Giter Club home page Giter Club logo

patentsview-disambiguation-clean's Introduction

PatentsView-Disambiguation

Setup

pip install git+git://github.com/iesl/grinch.git
pip install git+git://github.com/epfml/sent2vec.git
conda install pytorch==1.2.0 torchvision==0.4.0 cudatoolkit=9.2 -c pytorch
    `
    python
    import nltk
    nltk.download('stopwords')
    nltk.download('punkt')
    `

Database Setup

Set the following files / values:

config/database_tables.ini
[DATABASE]

granted_patent_database =
pregrant_database =
config/database_config.ini
[DATABASE]

host =
username =
password =

Download Resources

Download pre-trained models for disambiguation, place in resources folder: Google Drive

Inventor

Build Features

python -m pv.disambiguation.inventor.build_assignee_features_sql
python -m pv.disambiguation.inventor.build_coinventor_features_sql
python -m pv.disambiguation.inventor.build_title_map_sql

Build Canopies

python -m pv.disambiguation.inventor.build_canopies_sql

Run clustering

wandb sweep bin/inventor/run_all.yaml
wandb agent $sweep_id
# or using slurm
sh bin/launch_sweep.sh $sweep_id

Finalize

python -m pv.disambiguation.inventor.finalize

Optional: Train Your Own Model

This command trains an inventor disambiguation model.

python -m pv.disambiguation.inventor.train_model --training_data data/inventor-train/eval_common_characteristics.train --dev_data data/inventor-train/eval_common_characteristics.dev --max_num_dev_canopies 200

Assignee

Build Mentions & Canopies

python -m pv.disambiguation.assignee.build_assignee_name_mentions_sql

Run clustering

wandb sweep bin/assignee/run_all.yaml
wandb agent $sweep_id
# or using slurm
sh bin/launch_sweep.sh $sweep_id

Finalize

python -m pv.disambiguation.assignee.finalize

Location

Build Mentions & Canopies

python -m pv.disambiguation.location.build_assignee_location_canopies
python -m pv.disambiguation.location.build_inventor_location_canopies
python -m pv.disambiguation.location.build_assignee_location_mentions
python -m pv.disambiguation.location.build_inventor_location_mentions

Run clustering

wandb sweep bin/location/run_all.yaml
wandb agent $sweep_id
# or using slurm
sh bin/launch_sweep.sh $sweep_id

Finalize

python -m pv.disambiguation.location.finalize

patentsview-disambiguation-clean's People

Contributors

bethanne-card avatar nmonath avatar sarvothaman avatar dipietroch avatar olivierbinette avatar reladric 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.