uhh-lt / comparative Goto Github PK
View Code? Open in Web Editor NEWComparative Sentence Classifier
Home Page: http://ltdemos.informatik.uni-hamburg.de/cam/
Comparative Sentence Classifier
Home Page: http://ltdemos.informatik.uni-hamburg.de/cam/
DBpedia ontology:
http://dbpedia.org/ontology/Python
Corpus based on commoncrawl:
http://panchenko.me/data/joint/corpora/common-crawl-2016/cc-2016-en-nohtml-nonoise-sort.txt.gz
ES + Kibana: latest ver. (copy arch.)
Sample code to index/search:
https://gist.github.com/alexanderpanchenko/1dc3634526040d65ca620d4e4fd21b72
3 Pairs, ~200 labeled sentences each:
-> better: a is better than b
-> worse: a is worse than b
-> no comparison: a and b mentioned, but no comparison
-> out: a and b mentioned, but in a list; only a or b mentioned
One sentence per line
embeddings as features
xgboost:
https://machinelearningmastery.com/develop-first-xgboost-model-python-scikit-learn/
1.) get Concepts ("Programming Language", "Cat", "Mammal", ...) from DBPedia
2.) get properties of those concepts ("typing systems", "furriness",...)
3.) get instances of those concepts ("ADA", "Ruby", ...)
3.) find a good list of "competitive discourse markers" ("because", "better,", ...)
4.) generate queries like AND AND AND ("because" OR "better" OR "worse" OR ...)
3.1) remove disambiguation after the name ("e.g. Abdullah (name)")
extract the most representative features of the linear models.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.