Comments (3)
This sounds like a good strategy to me - let's try it and see what we come
back with. After going through all the hand coded articles I felt like the
most important geoinfo was definitely in the headline and first paragraph.
/////////////////////////////
Catherine D'Ignazio
Research Assistant, MIT Media Lab Center for Civic Media
[email protected] || [email protected] || @kanarinka || +1
617 501 2441 || www.kanarinka.com ||
http://civic.mit.edu/blog/kanarinka/
On Fri, Oct 25, 2013 at 12:16 PM, rahulbot [email protected] wrote:
The idea would be to score each country mention. A regular mention would
earn 1 point. A mention in the headline would earn 3 points. The first
mention in the article would earn 2 points. Those number are fairly
arbitrary.Then the country the article is about would be the one with the most
points.See #5 (comment)#5 (comment) a motivating example in the hand-coded corpus, plus this idea just sort
of felt right to us in earlier email discussions.—
Reply to this email directly or view it on GitHubhttps://github.com//issues/6
.
from cliff-annotator.
Catherine why don't you take this one - so you can learn the Java stuff I added. Check out the stuff in the edu.mit.civic.mediacloud.where.aboutness
and make your own subclass of AboutnessStrategy
in there. Then instantiate that in edu.mit.civic.mediacloud.ParseManager.aboutness
and see if it works better.
from cliff-annotator.
ok great! Will try to do before Thursday (finishing writing up my thesis
proposal at the moment)
www.kanarinka.com || [email protected] || 617-501-2441
On Tue, Oct 29, 2013 at 9:57 AM, rahulbot [email protected] wrote:
Catherine why don't you take this one - so you can learn the Java stuff I
added. Check out the stuff in the edu.mit.civic.mediacloud.where.aboutnessand make your own subclass of
AboutnessStrategy in there. Then instantiate that in
edu.mit.civic.mediacloud.ParseManager.aboutness and see if it works
better.—
Reply to this email directly or view it on GitHubhttps://github.com//issues/6#issuecomment-27304379
.
from cliff-annotator.
Related Issues (20)
- return better status while index is building HOT 1
- charIndex of mentions is offset by preceding demonyms when replaceAllDemonyms=true HOT 2
- `results.mentions.source.string` contains the normalised country name, intead of the raw string matched. HOT 2
- integrate co-ref resolution into person entity counts HOT 1
- DELETE IT
- upgrade default Stanford NER to v3.9.2 HOT 9
- News Articles about Washington, always resolve to Washington state instead of Washington, DC. HOT 1
- support language at the query level HOT 1
- move configuration to env-vars HOT 1
- rename packages to match brand HOT 1
- Are there any API docs which go over what the meaning of each key in the json response means? HOT 5
- Can't get CLIFF to run HOT 2
- Unable to access through tomcat (404 error) HOT 1
- Unable to geoparse German text HOT 1
- Gazetteer index Error HOT 3
- Live demo currently down HOT 2
- upgrade to latest NER HOT 1
- upgrade to latest CLIFF
- Add support for French HOT 1
- What is the maximum sequence length? HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from cliff-annotator.