The aim of this task is to predict someone's English proficiency based on a text input.

Last update: Dec 13, 2021

Overview

English_proficiency_prediction_NLP

The aim of this task is to predict someone's English proficiency based on a text input.

Using the The NICT JLE Corpus available here : https://alaginrc.nict.go.jp/nict_jle/index_E.html

The source of the corpus data is the transcripts of the audio-recorded speech samples of 1,281 participants (1.2 million words, 300 hours in total) of English oral proficiency interview test. Each participant got a SST (Standard Speaking Test) score between 1 (low proficiency) and 9 (high proficiency) based on this test.

The goal is to build a machine learning algorithm for predicting the SST score of each participant based on their transcript.

Steps:

1 - Pre-process the dataset: extract the participant transcript (all tags). Inside participant transcript, you can remove all other tags and extract only English words.

2 - Process the dataset: extract features with the Bag of Word (BoW) technique

3 - Train a classifier to predict the SST score

4 - Compute the accuracy of your system (the number of participant classified correctly) and plot the confusion matrix.

5 - Try to improve your system (for example you can try to use GloVe instead of BoW).

The aim of this task is to predict someone's English proficiency based on a text input.

Related tags

Overview

English_proficiency_prediction_NLP

Owner

GNES enables large-scale index and semantic search for text-to-text, image-to-image, video-to-video and any-to-any content form

Python utility library for compositing PDF documents with reportlab.

Understanding the Difficulty of Training Transformers

APEACH: Attacking Pejorative Expressions with Analysis on Crowd-generated Hate Speech Evaluation Datasets

Optimal Transport Tools (OTT), A toolbox for all things Wasserstein.

Textpipe: clean and extract metadata from text

code for modular summarization work published in ACL2021 by Krishna et al

PyABSA - Open & Efficient for Framework for Aspect-based Sentiment Analysis

A machine learning model for analyzing text for user sentiment and determine whether its a positive, neutral, or negative review.

Simple Text-To-Speech Bot For Discord

One Stop Anomaly Shop: Anomaly detection using two-phase approach: (a) pre-labeling using statistics, Natural Language Processing and static rules; (b) anomaly scoring using supervised and unsupervised machine learning.

Big Bird: Transformers for Longer Sequences

Built for cleaning purposes in military institutions

Unsupervised Abstract Reasoning for Raven’s Problem Matrices

Official code for Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset

Code for Text Prior Guided Scene Text Image Super-Resolution

A simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN

leaking paid token generator that was a shit lmao for 100$ haha

Flexible interface for high-performance research using SOTA Transformers leveraging Pytorch Lightning, Transformers, and Hydra.

The PyTorch based implementation of continuous integrate-and-fire (CIF) module.