Python implementation of an N-gram language model with Laplace smoothing and sentence generation.
-
Updated
Feb 9, 2018 - Python
Python implementation of an N-gram language model with Laplace smoothing and sentence generation.
OpenCV, apply 'Homogeneous', 'Gaussian' filter on image.
SUPERVISED LEARNING: REGRESSION: Linear - Polynomial - Ridge/Lasso CLASSIFICATION: K-NN - Naïve Bayes - Decision Tree - Logistic Regression - Confusion Matrix - SVM TIME SERIES ANALYSIS: Linear & Logistic Regr. - Autoregressive Model - ARIMA - Naïve - Smoothing Technique UNSUPERVISED LEARNING: CLUSTERING: K-Means - Agglomerative - Mean-Shift - F…
This stores the CS2731 course projects in the Natural Language Processing class.
A Bigram Language Model from scratch with no-smoothing and add-one smoothing. Outputs bigram counts, bigram probabilities and probability of test sentence.
Developed N-gram based and LSTM based Language Models for various channels of social media
Built a system from scratch in Python which can detect spelling and grammatical errors in a word and sentence respectively using N-gram based Smoothed-Language Model, Levenshtein Distance, Hidden Markov Model and Naive Bayes Classifier.
Methods for numerical differentiation of noisy data in python
Identifying the boundaries of main content of fiction and non-fiction works in the HathiTrust Extracted Features dataset.
Created by Mehmet Zahid Genç
In this section, we will perform time series analysis by participating in the Gdz Elektrik Datathon 2023 competition.
Offical implementation of "Adaptive Smoothing Gradient Learning for Spiking Neural Networks", ICML 2023
Implementation of smoothing-based optimization algorithms
Course Repository for ELL881 (Special Topics:Modern Natural Language Processing), 6th Semester, 2023, IITD
A secure Image Processing pipeline based on Homomorphic Encryption, capable of performing various central tasks. Most notably, it includes matching encrypted images using the SIFT algorithm.
An NLP project leveraging character trigrams and smoothing techniques (Lidstone, Linear Discounting, Absolute Discounting) for language identification. Trained on for Spanish, Italian, English, French, Dutch, and German, achieving 99.8932% accuracy. Includes datasets, model parameters, and comprehensive documentation.
Add a description, image, and links to the smoothing-methods topic page so that developers can more easily learn about it.
To associate your repository with the smoothing-methods topic, visit your repo's landing page and select "manage topics."