StarSpace是一个对于各种实体进行表示学习的工具（StarSpace is a general-purpose neural model for efficient learning of entity embeddings for solving a wide variety of problems）

    主要可以解决的问题包括：

    （1）Learning word, sentence or document level embeddings

    （2）Text classification, or any other labeling task.

    （3）Metric/similarity learning, e.g. learning sentence or document similarity.

    （4）Embedding graphs, e.g. multi-relational graphs such as Freebase.

 环境要求：linux系统，(gcc-4.6.3 or newer) or (clang-3.3 or newer)

    Compilation is carried out using a Makefile, so you will need to have a working make.

    install Boost library and specify the path of boost library in makefile in order to run StarSpace

    Boost安装：

$wget https://dl.bintray.com/boostorg/release/1.63.0/source/boost_1_63_0.zip
$unzip boost_1_63_0.zip
$sudo mv boost_1_63_0 /usr/local/bin

    build StarSpace

git clone https://github.com/facebookresearch/Starspace.git
cd Starspace
make

    输入数据格式：

    Each line will be one input example, in the simplest case the input has k words, and each labels 1..r is a single word

word_1 word_2 ... word_k __label__1 ... __label__r

    数据格式和fasttext一样：

参考：

https://github.com/facebookresearch/Starspace