good-turing-smoothing 开源项目推荐（22 个）

ddbourgin /numpy-ml

机器学习，在numpy

maxbane /simplegoodturing

Python implementation of Gale and Sampson's (1995/2001) "Simple Good Turing" algorithm.

StarlangSoftware /NGram-Py

Ngrams with Basic Smoothings

StarlangSoftware /NGram-CPP

Ngrams with Basic Smoothings

StarlangSoftware /NGram-CS

Ngrams with Basic Smoothings

StarlangSoftware /NGram

Ngrams with Basic Smoothings

ChinmayMittal /ELL881

Course Repository for ELL881 (Special Topics:Modern Natural Language Processing), 6th Semester, 2023, IITD

oqadiSAK /ngram-language-model

Statistical language model of Turkish utilizing ngrams of Turkish syllables with Good Turing smoothing implementation.

Raina-Xin /KnowSum

Code for Evaluating the Unseen Capabilities: How Many Theorems Do LLMs Know?

AslanDevbrat /Computational-Linguistic

Assigmnents of CL

StarlangSoftware /NGram-Js

Ngrams with basic smoothing.

StarlangSoftware /NGram-Cy

Ngrams with Basic Smoothings

apriljkissinger /DS_Capstone_Coursera

Text Prediction algorithm and app built for the Capstone Project of the Coursera: John Hopkins Data Science Certification. Utilizes a quadri-gram model with Kneser-Ney smoothing and Good Turning Frequency Estimation.

MarkoMilenovic01 /NGramLanguageModels

Implementation of classical n-gram language models with Good-Turing and Kneser–Ney smoothing for NLP.

ebylmz /turkish-ngram-model

📖 N-Gram language model for Turkish

mayankmittal29 /SmoothLM---N-gram_Language_Modeling_with_Smoothing

An implementation of n-gram language models with various smoothing techniques for natural text generation and analysis with tokenization and perplexity calculations

MallaSailesh /LanguageModelling-And-Tokenization

Implemented a tokenizer class , some language models techniques and based on those models generating next words.

MarcosWendell /word_prediction_in_corpus

Assignment for Computational Linguistics' course - Tilburg University

DrFarouk /word-frequency-estimation

A coursework-style project from my MSc Machine Learning on Big Data (University of East London), using PySpark to compute word frequency distributions on a large English corpus (~9.5 million words) and to compare frequency estimates from small samples against the full dataset.

aguswip /numpy2

Simplify NumPy integration in web applications with automated JSON serialization and framework support for FastAPI, Flask, and Django.