NLP
Notes
Links
- SpaCy - Industrial-strength Natural Language Processing (NLP) with Python and Cython. (HN: SpaCy 3.0 (2021))
- NLP progress - Track the progress in Natural Language Processing (NLP) and give an overview of the state-of-the-art across the most common NLP tasks and their corresponding datasets. (Web)
- LASER Language-Agnostic SEntence Representations - Library to calculate and use multilingual sentence embeddings.
- nlp-tutorial - Tutorial for who is studying NLP(Natural Language Processing) using TensorFlow and PyTorch.
- ParlAI - Framework for training and evaluating AI models on a variety of openly available dialogue datasets.
- Project Alias - Open-source parasite to train custom wake-up names for smart home devices while disturbing their built-in microphone.
- Transfer NLP library - Framework built on top of PyTorch to promote reproducible experimentation and Transfer Learning in NLP.
- Unsupervised Data Augmentation - Semi-supervised learning method which achieves state-of-the-art results on a wide variety of language and vision tasks.
- Introduction to Natural Language Processing book - Survey of computational methods for understanding, generating, and manipulating human language, which offers a synthesis of classical representations and algorithms with contemporary machine learning techniques.
- SentenceRepresentation - Code acompanies the paper 'Learning Sentence Representations from Unlabelled Data' Felix Hill, KyungHyun Cho and Anna Korhonen 2016.
- Megatron LM - Ongoing research training transformer language models at scale, including: BERT & GPT-2.
- XLNet - New unsupervised language representation learning method based on a novel generalized permutation language modeling objective.
- sticker - Sequence labeler that uses either recurrent neural networks, transformers, or dilated convolution networks.
- Interactive Attention Visualization - Small example of an interactive visualization for attention values as being used by transformer language models like GPT2 and BERT.
- GluonNLP - Toolkit that enables easy text preprocessing, datasets loading and neural models building to help you speed up your NLP research.
- Natural Language Toolkit (NLTK) - Suite of open source Python modules, data sets, and tutorials supporting research and development in Natural Language Processing. (Web) (Book)
- NLP 100 Exercise - Bootcamp designed for learning skills for programming, data analysis, and research activities. (Code)
- This Word Does Not Exist - Allows people to train a variant of GPT-2 that makes up words, definitions and examples from scratch. (Code) (HN)
- Inferbeddings - Injecting Background Knowledge in Neural Models via Adversarial Set Regularisation.
- nlp - Lightweight and extensible library to easily share and access datasets and evaluation metrics for NLP.
- Language Interpretability Tool (LIT) - Interactively analyze NLP models for model understanding in an extensible and framework agnostic interface.
- BERTopic - Topic modeling technique that leverages BERT embeddings and c-TF-IDF to create dense clusters allowing for easily interpretable topics whilst keeping important words in the topic descriptions.
- Sentence-BERT for spaCy - Wraps sentence-transformers (also known as sentence-BERT) directly in spaCy.
- Simple Transformers - Based on the Transformers library by HuggingFace. Lets you quickly train and evaluate Transformer models.
- Deep Bidirectional Transformers for Language Understanding (2020) - Explains a legendary paper, BERT. (HN)
- LambdaBERT - Transformers-style implementation of BERT using LambdaNetworks instead of self-attention.
- LAMA: LAnguage Model Analysis - Probe for analyzing the factual and commonsense knowledge contained in pretrained language models.
- The Pile - Large, diverse, open source language modelling data set that consists of many smaller datasets combined together.
- Contextualized Topic Models - Family of topic models that use pre-trained representations of language (e.g., BERT) to support topic modeling.
- NLU - Power of Spark NLP, the Simplicity of Python. 1 line for hundreds of NLP models and algorithms.
- FastSeq - Provides efficient implementation of popular sequence models (e.g. Bart, ProphetNet) for text generation, summarization, translation tasks etc.
- FastFormers - Provides a set of recipes and methods to achieve highly efficient inference of Transformer models for Natural Language Understanding (NLU).
- huggingface_hub - Client library to download and publish models and other files on the huggingface.co hub.
- SLING - A natural language frame semantics parser - Built to learn to read and understand Wikipedia articles in many languages for the purpose of knowledge base completion.
- Deep Daze - Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network).
- rust-bert - Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...).
- Shifterator - Interpretable data visualizations for understanding how texts differ at the word level.
- Big Sleep - Simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN.
- Beyond the Imitation Game Benchmark (BIG-bench) - Collaborative benchmark intended to probe large language models, and extrapolate their future capabilities.
- AutoNLP - Automatic way to train, evaluate and deploy state-of-the-art NLP models for different tasks.
- Classical Language Toolkit (CLTK) - Python library offering natural language processing (NLP) for pre-modern languages. (Web)
- GENRE (Generarive ENtity REtrieval) - Uses a sequence-to-sequence approach to entity retrieval (e.g., linking), based on fine-tuned BART architecture.
- DensePhrases - Provides answers to your natural language questions from the entire Wikipedia in real-time.
- adapter-transformers - Friendly fork of HuggingFace's Transformers, adding Adapters to PyTorch language models.
- GPT-NeoX - Implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library.
- Transformers Interpret - Model explainability tool designed to work exclusively with the transformers package.
- Evaluation Harness for Large Language Models - Framework for few-shot evaluation of autoregressive language models.
- ConceptNet Numberbatch - Set of semantic vectors (also known as word embeddings) than can be used directly as a representation of word meanings.
- BEIR - Heterogeneous benchmark containing diverse IR tasks. It also provides a common and easy framework for evaluation of your NLP-based retrieval models within the benchmark.