sentencepiece - Unsupervised text tokenizer for Neural Network-based text generation.

  •        388

SentencePiece is an unsupervised text tokenizer and detokenizer mainly for Neural Network-based text generation systems where the vocabulary size is predetermined prior to the neural model training. SentencePiece implements sub-word units (also known as wordpieces [Wu et al.] [Schuster et al.] and byte-pair-encoding (BPE) [Sennrich et al.]) with the extension of direct training from raw sentences. SentencePiece allows us to make a purely end-to-end system that does not depend on language-specific pre/postprocessing.This is not an official Google product.



Related Projects

PyTorch-NLP - Supporting Rapid Prototyping with a Toolkit (incl. Datasets and Neural Network Layers)

  •    Python

PyTorch-NLP, or torchnlp for short, is a library of neural network layers, text processing modules and datasets designed to accelerate Natural Language Processing (NLP) research. Join our community, add datasets and neural network layers! Chat with us on Gitter and join the Google Group, we're eager to collaborate with you.

zhihu - This repo contains the source code in my personal column (https://zhuanlan

  •    Jupyter

This repo contains the source code in my personal column (, implemented using Python 3.6. Including Natural Language Processing and Computer Vision projects, such as text generation, machine translation, deep convolution GAN and other actual combat code.

spaCy - 💫 Industrial-strength Natural Language Processing (NLP) with Python and Cython

  •    Python

spaCy is a library for advanced Natural Language Processing in Python and Cython. It's built on the very latest research, and was designed from day one to be used in real products. spaCy comes with pre-trained statistical models and word vectors, and currently supports tokenization for 20+ languages. It features the fastest syntactic parser in the world, convolutional neural network models for tagging, parsing and named entity recognition and easy deep learning integration. It's commercial open-source software, released under the MIT license. 💫 Version 2.0 out now! Check out the new features here.

neuralmonkey - An open-source tool for sequence learning in NLP built on TensorFlow.

  •    Python

The Neural Monkey package provides a higher level abstraction for sequential neural network models, most prominently in Natural Language Processing (NLP). It is built on TensorFlow. It can be used for fast prototyping of sequential models in NLP which can be used e.g. for neural machine translation or sentence classification. The higher-level API brings together a collection of standard building blocks (RNN encoder and decoder, multi-layer perceptron) and a simple way of adding new building blocks implemented directly in TensorFlow.

fastText_multilingual - Multilingual word vectors in 78 languages

  •    Jupyter

Facebook recently open-sourced word vectors in 89 languages. However these vectors are monolingual; meaning that while similar words within a language share similar vectors, translation words from different languages do not have similar vectors. In a recent paper at ICLR 2017, we showed how the SVD can be used to learn a linear transformation (a matrix), which aligns monolingual vectors from two languages in a single vector space. In this repository we provide 78 matrices, which can be used to align the majority of the fastText languages in a single space. Word embeddings define the similarity between two words by the normalised inner product of their vectors. The matrices in this repository place languages in a single space, without changing any of these monolingual similarity relationships. When you use the resulting multilingual vectors for monolingual tasks, they will perform exactly the same as the original vectors. To learn more about word embeddings, check out Colah's blog or Sam's introduction to vector representations.

OpenNMT-tf - Neural machine translation and sequence learning using TensorFlow

  •    Python

and all of the above can be used simultaneously to train novel and complex architectures. See the predefined models to discover how they are defined and the API documentation to customize them. Additional experimental models are available in the config/models/ directory and can be used with the option --model <>.

gensim - Topic Modelling for Humans

  •    Python

Gensim is a Python library for topic modelling, document indexing and similarity retrieval with large corpora. Target audience is the natural language processing (NLP) and information retrieval (IR) community. If this feature list left you scratching your head, you can first read more about the Vector Space Model and unsupervised document analysis on Wikipedia.

lectures - Oxford Deep NLP 2017 course


This repository contains the lecture slides and course description for the Deep Natural Language Processing course offered in Hilary Term 2017 at the University of Oxford. This is an applied course focussing on recent advances in analysing and generating speech and text using recurrent neural networks. We introduce the mathematical definitions of the relevant machine learning models and derive their associated optimisation algorithms. The course covers a range of applications of neural networks in NLP including analysing latent dimensions in text, transcribing speech to text, translating between languages, and answering questions. These topics are organised into three high level themes forming a progression from understanding the use of neural networks for sequential language modelling, to understanding their use as conditional language models for transduction tasks, and finally to approaches employing these techniques in combination with other mechanisms for advanced applications. Throughout the course the practical implementation of such models on CPU and GPU hardware is also discussed.

models - Model configurations

  •    Python

PaddlePaddle provides a rich set of computational units to enable users to adopt a modular approach to solving various learning problems. In this repo, we demonstrate how to use PaddlePaddle to solve common machine learning tasks, providing several different neural network model that anyone can easily learn and use. The word embedding expresses words with a real vector. Each dimension of the vector represents some of the latent grammatical or semantic features of the text and is one of the most successful concepts in the field of natural language processing. The generalized word vector can also be applied to discrete features. The study of word vector is usually an unsupervised learning. Therefore, it is possible to take full advantage of massive unmarked data to capture the relationship between features and to solve the problem of sparse features, missing tag data, and data noise. However, in the common word vector learning method, the last layer of the model often encounters a large-scale classification problem, which is the bottleneck of computing performance.

ludwig - Ludwig is a toolbox built on top of TensorFlow that allows to train and test deep learning models without the need to write code

  •    Python

Ludwig is a toolbox built on top of TensorFlow that allows to train and test deep learning models without the need to write code. All you need to provide is a CSV file containing your data, a list of columns to use as inputs, and a list of columns to use as outputs, Ludwig will do the rest. Simple commands can be used to train models both locally and in a distributed way, and to use them to predict on new data.

magnitude - A fast, efficient universal vector embedding utility package.

