Geographical Evaluation of Word Embeddings
Michal Konkol
and
Tomáš Brychcín
and
Michal Nykl
and
Tomáš Hercig
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (2017)
BibTex
|
PDF
Abstract
Word embeddings are commonly compared either with human-annotated word
similarities or through improvements in natural language processing tasks. We
propose a novel principle which compares the information from word embeddings
with reality. We implement this principle by comparing the information in the
word embeddings with geographical positions of cities. Our evaluation linearly
transforms the semantic space to optimally fit the real positions of cities and
measures the deviation between the position given by word embeddings and the
real position. A set of well-known word embeddings with state-of-the-art
results were evaluated. We also introduce a visualization that helps with error
analysis.