Awesome GitHub RepositoriesN-Gram Co-occurrence Models

fastText is a library and framework for word embedding generation, text vectorization, and supervised text classification. It provides tools to transform raw text into fixed-length vector representations and to train models that assign category labels to sentences or documents. The system utilizes subword-based vectorization and character n-gram embeddings, allowing it to generate meaningful vectors for words that were not present during training. To manage resource usage, it includes a quantized language model implementation that employs product quantization and dimensionality reduction to d

LanguageTool is a multilingual grammar and style checking engine designed to detect spelling, grammar, and writing errors across multiple languages. It provides automated proofreading capabilities that can be deployed as a self-hosted server or executed as a standalone local desktop application. The project distinguishes itself through a flexible rule development framework, allowing linguistic patterns to be defined via XML or implemented as custom Java classes. It utilizes n-gram frequency modeling for confused word detection and supports neural word embeddings to improve disambiguation betw

This project is a collection of pre-trained dense and sparse word vectors trained on diverse Chinese corpora. It serves as a library of linguistic representations and an NLP vector dataset designed to improve the accuracy of semantic and morphological analysis in text models. The collection provides corpus-specific representations and utilizes n-gram co-occurrence modeling to capture diverse linguistic patterns. It includes a hybrid of dense-sparse vectors to balance computational efficiency and semantic precision. The project covers semantic vector search and the development of Chinese natu

This project is a collection of foundational machine learning algorithms and data science tools implemented in Python. It focuses on building the logic of these tools using basic programming primitives rather than relying on specialized libraries. The implementation covers several core domains, including a linear algebra library for matrix and vector operations, a statistical analysis toolkit for probability and hypothesis testing, and a framework for map-reduce distributed processing. It also includes implementations for natural language processing, graph theory for network analysis, and var

TextBlob is a natural language processing library that provides a unified interface for common linguistic tasks. It operates as a wrapper-based API, simplifying the use of complex processing libraries by delegating core operations to specialized external frameworks. The project features a pluggable processing pipeline that allows for the integration of custom logic and alternative language engines. It supports the extension of processing models through plugins to add specific language support or custom data processing. The library covers a broad range of linguistic capabilities, including se

Apache Hive is a SQL-on-Hadoop data warehouse that enables querying and managing petabytes of data stored in distributed storage such as HDFS and cloud storage services. It provides a familiar SQL interface for batch analytics and reporting, supported by a core set of components including the HiveServer2 Thrift service for remote query execution, the Hive Metastore Service for central metadata management, the Hive ACID Transaction Engine for concurrent read-write operations, and the Hive LLAP Interactive Engine for low-latency analytical processing. The WebHCat REST API offers an HTTP interfac

makemore is a character-level language model and text generation engine. It serves as an educational implementation of the architecture and training processes used in large language models, built as a neural network using the PyTorch framework. The system demonstrates sequence prediction by learning the probability distributions of characters within a dataset to generate novel text strings. It implements this through a progression of techniques, including n-gram probability modeling and the use of automatic differentiation for weight optimization. The project covers the full machine learning

This project is a CJK input method framework and configuration set designed for the Rime input engine. It provides a comprehensive system of schemas and dictionary packs to optimize Chinese character entry through pinyin and double-pinyin workflows. The framework is distinguished by its use of Lua-powered extensions that add dynamic utilities, such as inline mathematical calculators, automated timestamps, and text formatting, directly to the input interface. It also features refined word libraries and language models specifically tuned to improve prediction accuracy and first-choice hit rates