asyml / asyml/forte

A Classification Example in Forte Pipeline

Open
#328 0 comments 0 reactions 1 assignee Claimed by @ziqian98 View on GitHub
e/3 model_interface
Dominant language
Python
Stars
253
Forks
59
PR merge metrics
No merged PRs in 30d

Description

**Is your feature request related to a problem? Please describe.**
Provide Forte with a classification example

**Describe the solution you'd like**
1. Using the reader to parse the dataset as Sentence Datapack and Token Datapack

2. Using the Text Extractor on the input to Build the word embedding table from a Token level and using the Attribute Extractor again on the output to get the label information from the Sentence Level.

3. Build a CNN and a Bert sentence classifier for the sentiment classification task on the IMDB movie review dataset.
(https://www.kaggle.com/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews)

**Describe alternatives you've considered**
Attribute Extractor in the output maybe replaced by other extractors.

**Additional context**
View the idea design at:
(https://drive.google.com/file/d/17kcwu-XOVzk-8lEmVDWWASuAohPIA-PQ/view?usp=sharing)

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.