Towards a Gold Standard for Evaluating Danish Word Embeddings

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10426962" target="_blank" >RIV/00216208:11320/20:10426962 - isvavai.cz</a>

Result on the web

<a href="https://www.aclweb.org/anthology/2020.lrec-1.585" target="_blank" >https://www.aclweb.org/anthology/2020.lrec-1.585</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Towards a Gold Standard for Evaluating Danish Word Embeddings

Original language description

This paper presents the process of compiling a model-agnostic similarity goal standard for evaluating Danish word embeddings based on human judgments made by 42 native speakers of Danish. Word embeddings resemble semantic similarity solely by distribution (meaning that word vectors do not reflect relatedness as differing from similarity), and we argue that this generalization poses a problem in most intrinsic evaluation scenarios. In order to be able to evaluate on both dimensions, our human-generated dataset is therefore designed to reflect the distinction between relatedness and similarity. The goal standard is applied for evaluating the “goodness” of six existing word embedding models for Danish, and it is discussed how a relatively low correlation can be explained by the fact that semantic similarity is substantially more challenging to model than relatedness, and that there seems to be a need for future human judgments to measure similarity in full context and along more than a single spectrum.

Czech name

—

Czech description

—

Type

O - Miscellaneous

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2020

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů