Reverse Dependencies of nltk
The following projects have a declared dependency on nltk:
- DunkinDonut — no summary
- dupecheck — Check for duplicate word series between generated text and a dataset
- DupliPy — A package for formatting and text replication, with added support for image augmentation.
- dutch-text-analytics — Dutch Text Analytics is a versatile toolkit designed to facilitate the exploration, execution, and validation of a diverse range of Natural Language Processing (NLP) tasks specifically tailored for the Dutch language. This repository provides a comprehensive set of tools, including code examples, scripts, and resources, to enhance and streamline your Dutch NLP projects.
- dvg — document-vector grep
- DXC-AI-Test — A Python package for DXC AI work
- dynamicfluency — The base python package for DynamicFluency: Monitor and understand the dynamicity of linguistic aspects in (L2) speech.
- dyslexic-readability — A readability scoring library tailored to the specific needs of Turkish dyslexic readers.
- e2eml — An end-to-end solution for automl
- e2eqavn — e2eqavn is end to end pipeline for question answering
- eaas — Evaluation as a Service for Natural Language Processing
- easyCorpus — a simple corpus tool
- easyeditor — easyeditor - Editing Large Language Models
- easyinstruct — An Easy-to-use Instruction Processing Framework for Large Language Models.
- easyjailbreak — Easy Jailbreak toolkit
- easyLDA — easily bult LDA Topic Models with just a list of docs (e.g. a list of twitter posts in CSV/TXT
- EasyNERTag — Easy tagging for annotate NER corpus
- easySum — You can easily summarize the text.
- easyted — A Python library for easy calculation of tree edit distances with visualization capabilities.
- eazeml — EazeML makes Task of Machine Learning and Data Science super easy.
- eazynlp — NLP made easy for researchers
- eda-ja — no summary
- edu-convokit — Edu-ConvoKit: An Open-Source Framework for Education Conversation Data
- edu-segmentation — To improve EDU segmentation performance using Segbot. As Segbot has an encoder-decoder model architecture, we can replace bidirectional GRU encoder with generative pretraining models such as BART and T5. Evaluate the new model using the RST dataset by using few-shot based settings (e.g. 100 examples) to train the model, instead of using the full dataset.
- education-inquiry-package — no summary
- EFCAMDAT — A library for doing all preprocessing related to EFCAMDAT
- efemarai — A CLI and SDK for interacting with the Efemarai ML testing platform.
- eflow — no summary
- ekphrasis — Text processing tool, geared towards text from social networks, such as Twitter or Facebook. Ekphrasis performs tokenization, word normalization, word segmentation (for splitting hashtags) and spell correction.
- ela — A Python package for exploratory lithology analysis
- elasticsearch-dsl — Python client for Elasticsearch
- electivegroup — A simple resume parser used for extracting information from resumes
- elon-newspaper1 — ffffffffffffffffff
- emacnn — A CLI for training a neural network on a specific YouTube channel's videos.
- email-decomposer — Fuzzy decomposition of email prefix to first/last name
- email-txt-classification — compiled packages
- embedded-topic-model — A package to run embedded topic modelling
- embeddings-explorer — A package for generating, exploring, and visualizing word embeddings graphs.
- embeddings-prep — A word2vec preprocessing and training package
- embeddingsprep — A word2vec preprocessing and training package
- embedeval — NLP Embeddings Evaluation Tool
- emiliaworks — Legitimacy Index
- emoatlas — no summary
- EmoLexGram — EmoLexGram is a python package for text-based emotion classification
- emora-stdm — Library for creating state-machine-based chatbots.
- emoter — A chatbot system integrated with a sentiment analyzer library (Emote) that is able to empathize with users.
- EmoTFIDF — A library to extract emotions using two methods, 1- Using lexicon based, counting frequency of emotion2- Integrating TFIDF to add a contextNote that lexicon license is for research purposes only.
- emoticon — python package to transform any emoticon to text or its meaning
- EmotionExtractor — Extract Emotion Words from Text or Word Tokens
- emotionpyy — Detecting emotions behind the text, pyemotionpyy package will help you to understand the emotions in textual meassages.