  •    Python

A feature-packed Python package and vector storage file format for utilizing vector embeddings in machine learning models in a fast, efficient, and simple manner developed by Plasticity. It is primarily intended to be a simpler / faster alternative to Gensim, but can be used as a generic key-vector store for domains outside NLP. Vector space embedding models have become increasingly common in machine learning and traditionally have been popular for natural language processing applications. A fast, lightweight tool to consume these large vector space embedding models efficiently is lacking.

dynet - DyNet: The Dynamic Neural Network Toolkit

  •    C++

DyNet is a neural network library developed by Carnegie Mellon University and many others. It is written in C++ (with bindings in Python) and is designed to be efficient when run on either CPU or GPU, and to work well with networks that have dynamic structures that change for every training instance. For example, these kinds of networks are particularly important in natural language processing tasks, and DyNet has been used to build state-of-the-art systems for syntactic parsing, machine translation, morphological inflection, and many other application areas. Read the documentation to get started, and feel free to contact the dynet-users group group with any questions (if you want to receive email make sure to select "all email" when you sign up). We greatly appreciate any bug reports and contributions, which can be made by filing an issue or making a pull request through the github page.

pattern - Web mining module for Python, with tools for scraping, natural language processing, machine learning, network analysis and visualization

  •    Python

It is well documented, thoroughly tested with 350+ unit tests and comes bundled with 50+ examples. The source code is licensed under BSD and available from This example trains a classifier on adjectives mined from Twitter using Python 3. First, tweets that contain hashtag #win or #fail are collected. For example: "$20 tip off a sweet little old lady today #win". The word part-of-speech tags are then parsed, keeping only adjectives. Each tweet is transformed to a vector, a dictionary of adjective → count items, labeled WIN or FAIL. The classifier uses the vectors to learn which other tweets look more like WIN or more like FAIL.

nlpcaffe - natural language processing with Caffe

  •    C++

NLP-Caffe is a pull request [1] on the Caffe framework developed by Yangqing Jia and Evan Shelhamer, among other members of the BVLC lab at Berkeley and a large number of independent online contributers. This fork makes it easier for NLP users to get started without merging C++ code. The current example constructs a language model for a small subset of Google's Billion Word corpus. It uses a two-layer LSTM architecture that processes in excess of 15,000 words per second [2], and achieves a perplexity of 79. More examples for Machine Translation using the encoder-decoder model and character-level RNNs are in the works. This code will eventually be merged into the Caffe master branch. This work was funded by the Stanford NLP Group, under the guidance of Chris Manning, and with the invaluable expertise of Thang Luong.

decaNLP - The Natural Language Decathlon: A Multitask Challenge for NLP

  •    Python

The Natural Language Decathlon is a multitask challenge that spans ten tasks: question answering (SQuAD), machine translation (IWSLT), summarization (CNN/DM), natural language inference (MNLI), sentiment analysis (SST), semantic role labeling(QA‑SRL), zero-shot relation extraction (QA‑ZRE), goal-oriented dialogue (WOZ, semantic parsing (WikiSQL), and commonsense reasoning (MWSC). Each task is cast as question answering, which makes it possible to use our new Multitask Question Answering Network (MQAN). This model jointly learns all tasks in decaNLP without any task-specific modules or parameters in the multitask setting. For a more thorough introduction to decaNLP and the tasks, see the main website, our blog post, or the paper. While the research direction associated with this repository focused on multitask learning, the framework itself is designed in a way that should make single-task training, transfer learning, and zero-shot evaluation simple. Similarly, the paper focused on multitask learning as a form of question answering, but this framework can be easily adapted for different approached to single-task or multitask learning.

practical-machine-learning-with-python - Master the essential skills needed to recognize and solve complex real-world problems with Machine Learning and Deep Learning by leveraging the highly popular Python Machine Learning Eco-system

  •    Jupyter

"Data is the new oil" is a saying which you must have heard by now along with the huge interest building up around Big Data and Machine Learning in the recent past along with Artificial Intelligence and Deep Learning. Besides this, data scientists have been termed as having "The sexiest job in the 21st Century" which makes it all the more worthwhile to build up some valuable expertise in these areas. Getting started with machine learning in the real world can be overwhelming with the vast amount of resources out there on the web. "Practical Machine Learning with Python" follows a structured and comprehensive three-tiered approach packed with concepts, methodologies, hands-on examples, and code. This book is packed with over 500 pages of useful information which helps its readers master the essential skills needed to recognize and solve complex problems with Machine Learning and Deep Learning by following a data-driven mindset. By using real-world case studies that leverage the popular Python Machine Learning ecosystem, this book is your perfect companion for learning the art and science of Machine Learning to become a successful practitioner. The concepts, techniques, tools, frameworks, and methodologies used in this book will teach you how to think, design, build, and execute Machine Learning systems and projects successfully.

sling - SLING - A natural language frame semantics parser

  •    C++

SLING is a parser for annotating text with frame semantic annotations. It is trained on an annotated corpus using Tensorflow and Dragnn.The parser is a general transition-based frame semantic parser using bi-directional LSTMs for input encoding and a Transition Based Recurrent Unit (TBRU) for output decoding. It is a jointly trained model using only the text tokens as input and the transition system has been designed to output frame graphs directly without any intervening symbolic representation.

nlpnet - A neural network architecture for NLP tasks, inspired in the SENNA system

  •    Python

Gitter is chat room for developers. nlpnet is a Python library for Natural Language Processing tasks based on neural networks. Currently, it performs part-of-speech tagging, semantic role labeling and dependency parsing. Most of the architecture is language independent, but some functions were specially tailored for working with Portuguese. This system was inspired by SENNA.