Reverse Dependencies of nltk
The following projects have a declared dependency on nltk:
- textblob — Simple, Pythonic text processing. Sentiment analysis, part-of-speech tagging, noun phrase parsing, and more.
- textboost — A tool leveraged by ML to aid the reading experience through bionic reading.
- TextBooster — Data augmentation techniques for text data using back translation and synonym replacement
- textbot — Read a column of strings from csv, parse wordnet pos_tags to lemmas, enumerate most_common lemmas, weight strings via top scoring lemmas
- textcaret — Simplified NLP Toolkit for unifying common Natural Language Processing Tasks
- textcl — Text preprocessing package for use in NLP tasks
- textcleaning-vgr — text cleaning
- textco — TEXT analytsis COpilot
- textcomplexity — Linguistic and stylistic complexity measures for text
- textcrafts — textcrafts: Summary, keyphrase and relation extraction with dependecy graphs
- texteval — Small python package to calculate the sentence similarity metrics.
- textfab — A tiny library for text preprocessing in NLP
- textfeatureinfo — Package to extract interesting details about text.
- textfeatures — A Python package to get basic features from the text data.
- TextFeatureSelection — Python library for feature selection for text features. It has filter method, genetic algorithm and TextFeatureSelectionEnsemble for improving text classification models. Helps improve your machine learning models
- textfier — Text-based Modifiers
- textflint — Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
- textflow — Simple and extensible framework for end to end text based natural language understanding.
- TextGenerationEvaluationMetrics — Various metrics for evaluating text generation models.
- texthero — Text preprocessing, representation and visualization from zero to hero.
- textherox — Text preprocessing, representation and visualization from zero to hero.
- textkit — Simple text analysis from the command line
- textkit-learn — Helps computers to understand human languages.
- textlytics — TEXTLYTICS -- the Text Analytics Toolkit
- textmining_utility — textmining package that uses existing libraries
- textnormaliser — A python package that runs a series of operations over text to decorate a corpus
- texto — Projet de textométrie.
- textoir — TEXTOIR is the first high-quality Text Open Intent Recognition platform.
- textprepper — TextPrepper is a simple text preprocessing tool designed to modify queries and documents for Langchain applications.
- textprepro — Everything Everyway All At Once Text Preprocessing.
- TextPreProc — The package is created to simplify a users effort of text clearning and exploration. It allows user to clean the data and do some basic analysis like N-gram WordCouds and Topic Modelling
- textraer — Text processor with classification using DataBERT.
- TextRandAug — We are highly thankful to Dr. Paul Buitelaar, Dr. Omnia Zayed, Dr. Mihael Arcan, Dr. John McCrae and Janet Choi. This module was built during 5th week CRT-AI training (NLP week) at National University of Ireland, Galway)
- TextSimila — Text Similarity Recommendation System
- textslack — Play with text data
- textsplitter — A Python library to split large text into smaller chunks based on the maximum token size and other criteria
- textsum — utility for using transformers summarization models on text docs
- texture-viz — Process and profile text datasets interactively
- textures — A python package to extract features from text data
- textweaver — A FastAPI-based web server for working with LLMs, embedding models, and Pinecone Vector DB.
- textwrangler — A simple library for cleaning and pre-processing text.
- tf-core — TextFlows core text mining module
- tf-taggers — TextFlows taggers module
- tfds-nightly — tensorflow/datasets is a library of datasets ready to use with TensorFlow.
- tfds-nightly-gradient — tensorflow/datasets is a library of datasets ready to use with TensorFlow.
- thaidp — ThaiDP = Thai Data Privacy Tool For Python
- thaitextaug — Thai Text Augmentation
- thext — THExt - Transformer-based Highlights Extraction
- thirdai — A faster cpu machine learning library
- thomasthechatbot — A Python chatbot that learns as you speak to it.
- Threaded-Sparse-TFIDF — Multithreading TF-IDF vectorization for similarity search using sparse matrices for computations.
