Word2vec Conjecture and A Limitative Result

10/24/2020
by   Falcon Z. Dai, et al.
0

Being inspired by the success of word2vec <cit.> in capturing analogies, we study the conjecture that analogical relations can be represented by vector spaces. Unlike many previous works that focus on the distributional semantic aspect of word2vec, we study the purely representational question: can all semantic word-word relations be represented by differences (or directions) of vectors? We call this the word2vec conjecture and point out some of its desirable implications. However, we will exhibit a class of relations that cannot be represented in this way, thus falsifying the conjecture and establishing a limitative result for the representability of semantic relations by vector spaces over fields of characteristic 0, e.g., real or complex numbers.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/24/2016

Issues in evaluating semantic spaces using word analogies

The offset method for solving word analogies has become a standard evalu...
research
10/11/2018

Towards Understanding Linear Word Analogies

A surprising property of word vectors is that vector algebra can often b...
research
01/27/2023

Proof of a conjecture of Krawchuk and Rampersad

We prove a 2018 conjecture of Krawchuk and Rampersad on the extremal beh...
research
01/13/2023

On a conjecture of Knuth about forward and back arcs

Following Janson's method, we prove a conjecture of Knuth: the numbers o...
research
06/01/2017

Morph-fitting: Fine-Tuning Word Vector Spaces with Simple Language-Specific Rules

Morphologically rich languages accentuate two properties of distribution...
research
04/08/2020

Are All Good Word Vector Spaces Isomorphic?

Existing algorithms for aligning cross-lingual word vector spaces assume...

Please sign up or login with your details

Forgot password? Click here to reset