CASM-Consulting / baleen

Entity Extraction Text Processor

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Baleen

See readme of upstream project here .

Getting Started

Run cd baleen; mvn package; ./start.sh to build an executable and run it.

Once running, the server can be accessed at http://localhost:6413. Use HTTP POST requests to have Baleen annotate data for you:

wget http://0.0.0.0:3124/sussex/consume --post-data='data=[{"text":"hello from www.google.com in Germany","id":"4"},{"text":"hello from www.google.com in Germany and drink 2 pints of water every day","id":"3"}]' -qO-

Responses are in the form

[{"text":"hello from www.google.com in Germany","id":"1","locations":[],"urls":["www.google.com"],"quantities":[]},{"text":"hello from www.google.com in Germany and drink 2 pints of water every day","id":"2","locations":[],"urls":["www.google.com"],"quantities":["2 pints"]}]

Currently only quantities, URLs and locations are extracted and returned.

About

Entity Extraction Text Processor

License:Apache License 2.0


Languages

Language:Java 80.0%Language:JavaScript 14.6%Language:HTML 3.2%Language:CSS 2.0%Language:Shell 0.0%