anandvyavahare / nlp-assignment Goto Github PK

Please read this document first to get started with this problem. This document contains introduction to the problem and data used in the problem and metadata of the files present in this folder.

There are separate files for the codes, input data(both CSV and .mp4), guide to setup the project, methodologies and results.

1. Introduction to the problem and Data--> text file for introduction to problem and data used

2. Code Folder: Contains another 2 folders for notebook(.ipynb) and python scripts (.py)

   1. ner_nltk_spacy --> Python script for Named Entity Recognition
   2. sent_analysis_rf --> Python script for Sentiment Analysis
   3. sk_topic_modeling --> Python Script for Topic Modeling using LDA
   4. speech2text.py --> Python script for speech to text conversion

3. csv files folder: Folder contains 3 csv files are used for sentiment analysis, topic modeling, and named entity recognition tasks

   1. dev_sent_emo --> csv file for dev
   2. train_sent_emo --> csv file for training
   3. test_sent_emo --> csv file for testing Note : Please update the paths for the above files at the beginning of every file accordingly

4. Methodoloy and Results: Folder contains 3 .pdf files explaining methodology applied and the results of the respective tasks

   1. NER_Results_Methodology --> For Named Entity Recognition
   2. Sentiment_Analysis_Methodology_Results --> For Sentiment Analysis
   3. Topic_Modeling_LDA_Methodology_Results --> For Topic Modeling using LDA

5. requirements.txt : File to install the dependencies required > pip3 install -r requirements.txt

6. setup.txt : Guide to set up the assignment

7. Input data: Can be found on the link: https://www.kaggle.com/zaber666/meld-dataset