The Art of Reproducible Machine Learning: A Survey of Methodology in Word Vector Experiments
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F20%3A00117106" target="_blank" >RIV/00216224:14330/20:00117106 - isvavai.cz</a>
Result on the web
<a href="https://nlp.fi.muni.cz/raslan/raslan20.pdf#page=63" target="_blank" >https://nlp.fi.muni.cz/raslan/raslan20.pdf#page=63</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
The Art of Reproducible Machine Learning: A Survey of Methodology in Word Vector Experiments
Original language description
<p>Since the seminal work of Mikolov et al. (2013), word vectors of log-bilinear SVMs have found their way into many NLP applications as an unsupervised measure of word relatedness.</p> <p>Due to the rapid pace of research and the publish-or-perish mantra of academic publishing, word vector experiments contain undisclosed parameters, which make them difficult to reproduce.</p> <p>In our work, we introduce the experiments and their parameters, compare the published experimental results with our own, and suggest default parameter settings and ways to make previous and future experiments easier to reproduce.</p> <p>We show that the lack of variable control can cause up to 24% difference in accuracy on the word analogy tasks.</p>
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the Fourteenth Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2020
ISBN
9788026316008
ISSN
2336-4289
e-ISSN
—
Number of pages
10
Pages from-to
55-64
Publisher name
Tribun EU
Place of publication
Brno
Event location
online
Event date
Dec 8, 2020
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
000655471300006