Semanlink - A Latent Variable Model Approach to PMI-based Word Embeddings (2016)

> Here it is shown that multiple word senses reside
in linear superposition within the word
embedding and simple sparse coding can recover
vectors that approximately capture the
senses

> Each extracted word sense is accompanied by one of about  2000 “discourse atoms” that gives a succinct description of which other words co-occur with that word sense.

> The success of the approach is mathematically explained using a variant of
the random walk on discourses model

("random walk": a generative model for language). Under the assumptions of this model,  there
exists a linear relationship between the vector of a
word w and the vectors of the words in its contexts (It is not the average of the words in w's context, but in a given corpus the matrix of the linear relationship does not depend on w. It can be estimated, and so we can compute the embedding of a word from the contexts it belongs to)

[Related blog post](/doc/?uri=https%3A%2F%2Fwww.offconvex.org%2F2016%2F07%2F10%2Fembeddingspolysemy%2F)

2018-08-28 About

Sanjeev Arora on "A theoretical approach to semantic representations" - YouTube (2016)

Tags:

2018-06-10 About

A Theoretical Approach to Semantic Coding and Hashing | Simons Institute for the Theory of Computing (2016)

Tags:

2018-05-26 About

Semantic Word Embeddings – Off the convex path

Tags:

2017-11-21 About