- tidyX — Python package to clean raw tweets for ML applications
- tieval — A framework for evaluation and development of temporal-aware models.
- time-restricted-eating-experiments — This library provides functions to analyzes food logging data.
- timewise-sup — The Timewise Subtraction Pipeline produces mid-infrared difference photometry based on measurements by the WISE satelite
- titania-nlp-project — Named Entity Recognition package using SpaCy
- titleize — Convert Strings to Title Case
- tj-preproc — An NLP Text Preprocessing Package
- tkitAutoRewriter — Terry toolkit sdk for AutoRewriter ,
- tkitSimhash — # Remove duplicates 重复内容筛选 tkitSimhash zh 根据经验,一般当两个文档特征字之间的汉明距离小于 3, 就可以判定两个文档相似。《数学之美》一书中,在讲述信息指纹时对这种算法有详细的介绍。 ```python from tkitSimhash import simHash sim=simHash() text1 = """' , in Valve's absence, the modern slew of co-op zombie games have not
- TLAF — TLA is built using PyTorch, Transformers and several other State-of-the-Art machine learning techniques and it aims to expedite and structure the cumbersome process of collecting, labeling, and analyzing data from Twitter for a corpus of languages while providing detailed labeled datasets for all the languages.
- to-paragraphs — no summary
- to-tmx — Txt-to-tmx file converter.
- tokenizer-hub — Yoctol Natural Language Tokenizer
- tokipona — A package for dealing with toki pona: vim syntax highlighting, tokipona wordnets, analysis of the vocabulary, synthesis of texts
- tomodapi — A framework for performing topic modelling
- toolva — SosiAl Media Bigdata Analysis service by pcn
- topic-cohesion — Cohesion measurement to evaluate partition
- topic-modeling-toolkit — Topic Modeling Toolkit
- topican — Topic analyser
- topicblob — TopicBlob is a package to perform quick and easy topic modeling on text.
- topicexplorer — InPhO Topic Explorer
- topicgpt — A package for integrating LLMs like GPT-3.5 and GPT-4 into topic modelling
- topicmodels — A package for topic modelling in python.
- topicnetwork — Topic modeling with text networks
- topicrankpy — A Python package to get useful information from documents using TopicRank Algorithm.
- topik — A Topic Modeling toolkit
- torch-snippets — One line functions for common tasks
- torchero — A pluggable & extensible trainer for pytorch
- torchmetrics — PyTorch native Metrics
- torchnlp — NLP framework implemented with pytorch
- Toxine — Tiny preprocessor for Russian text
- tpro — tpro processes transcripts from speech-to-text services and outputs to various formats.
- tr-news-scraper — tr-news-scraper is a Python library that allows users to scrape Turkish news articles based on specified keywords from multiple sources. It gather news content from various news websites, enabling users to extract valuable information for analysis or research purposes.
- trainerai — This is A Package Used To Train Your AI Model With Data.
- transcr-esiviero — My first package to make the transcription process easier
- Transformer-Text-AutoEncoder — Transformer Text AutoEncoder: An autoencoder is a type of artificial neural network used to learn efficient encodings of unlabeled data, the same is employed for textual data employing pre-trained models from the hugging-face library.
- transformers — State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
- translatability — Score German noun compounds according to their English-translatability.
- Translation-Gummy — Translation Gummy is a magical gadget which enables user to be able to speak and understand other languages.
- transvec — Multilingual word embeddings.
- traversaal — A semantic search package for hotel data
- treegrams — Extracts sub-tree patterns from NLTK tree structures.
- treets — This library provides functions to analyzes food logging data.
- treform — A text mining tool for Korean and English
- Trial2Vec — Pretrained BERT models for encoding clinical trial documents to compact embeddings.
- trialtracker — Methods to extract and transform clinical trial data
- triplex — Explaining models, with Triples.
- troj — TrojAI provides the troj Python convenience package to allow users to integrate TrojAI adversarial protections and robustness metrics seamlessly into their AI development pipelines.
- trojai — TrojAI model and dataset generation library