Dec-13-2016, 03:33 PM
Quote:Could you please show - as example - how you would build and fill a dictionary?when working.
Quote:Thanks a lot for your proposition!
??? didn't know I had one
Relations between entities
|
Dec-13-2016, 03:33 PM
Quote:Could you please show - as example - how you would build and fill a dictionary?when working. Quote:Thanks a lot for your proposition! ??? didn't know I had one
Just got back from an appointment.
Last night after football, I was able to get the data from the json files behaving properly. I have started building the dictionaries, and once that is working I'll re-post code with examples of how to extract the data. Should be in the next few hours.
I wish that you had posted the entire task at the start.
Since you sent it in a private e-mail, I ignored it until a few minutes ago. You need to process this corpus with NLTK (nltk can be loaded into your python with 'pip install nltk') once you do this, you can follow how to load a corpus from a JSON file here I tried it, but it failed with the error The command I used was:>>> import codecs >>> reader = codecs.getreader("utf-8") >>> nltk.data.load("https://code.google.com/archive/p/relation-extraction-corpus/downloads/20131104-place_of_death.json")I also tried it without the codecs, and again with escaped slashes. same results. I think that your best bet is to see if you get a byte on your posting in jobs. Again, just so someone knows what their getting into, I'd post the entire task. It's not fair to do less. It no longer makes sense to continue with the dictionary idea
Dec-16-2016, 07:20 PM
(Dec-14-2016, 01:21 AM)Larz60+ Wrote: I wish that you had posted the entire task at the start. You're a better person than me for doing something based off a PM. I would have just responded "post that in the forum". If someone else has the same problem/issue, PMs will never help them :p
Dec-16-2016, 07:39 PM
Quote:I would have just responded "post that in the forum". Actually, I did, but continued for a while until I realized that I was being taken for a walk
Dec-19-2016, 12:33 AM
You two guys are right. So, I have here our to do list.
We're struggling on steps 2 and 3. So if anybody could help, we'd be very happy! PS: Concerning the features - it would help already a lot, if we had a rough structure of the code (so, the features don't have to be too elaborated - we can do this! :) ).
Dec-19-2016, 11:41 AM
(Dec-19-2016, 12:33 AM)MattaFX Wrote: So, I have here our to do list. And that's the list there: Quote:We will perform the classification for two kinds of relations: place of birth and institution. Your task is to design and extract a set of features, to give these features as input to the logistic regression and to evaluate the performance.
Dec-19-2016, 05:55 PM
What has it got to do with Python?
Unless noted otherwise, code in my posts should be understood as "coding suggestions", and its use may require more neurones than the two necessary for Ctrl-C/Ctrl-V.
Your one-stop place for all your GIMP needs: gimp-forum.net
Dec-19-2016, 06:19 PM
|
|