Coder Social home page Coder Social logo

malcolmgreaves / implie Goto Github PK

View Code? Open in Web Editor NEW

This project forked from knowitall/implie

0.0 2.0 0.0 25.64 MB

Implicit relation extractor using a natural language model.

License: BSD 3-Clause "New" or "Revised" License

Scala 99.82% Python 0.18%

implie's Introduction

ImplIE

ImplIE (Implicit relation Information Extraction) is a program that extracts binary relations from English sentences where the relationship between the two entities is not explicitly stated in the text. ImplIE supports the following target relations out-of-the-box: has nationality, has job title, has province, has city, and has religion. However, other relations can be supported by providing a list of keywords for a new target relations. This is possible because ImplIE uses a target independent syntactic language model.

For example, consider the following sentence:

French journalist Paul Legall reported that all three hostages arrived safely at Athens International Airport.

The out-of-the-box ImplIE system extracts the following binary relations:

(French journalist Paul Legall; has nationality; French)
(journalist Paul Legall; has job title; journalist)
(Athens International Airport; has city; Athens)

Building

ImplIE uses Java 8 and the sbt build system. Install sbt. Enter the root directory of this repository and run command

sbt compile

This will take a while the first time since it will download and resolve all the dependencies.

Using ImplIE as a Dependency

We haven't released ImplIE to maven, but it can be released locally. From this repository run the following commands to release the project locally.

sbt
publish-local

Then ImplIE can locally be added as a dependency in sbt by adding the following to the libraryDependencies.

libraryDependencies ++= Seq(
    // other dependencies...
    "edu.washington.cs.knowitall.implie" %% "implie" % "1.0.0-SNAPSHOT",
    // other dependencies...
)

Citing ImplIE

TODO: add bibTex when paper is published

Contributors

  • Gene Kim
  • Natalie Hawkins

implie's People

Watchers

Malcolm Greaves avatar James Cloos avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.