Issues in evaluating semantic spaces using word analogies
T. Linzen. (2016)cite arxiv:1606.07736Comment: 6 pages; The First Workshop on Evaluating Vector Space Representations for NLP.
Abstract
The offset method for solving word analogies has become a standard evaluation
tool for vector-space semantic models: it is considered desirable for a space
to represent semantic relations as consistent vector offsets. We show that the
method's reliance on cosine similarity conflates offset consistency with
largely irrelevant neighborhood structure, and propose simple baselines that
should be used to improve the utility of the method in vector space evaluation.
Description
Issues in evaluating semantic spaces using word analogies
%0 Generic
%1 linzen2016issues
%A Linzen, Tal
%D 2016
%K analogy evaluation issues semantic
%T Issues in evaluating semantic spaces using word analogies
%U http://arxiv.org/abs/1606.07736
%X The offset method for solving word analogies has become a standard evaluation
tool for vector-space semantic models: it is considered desirable for a space
to represent semantic relations as consistent vector offsets. We show that the
method's reliance on cosine similarity conflates offset consistency with
largely irrelevant neighborhood structure, and propose simple baselines that
should be used to improve the utility of the method in vector space evaluation.
@misc{linzen2016issues,
abstract = {The offset method for solving word analogies has become a standard evaluation
tool for vector-space semantic models: it is considered desirable for a space
to represent semantic relations as consistent vector offsets. We show that the
method's reliance on cosine similarity conflates offset consistency with
largely irrelevant neighborhood structure, and propose simple baselines that
should be used to improve the utility of the method in vector space evaluation.},
added-at = {2017-03-28T16:06:46.000+0200},
author = {Linzen, Tal},
biburl = {https://www.bibsonomy.org/bibtex/2ad3ba8dabbc4ffe28abf587526bcd7ab/thoni},
description = {Issues in evaluating semantic spaces using word analogies},
interhash = {f385f750c21cccbdbd72635f4cca4782},
intrahash = {ad3ba8dabbc4ffe28abf587526bcd7ab},
keywords = {analogy evaluation issues semantic},
note = {cite arxiv:1606.07736Comment: 6 pages; The First Workshop on Evaluating Vector Space Representations for NLP},
timestamp = {2017-03-28T16:08:25.000+0200},
title = {Issues in evaluating semantic spaces using word analogies},
url = {http://arxiv.org/abs/1606.07736},
year = 2016
}