- empathy-machines — An off-the-rack NLP sentiment classifier- upload your own corpus or use the pre-installed ones
- empythy — An off-the-rack NLP sentiment classifier- upload your own corpus or use the pre-installed ones
- emucorebrain — Brain of EmulationCore
- en-tts — Web app, command-line interface and Python library for synthesizing English texts into speech.
- engawa — no summary
- english-text-normalization — Command-line interface (CLI) and library to normalize English texts.
- enlivensystems-newspaper — Simplified python article discovery & extraction.
- enlp — Python library of NLP functions originally collated by Equinor Knowledge and AI Data Science team.
- entail — Python Distribution Utilities
- entex — Text Entity Extractor
- enti — A toolkit for unstructured text
- entity_extract — Used for the entity extraction of a text and a corpora and to compare and reduce entity lists
- entity-search — Entity Search
- EntityExtractor — Extract specific entities from a text. Give Base64 and get a JSON formatted output data.
- EqFlow — Introducing EqFlow: Your all-in-one solution for efficient web scraping, AI development, and more. Streamline your projects with its intuitive API, eliminating the need for multiple libraries like requests and bs4. EqFlow's lightning-fast performance and simplified syntax redefine coding, making tasks that once required extensive code a breeze. Elevate your coding experience, embrace efficiency, and unlock your true creative potential with EqFlow.
- eric-chen-forward — Classifier for institution and scholar data
- errudite — NLP error analysis.
- erutils — no summary
- esanalyzer — Emotion("fear", "anger", "surprise", "sadness", "disgust", "joy") and Sentiment("Positive","Negative") Analysis
- esco-playground — no summary
- espnet — ESPnet: end-to-end speech processing toolkit
- EssaySummarizer — Essay Summarizer.
- etc-ml — etc project
- ethnicseer — name-ethnicity classifier
- evals — no summary
- evals-nightly — no summary
- evaluate — HuggingFace community-driven open-source library of evaluation
- everyvoice — Text-to-Speech Synthesis for the Speech Generation for Indigenous Language Education Small Teams Project
- evidently — Open-source tools to analyze, monitor, and debug machine learning model in production.
- excel-ngrams — An app to output n-grams from column in Excel spreadsheet
- Expanda — Integrated Corpus-Building Environment
- explainaboard — Explainable Leaderboards for Natural Language Processing
- explainitall — no summary
- ExplanationText — no summary
- extra-model — Code to run the Extra algorithm for unsupervised topic extraction.
- fabler — Multimodal AI Story Teller, built with Stable Diffusion, GPT, and neural text-to-speech.
- FacebookMessengerAnalyzer — A library which allows users to easily run simple Data Analytics on their Facebook Messenger Data
- factscore — FactScore is an automatic evaluation metric for factual precision in long-form text generation. It uses large language models and retrieval to break down generations into atomic facts and then measure the correctness with respect to a knowledge source (like Wikipedia).
- FactScoreLite — FactScore (Fine-grained atomic evaluation of factual precision in long form text generation) computing package.
- FactualSceneGraph — A package for scene graph parsing and evaluation
- faithscore — Faithscore is a noverl metric for evaluating hallucinations in large vision-language models!
- faker-file — Generate files with fake data.
- faknow — A unified library for fake news detection.
- faKy — faKy is a Python library for text analysis. It provides functions for readability, complexity, sentiment, and statistical analysis in the scope of fake news detection.
- falcon-evaluate — Falcon Evaluate is an open-source Python library designed to simplify the process of evaluating and validating open source LLM models such as llama2,mistral ,etc. This library aims to provide an easy-to-use toolkit for assessing the performance, bias, and general behavior of LLMs in various natural language understanding (NLU) tasks.
- farm-haystack — LLM framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data.
- fast-forward-job-hunting — Fast Forward Job Hunting speeds up your job seeking efforts. It saves your time and helps you into employment significantly faster.
- fast-keywords — Fast keyword identification with n-gram vector string matching.
- fast-psq — Efficient Implementation of Probabilistic Structured Queries
- fast-scores — no summary