Explore Projects

Discover 46 open source projects

Active filters (1):
Search: sentence×
Clear all

Showing 21-40 of 46 projects

ddangelov/Top2Vec

Top2Vec learns jointly embedded topic, document and word vectors for semantic search and topic modeling.

3.1K
Archived
Python
LLM Wrappers & SDKs
API Frameworks
Python
#topic-modeling#semantic-search#sentence-embedding

iChochy/NCE

This is an online learning platform for the New Concept English language learning series, with features like course text reading and sentence-level audio.

2.6K
Stable
JavaScript
Tutorials & Courses
Frontend Frameworks
JavaScript
#english-learning#nce#course-content

facebookresearch/large_concept_model

Large Concept Models for language modeling in a sentence representation space using PyTorch.

2.3K
Archived
Python
LLM Frameworks
API Frameworks
PyTorch
#language-models#nlp#seq2seq

MinishLab/model2vec

A high-performance library for generating state-of-the-art static embeddings for natural language processing tasks.

2.0K
Stable
Python
LLM Frameworks
API Frameworks
Python
#embeddings#machine-learning#nlp

yongzhuo/Keras-TextClassification

A comprehensive set of Keras-based NLP models for text classification, similarity, and more, with support for Chinese and English.

1.8K
Archived
Python
LLM Frameworks
API Frameworks
Keras
#nlp#text-classification#embeddings

IntelLabs/fastRAG

Efficient retrieval augmentation and generation framework for multi-modal information retrieval and question-answering

1.8K
Active
Python
LLM Frameworks
RAG Frameworks
PyTorch
#information-retrieval#question-answering#multi-modal

undertheseanlp/underthesea

Underthesea is a powerful Vietnamese NLP toolkit for developers working with natural language processing tasks.

1.7K
Active
Python
LLM Frameworks
API Frameworks
#vietnamese#nlp#natural-language-processing

nyu-mll/jiant

jiant is an NLP toolkit that provides pre-trained BERT models and tools for multi-task learning and transfer learning.

1.7K
Archived
Python
LLM Frameworks
Fine-tuning
PyTorch
#nlp#bert#transformers

terrifyzhao/bert-utils

BERT-based utility library for generating sentence vectors and performing text classification

1.7K
Archived
Python
React
#text-vectorization#natural-language-processing#bert

jasonwei20/eda_nlp

Data augmentation for NLP using CNN and RNN, presented at EMNLP 2019

1.6K
Archived
Python
Python
#data-augmentation#nlp#text-classification

yongzhuo/nlp_xiaojiang

A comprehensive NLP toolkit for Chinese language processing, including chatbots, text similarity, classification, and more.

1.5K
Archived
Python
LLM Frameworks
API Frameworks
PyTorch
#nlp#chatbot#text-classification

WenRichard/KBQA-BERT

A BERT-based knowledge graph question-answering system with online and offline modes.

1.5K
Archived
Python
LLM Frameworks
API Frameworks
Python
#bert#knowledge-graph#nlp

winkjs/wink-nlp

A developer-friendly natural language processing library for building chatbots, extracting entities, and analyzing sentiment.

1.4K
Stable
JavaScript
NLP Frameworks
API Frameworks
Node.js
#natural-language-processing#sentiment-analysis#named-entity-extraction

textstat/textstat

A Python package to calculate readability statistics of text objects, including paragraphs, sentences, and articles.

1.4K
Stable
Python
CLI Tools
API Frameworks
Python
#readability#text-analysis#nlp

natasha/natasha

Python library for solving basic Russian NLP tasks, with an API for lower level Natasha projects.

1.3K
Archived
Python
Natural Language Processing
CLI Tools
Python
#nlp#russian#tokenizer

SeanLee97/xmnlp

Chinese NLP library with various tools and features for text processing, analysis, and manipulation.

1.3K
Archived
Python
React
#NLP#Chinese NLP#text processing

segment-any-text/wtpsplit

A robust, efficient, and adaptable toolkit for segmenting text into sentences or other semantic units.

1.3K
Active
Python
NLP
API Frameworks
Python
#natural-language-processing#sentence-segmentation#deep-learning

epfml/sent2vec

A C++ library for unsupervised sentence representation learning, useful for AI-powered coding tools.

1.2K
Archived
C++
LLM Frameworks
#natural-language-processing#machine-learning#text-embeddings

unitaryai/detoxify

Detoxify is a Python library with trained models to detect toxic comments, built using Pytorch Lightning and Transformers.

1.2K
Active
Python
Computer Vision
API Development
Pytorch Lightning
#bert#nlp#toxic-comments

xiaoxu193/PyTeaser

A Python library that summarizes news articles by extracting the most important sentences.

1.2K
Archived
Python
Text Processing
CLI Tools
Python
#news#summarization#text-processing

Stay in the loop

Get weekly updates on trending AI coding tools and projects.