use of entity-linking to identify FE > candidates. In general Named entity linking (NEL) means linking the > mentions of entities in text to a central knowledge base(e.g. > Wikipedia). Do you mean to use the above concept to find FE's? Can > you please clarify bit more on use of entity-linking to identify FE's? > > This is the my understanding of the step-1 of the idea i.e. Verb > extraction and Ranking. > We use a list of domains (e.g. Sports) then dig in to more specific > sub-domain (e.g. Soccer, Cricket, Rugby ect) of Wikipedia. The > navigate to specific wiki-pages under the sub domain. For each wiki > page we extract and rank the verbs based on the sub-domain and > higher ranked verbs are used as LU's. > What are your comments about this idea? > > Thanks > > > > > -- > Regards > > Kasun Perera > > > > > -- > Regards > > Kasun Perera >
-- Marco Fossati http://about.me/marco.fossati Twitter: @hjfocs Skype: hell_j ------------------------------------------------------------------------------ Dive into the World of Parallel Programming The Go Parallel Website, sponsored by Intel and developed in partnership with Slashdot Media, is your hub for all things parallel software development, from weekly thought leadership blogs to news, videos, case studies, tutorials and more. Take a look and join the conversation now. http://goparallel.sourceforge.net/ _______________________________________________ Dbpedia-gsoc mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/dbpedia-gsoc
