All Projects → stanfordnlp → Phrasal

stanfordnlp / Phrasal

Licence: gpl-3.0
A large-scale statistical machine translation system written in Java.

Programming Languages

java
68154 projects - #9 most used programming language

Projects that are alternatives of or similar to Phrasal

Kb Infobot
A dialogue bot for information access
Stars: ✭ 181 (-4.74%)
Mutual labels:  natural-language-processing
Id Nlp Resource
A list of Indonesian NLP resources.
Stars: ✭ 185 (-2.63%)
Mutual labels:  natural-language-processing
Hunspell Dict Ko
Korean spellchecking dictionary for Hunspell
Stars: ✭ 187 (-1.58%)
Mutual labels:  natural-language-processing
Bert Sklearn
a sklearn wrapper for Google's BERT model
Stars: ✭ 182 (-4.21%)
Mutual labels:  natural-language-processing
Dkpro Core
Collection of software components for natural language processing (NLP) based on the Apache UIMA framework.
Stars: ✭ 184 (-3.16%)
Mutual labels:  natural-language-processing
Deep Generative Models For Natural Language Processing
DGMs for NLP. A roadmap.
Stars: ✭ 185 (-2.63%)
Mutual labels:  natural-language-processing
Nlp profiler
A simple NLP library allows profiling datasets with one or more text columns. When given a dataset and a column name containing text data, NLP Profiler will return either high-level insights or low-level/granular statistical information about the text in that column.
Stars: ✭ 181 (-4.74%)
Mutual labels:  natural-language-processing
Germanwordembeddings
Toolkit to obtain and preprocess german corpora, train models using word2vec (gensim) and evaluate them with generated testsets
Stars: ✭ 189 (-0.53%)
Mutual labels:  natural-language-processing
Glad
Global-Locally Self-Attentive Dialogue State Tracker
Stars: ✭ 185 (-2.63%)
Mutual labels:  natural-language-processing
Deep Survey Text Classification
The project surveys 16+ Natural Language Processing (NLP) research papers that propose novel Deep Neural Network Models for Text Classification, based on Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). It also implements each of the models using Tensorflow and Keras.
Stars: ✭ 187 (-1.58%)
Mutual labels:  natural-language-processing
Recurrent Convolutional Neural Network Text Classifier
My (slightly modified) Keras implementation of the Recurrent Convolutional Neural Network (RCNN) described here: http://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/view/9745.
Stars: ✭ 182 (-4.21%)
Mutual labels:  natural-language-processing
Hntitlenator
Test your HN title against a neural network
Stars: ✭ 184 (-3.16%)
Mutual labels:  natural-language-processing
Deepinterests
深度有趣
Stars: ✭ 2,232 (+1074.74%)
Mutual labels:  natural-language-processing
Sentence Similarity
This repository contains various ways to calculate sentence vector similarity using NLP models
Stars: ✭ 182 (-4.21%)
Mutual labels:  natural-language-processing
Notebooks
Jupyter Notebooks with Deep Learning Tutorials
Stars: ✭ 188 (-1.05%)
Mutual labels:  natural-language-processing
Deeptoxic
top 1% solution to toxic comment classification challenge on Kaggle.
Stars: ✭ 180 (-5.26%)
Mutual labels:  natural-language-processing
Neuralqa
NeuralQA: A Usable Library for Question Answering on Large Datasets with BERT
Stars: ✭ 185 (-2.63%)
Mutual labels:  natural-language-processing
Arxivnotes
IssuesにNLP(自然言語処理)に関連するの論文を読んだまとめを書いています.雑です.🚧 マークは編集中の論文です(事実上放置のものも多いです).🍡 マークは概要のみ書いてます(早く見れる的な意味で団子).
Stars: ✭ 190 (+0%)
Mutual labels:  natural-language-processing
Vec4ir
Word Embeddings for Information Retrieval
Stars: ✭ 188 (-1.05%)
Mutual labels:  natural-language-processing
Bert Vocab Builder
Builds wordpiece(subword) vocabulary compatible for Google Research's BERT
Stars: ✭ 187 (-1.58%)
Mutual labels:  natural-language-processing

Phrasal: A statistical machine translation system

Phrasal is licensed under the GPL (v3+). For details, please see the file LICENSE.txt in the root directory of this software package.

Copyright (c) 2007-2016 The Board of Trustees of The Leland Stanford Junior University. All Rights Reserved.

Installation

We use Gradle to build Phrasal. Gradle will install all dependencies. You need Gradle version 2.1+. If you are on OS X, the easiest way to get Gradle is to install Homebrew and then to type brew install gradle.

Linux / Mac OS X

These instructions assume you are using the bash shell, which is usually the default shell.

  1. Switch to the root of the Phrasal repository and execute: gradle installDist

  2. Set PHRASAL_HOME: export PHRASAL_HOME=`pwd`

  3. Set CLASSPATH: export CLASSPATH=$PHRASAL_HOME/build/install/phrasal/lib/*

  4. (Optional) Build Eclipse project files by executing: gradle eclipse.

  5. (Optional, requires g++, JDK) Build the KenLM loader: gradle compileKenLM.

  6. (Optional, requires g++, JDK, and Boost) Build the KenLM language model estimation tools: gradle compileKenLMtools.

Windows

Follow the Linux instructions above. Then be sure to execute gradle startupScripts to generate a .bat file.

Citation

If you use Phrasal for research, then please cite the following paper:

@inproceedings{Green2014,
 author = {Spence Green and Daniel Cer and Christopher D. Manning},
 title = {Phrasal: A Toolkit for New Directions in Statistical Machine Translation},
 booktitle = {In Proceddings of the Ninth Workshop on Statistical Machine Translation},
 year = {2014}
}

Documentation / User Guide

See the user guide for complete installation and configuration instructions. The guide also contains a tutorial for building an MT system from raw text.

Support

We have 3 mailing lists for Phrasal, all of which are shared with other Stanford JavaNLP tools (with the exclusion of the parser).

Each address is at @lists.stanford.edu:

java-nlp-user -- This is the best list to post to in order to ask questions, make announcements, or for discussion among JavaNLP users. You have to subscribe to be able to use it. Join the list via this webpage or by emailing [email protected]. (Leave the subject and message body empty.) You can also look at the list archives.

java-nlp-announce -- This list will be used only to announce new versions of Stanford JavaNLP tools. So it will be very low volume (expect 1-3 message a year). Join the list via via this webpage or by emailing [email protected]. (Leave the subject and message body empty.)

java-nlp-support -- This list goes only to the software maintainers. It's a good address for licensing questions, etc. For general use and support questions, please join and use java-nlp-user. You cannot join java-nlp-support, but you can mail questions to [email protected].

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].