Code Monkey home page Code Monkey logo

Comments (2)

LittlePea13 avatar LittlePea13 commented on May 29, 2024 1

Hi there, for the pre-training phase there are no entity types, since we didn't include them in the silver data process.

However, when evaluating on downstream tasks, the model is finetuned and predicts the entity type by use of special tokens. Therefore it depends on which task/dataset specifically you refer to.

For instance, in CONLL04, 4 special tokens are added, <peop>, <org>, <other> and <loc> which are used in place of the <subj>, <obj> tokens that surround decoded entities:

tokenizer.add_tokens(['<peop>', '<org>', '<other>', '<loc>'], special_tokens = True)

Therefore a triplet instance looks like this: <triplet> Richard C. Wallace <peop> Pittsburgh <loc> residence.

If you need REBEL to predict entity types, you would need to finetune it on your own dataset or any of the benchmarks reported in the paper.

Hope this helps!

from rebel.

Buted avatar Buted commented on May 29, 2024

Your explanation answers my question. Thx for your kind answer :)

from rebel.

Related Issues (20)

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.