Towards Useful Word Embeddings: Evaluation on Information Retrieval, Text Classification, and Language Modeling
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F20%3A00117105" target="_blank" >RIV/00216224:14330/20:00117105 - isvavai.cz</a>
Result on the web
<a href="https://www.fi.muni.cz/usr/sojka/papers/raslan-2020-novotny-stefanik-luptak-sojka.pdf" target="_blank" >https://www.fi.muni.cz/usr/sojka/papers/raslan-2020-novotny-stefanik-luptak-sojka.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Towards Useful Word Embeddings: Evaluation on Information Retrieval, Text Classification, and Language Modeling
Original language description
<p>Since the seminal work of Mikolov et al. (2013), word vectors of log-bilinear models have found their way into many NLP applications and were extended with the positional model.</p> <p>Although the positional model improves accuracy on the intrinsic English word analogy task, prior work has neglected its evaluation on extrinsic end tasks, which correspond to real-world NLP applications.</p> <p>In this paper, we describe our first steps in evaluating positional weighting on the information retrieval, text classification, and language modeling extrinsic end 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
37-46
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
000655471300004