Search Results for "python::module"

Chonkie is an AI-powered framework designed for building conversational agents and chatbots with natural language understanding and multi-turn conversation support.

Transformers4Rec is an advanced recommendation system library that leverages Transformer models for sequential and session-based recommendations. The library works as a bridge between natural language processing (NLP) and recommender systems (RecSys) by integrating with one of the most popular NLP frameworks, Hugging Face Transformers (HF). Transformers4Rec makes state-of-the-art transformer architectures available for RecSys researchers and industry practitioners. Traditional recommendation...

FunNLP is a large, curated collection of resources, corpora, and tools for Chinese natural language processing (NLP). It aggregates datasets, lexicons, wordlists, sentiment dictionaries, knowledge graphs, and pretrained model references, serving as a one-stop resource hub for Chinese NLP practitioners. The repository is organized into categories such as sentiment analysis, text classification, named entity recognition, knowledge graphs, and various lexicons (e.g. sensitive words, emotion...

XLM (Cross-lingual Language Model) is a family of multilingual pretraining methods that align representations across languages to enable strong zero-shot transfer. It popularized objectives like Masked Language Modeling (MLM) across many languages and Translation Language Modeling (TLM) that jointly trains on parallel sentence pairs to tighten cross-lingual alignment. Using a shared subword vocabulary, XLM learns language-agnostic features that work well for classification and sequence...

cocoNLP is a lightweight natural-language processing toolkit geared toward practical information extraction from raw text, especially for Chinese and mixed Chinese–English content. Instead of requiring a heavy pipeline, it focuses on quick wins such as extracting names, places, organizations, emails, phone numbers, and dates directly from unstructured sentences. The project blends pattern-based methods with NLP heuristics, giving developers dependable results for real-world texts like chats,...

Turku Event Extraction System (TEES) is a free and open source natural language processing system developed for the extraction of events and relations from biomedical text. It is written mostly in Python, and should work in generic Unix/Linux environments. Currently, the TEES source code repository still remains on GitHub at http://jbjorne.github.com/TEES/ where there is also a wiki with more information.

...Students work through programming exercises and problem sets that build intuition for both classical algorithms (like HMMs and CRFs) and neural approaches (like word embeddings and sequence models). The materials emphasize theory grounded in practical experimentation, often via Python notebooks or scripts that visualize results and encourage ablation studies. Clear organization and self-contained examples make it possible to follow along outside the classroom, using the repo as a self-study resource. For learners and instructors alike, the course provides a coherent path from foundational linguistics to current techniques, with reproducible code that makes concepts concrete.

The program provides Java interface (to C++ Lemmatizer via XML-RPC) in order to perform lemmatizing in Russian, English, and German (lemma is the canonical form of a lexeme in Natural Language Processing). RussianPOSTagger could work as a module of GATE.

MutationFinder is a biomedical natural language processing (NLP) system for extracting mentions of point mutations from free text. MutationFinder achieves high performance (99% precision, 81% recall on blind test data) as an information extraction system

Collection of Python scripts providing interactions between the sociological investigation platform and webservices (such as NLP, search engine, web database).