https://github.com/dimits-ts/text_analytics

Language Modelling (text generation, spell correction) and Sentiment Analysis / POS Tagging with MLP, RNN, CNN and BERT models and LLM prompting
https://github.com/dimits-ts/text_analytics

baseline-model bert cnn fasttext-embeddings language-modeling llm mlp-classifier pos-tagging prompting pytorch rnn sentiment-analysis sklearn spell-correction tensorflow text-generation transformers transformers-library

Last synced: about 9 hours ago
JSON representation

Language Modelling (text generation, spell correction) and Sentiment Analysis / POS Tagging with MLP, RNN, CNN and BERT models and LLM prompting

• Host: GitHub
• URL: https://github.com/dimits-ts/text_analytics
• Owner: dimits-ts
• Created: 2024-01-16T10:19:31.000Z (10 months ago)
• Default Branch: master
• Last Pushed: 2024-03-31T10:56:11.000Z (7 months ago)
• Last Synced: 2024-04-22T02:45:10.505Z (7 months ago)
• Topics: baseline-model, bert, cnn, fasttext-embeddings, language-modeling, llm, mlp-classifier, pos-tagging, prompting, pytorch, rnn, sentiment-analysis, sklearn, spell-correction, tensorflow, text-generation, transformers, transformers-library
• Language: Jupyter Notebook
• Homepage:
• Size: 69.1 MB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Text Analytics

## Language Moddeling

We create bigram, trigram and linear interpolation language models which are used for language generation and spell correction. 

[Source code](https://github.com/dimits-exe/text_analytics/tree/master/language_modeling) [Report](https://github.com/dimits-exe/text_analytics/blob/master/language_modeling/report.pdf)

## Sentiment Classification and POS Tagging tasks

We create deep learning models using the `Transformers\Datasets`, `Pytorch` and `Tensorflow` libraries. 

We also use the `keras_tuner` / `transformers_trainer` frameworks to optimize hyperparameters and model architecture.

We briefly mention additional tasks carried out:

* Sentiment Analysis: Dataset selection, exploratory analysis, custom stopwords, data augmentation. 

* POS Taggging: Dataset selection, exploratory analysis, custom parsing, custom baseline ("smart dummy") model, local caching of heavy computations, automated results generation (python -> LaTeX).

Each task features two IPython notebooks containing the executed code, python source files for repeated custom tasks and a unified report.

The reports discuss in detail the design decisions for each classifier and include graphs and aggregated results comparing the current model to the previous models.   

### Simple MLP model

[Sentiment classification](https://github.com/dimits-exe/text_analytics/blob/master/mlp_nlp/ex_9.ipynb) [POS Tagging](https://github.com/dimits-exe/text_analytics/blob/master/mlp_nlp/ex_10.ipynb) [Report](https://github.com/dimits-exe/text_analytics/blob/master/mlp_nlp/report.pdf)

### RNN Model

[Sentiment classification](https://github.com/dimits-exe/text_analytics/blob/master/rnn/ex_1.ipynb) [POS Tagging](https://github.com/dimits-exe/text_analytics/blob/master/rnn/ex2.ipynb) [Report](https://github.com/dimits-exe/text_analytics/blob/master/rnn/report.pdf)

### CNN Model

[Sentiment classification](https://github.com/dimits-exe/text_analytics/blob/master/cnn/ex_2.ipynb) [POS Tagging](https://github.com/dimits-exe/text_analytics/blob/master/cnn/ex3.ipynb) [Report](https://github.com/dimits-exe/text_analytics/blob/master/cnn/report.pdf)

### BERT Model

[Sentiment classification](https://github.com/dimits-exe/text_analytics/blob/master/transformers/ex_1.ipynb) [POS Tagging](https://github.com/dimits-exe/text_analytics/blob/master/transformers/ex3.ipynb) [Report](https://github.com/dimits-exe/text_analytics/blob/master/transformers/report.tex)