seamrvaulter / ner Goto Github PK
View Code? Open in Web Editor NEWThis project forked from yana-ponomarova/ner
NER trained to recongnize Oil & Gas supply chain sites and products
This project forked from yana-ponomarova/ner
NER trained to recongnize Oil & Gas supply chain sites and products
Project: TestNER Author: Yana Ponomarova and Selsabil Gaied Creation Date: 12/01/2016 Last updated: 18/01/2016 by Yana Ponomarova Objective: To train a model based on the NER from Stanford NLP library to recognize the Supply Chain entities in the Oil & Gas iundustry: PROD - product (eg., crude oil, gas, heavy crude, diesel), TERM - terminal (eg., Torshamnen terminal), OFI - oil field (eg., Western Siberian Oil Fields), REF - refinery (eg., Lisichansk oil refinery), PIPE - pipeline (or other transportation mode) (eg., Eilat Ashkelon Crude Oil Pipeline) or O - other (all the rest). This model is then applied to determine the entities in the unseen text. Files: 1- main.ner.Train.scala: //CrfTrainer.trainClassifier("FileName","SerializeTo") 2- main.ner.interactiveTraining.scala: An interactive app that presents the user with a document and allows them to annotate each token as a named entity type. By convention, an annotation of "O" means the token is not a named entity. Documents are presented to the user line-by-line. For convenience, hitting "ENTER" indicates the current token is not a named entity and is automatically annotated with a "O". Also for convenience, if the user sees there are no named entities on the current line, they may type "next", in which case all remaining tokens on the current line are automatically annotated with "O" and the next line is presented. All annotations are written to file in a format that can be read by the Stanford NER tool for training. Input: (Required) args(0): File path+name to write annotations val annotationsWriteFile = args(0) args(1):Location of directory containing documents on which to perform annotations. val documentDirectory = args(1) 3- main.ner.NERDemo.scala: Stanford NER Demo file rewritten in Scala Use: - If arguments aren't specified, they default to classifiers/english.muc.7class.distsim.crf.ser.gz and some hardcoded sample text. - Or: args(0): classifier - Else, input required: args(0): classifier args(1): textFile Ex., classifiers/CrudeSupply2.classifier.ser.gz src/main/ressources/SupplyExample.txt 4- main.ner.NERMultiClassifier.scala: same as main.ner.NERDemo.scala, difference that it combines the result of the petro-gaz classifier with the stanford classifier. 5- run.sh (to be completed)
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.