L'organisation Stanford NLP possède une présence publique significative sur GitHub, avec un large éventail de dépôts. Ils développent principalement en Python, Java et C, avec des projets notables comme DSPy, CoreNLP et stanza, qui sont largement utilisés pour le traitement du langage naturel.
DSPy: The framework for programming—not prompting—language models
CoreNLP: A Java suite of core NLP tools for tokenization, sentence segmentation, NER, parsing, coreference, sentiment analysis, etc.
Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
Software in C and data files for the popular GloVe model for distributed word representations, a.k.a. word vectors or embeddings
Course notes for CS224N Winter17
Stanford NLP Python library for Representation Finetuning (ReFT)
Tree-structured Long Short-Term Memory networks (http://arxiv.org/abs/1503.00075)
Stanford NLP Python library for understanding and improving PyTorch models via interventions
String-to-String Algorithms for Natural Language Processing
Python interface to CoreNLP using a bidirectional server-client interface.
Implementation for the paper "Compositional Attention Networks for Machine Reasoning" (Hudson and Manning, ICLR 2018)
A large-scale statistical machine translation system written in Java.
SPINN (Stack-augmented Parser-Interpreter Neural Network): fast, batchable, context-aware TreeRNNs
Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
The baselines used in the CoQA paper
Framework for learning dialogue agents in a two-player game setting.
Stanford NLP group's shared Python tools.
Stanford's Alexa Prize socialbot
[Deprecated] This library has been renamed to "Stanza". Latest development at: https://github.com/stanfordnlp/stanza
Workflow-Guided Exploration: sample-efficient RL agent for web tasks
Logical structure analysis for visually structured documents
http://cs224n.stanford.edu
Aucune description fournie pour ce dépôt.
Model training tutorials for the Stanza Python NLP Library
Code for Relevance-guided Supervision for OpenQA with ColBERT (TACL'21)
Mapping natural language commands to web elements
Aucune description fournie pour ce dépôt.
A baseline system for ContractNLI (https://stanfordnlp.github.io/contract-nli/)
Semantic Parser with Execution
Code for Learning to Generate Compositional Color Descriptions
Demos for the MiniWoB++ benchmark
Python bindings for Stanford CoreNLP's protobufs.
Code for our paper Resources and Evaluations for Multi-Distribution Dense Information Retrieval
Scripts for pushing models to huggingface repos
ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts
An English NER dataset built from foreign newswire
Universe: a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.
Aucune description fournie pour ce dépôt.
Updated version of SST
Extra hand parsed data for training models
Aucune description fournie pour ce dépôt.
datasets for plotting
Aucune description fournie pour ce dépôt.
CoQA -- A Conversational Question Answering Challenge
Web interface for the plotting project
Dataset for pdf-struct (https://github.com/stanfordnlp/pdf-struct)
A fork of ParlAI supporting Chirpy Cardinal's custom neural generator
A repository for hosting models for https://github.com/stanfordnlp/pdf-struct
A history of NLP at Stanford, initially written for the Stanford NLP 25 year reunion in 2025
A re-implementation of nndep using PyTorch.
Stanford's Alexa Prize socialbot [internal]
Sindhi tokenization data from ISRA
The repository for making new post submissions to the SAIL Blog
Aucune description fournie pour ce dépôt.
Stanford NLP développe divers projets liés au traitement du langage naturel, incluant des bibliothèques comme CoreNLP et stanza, ainsi que des outils pour le fine-tuning et la représentation des mots.
L'organisation utilise principalement Python, Java et C pour ses projets, mais elle exploite également d'autres langages comme TeX et Lua dans certains de ses dépôts.
Oui, tous les dépôts de stanfordnlp sur GitHub sont publics, permettant à la communauté d'accéder à leurs projets, de contribuer et d'utiliser leurs outils pour le traitement du langage naturel.
Surveillez Stanford NLP avec RepoGuard et soyez alerté dès qu'un nouveau dépôt public apparaît.
Surveiller ce compte