Code Monkey home page Code Monkey logo

kirubarajan / narrative_chains Goto Github PK

View Code? Open in Web Editor NEW
14.0 2.0 4.0 313 KB

An implementation of (Chambers and Jurafsky, 2008), using updated machine learning models, and different training data domains for an independent study at the University of Pennsylvania.

Home Page: https://kirubarajan.com/blog/narrative

License: MIT License

Python 99.10% Shell 0.90%
narrative-chains natural-language-processing ppmi spacy dependency-parsing machine-learning

narrative_chains's Introduction

welcome!

i research machine learning for natural language processing and i like full-stack development

narrative_chains's People

Contributors

kirubarajan avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

narrative_chains's Issues

How to generate the model?

Hi Arun,

This looks like a great system! Thank you for making it available under the MIT license!

I installed it today (noting that it took a while to install pymagnitude), however when I went to run the preexisting model on sample input, neither the model.pickle nor data/input1.txt were there. I was wondering whether these files were available somewhere, or if not, how to generate them? I saw that it may depend on having the Annotated Gigaword here (https://catalog.ldc.upenn.edu/LDC2012T21). Is it correct that I need to obtain this dataset in order to generate the model? Also, what is the format of the input1.txt file?

Thanks!

I'm trying to extract narrative chains to mine typical responses to previous actions for how people respond to difficult situations such as domestic violence, and then generate Monte-Carlo simulations based on the possible responses:

consider(B,do(B,issueWarningOfConsequences(B,A))) :-                                                                                                                                                                                                                                                                           
    believe(B,do(A,physicallyAttack(A,B))).                                                                                                                                                                                                                                                                                    
consider(B,do(B,fileAPoliceReportAbout(B,A))) :-                                                                                                                                                                                                                                                                               
    believe(B,do(A,physicallyAttack(A,B))). 

Once these simulations are running, I can begin constructing professionally recommended responses using a BDI agent. Once these good responses are created, the system can then function as a real-time decision aid to people in difficult situations.

Regards,
Andrew

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.