StarSpace

This completely misunderstands what this is. In this context "knowledge graph" means a representation of knowledge independent of it's serialization format (ie, RDF vs whatever). It's usable wherever you have a key value (key:value of relationship) or a triple (key:relationship:something). This is probably 85% of everything that is stored in a database, with the exception being paths that vary enough that you can't use the path as a key or relationship. In particular, most trees are suitable if you use collapse the path down to a single relationship. I've done a bunch of work on graph embedding. They are very effective for use in anything that can be thought of as a recommendation system ("this person would like these books") or similarity ("this person is similar to these people"). Back when I was working on them I found Starspace wonder

I like https://github.com/facebookresearch/Starspace#graphspace-lin... for fast and easy graph embedding generation via a GNN.

I like the README.md for StarSpace[1] because it has lots of examples which get you thinking. I used graph embeddings as input to a classifier to classify people when follower/followee information was easy to gather but text wasn't. Basically anything that can be represented as a graph can be used. There is some interesting work being done using code syntax trees as input which uses a very similar approach. See code2vec[2] I'm not aware of any way to transfer text embeddings into graph emneddings, but you can could concatenate them and use them together (I've done this before) or maybe do some dimension reduction or do a multi-task learning thing and try to learn some combined representation. I'm not ware of the scalability limits for this particular library, but Facebook Research's pytorch-biggraph[3] (released 2 days ago) scales to tril

"this margin is too small to contain" I really should write a post or something about it. Basically you do a co-embedding of the graph and natural language and then you can use either to find the other. Something very roughly like the ImageSpace co-embedding example from StarSpace[1], but you do a graph representation on one side, and a phrase/sentence representation on the other. [1] https://github.com/facebookresearch/Starspace

Nice list. Nr. 1, FastText, was actually released in the middle of 2016 :-) The world moves fast… Maybe they confused it with StarSpace [0], also by Facebook Research, which was indeed published in 2017? [0] https://github.com/facebookresearch/StarSpace

No mention of StarSpace (from FaceBook) ? It figures, with the rapid pace of innovation these days. StarSpace can compute 6 types of entity embeddings, of which word embeddings are just one type. It's a whole family of algorithms. https://github.com/facebookresearch/Starspace/

You may be interested in Facebook's recent StarSpace[1] paper, which also shows how this simple "entity embeddings" approach can be used for different tasks. [1] https://github.com/facebookresearch/StarSpace