|
Learning distributional token representations from visual features
Broscheit, Samuel
;
Gemulla, Rainer
;
Keuper, Margret
![[img]](https://madoc.bib.uni-mannheim.de/45649/1.hassmallThumbnailVersion/Learning%20Distributional%20Token%20Representations%20from%20Visual%20Features.pdf)  Vorschau |
|
PDF
Learning Distributional Token Representations from Visual Features.pdf
- Veröffentlichte Version
Download (334kB)
|
|
URL:
|
https://madoc.bib.uni-mannheim.de/45649
|
|
Weitere URL:
|
http://aclweb.org/anthology/W18-3025
|
|
URN:
|
urn:nbn:de:bsz:180-madoc-456495
|
|
Dokumenttyp:
|
Konferenzveröffentlichung
|
|
Erscheinungsjahr:
|
2018
|
|
Buchtitel:
|
ACL 2018, Representation Learning for NLP : Proceedings of the Third Workshop : July 20, 2018 Melbourne, Australia
|
|
Seitenbereich:
|
187-194
|
|
Veranstaltungstitel:
|
3rd Workshop on Representation Learning for NL
|
|
Veranstaltungsort:
|
Melbourne, Australia
|
|
Veranstaltungsdatum:
|
20.7.2018
|
|
Herausgeber:
|
Augenstein, Isabelle
|
|
Ort der Veröffentlichung:
|
Stroudsburg, PA
|
|
Verlag:
|
Association for Computational Linguistics
|
|
ISBN:
|
978-1-948087-43-8
|
|
Sprache der Veröffentlichung:
|
Englisch
|
|
Einrichtung:
|
Fakultät für Wirtschaftsinformatik und Wirtschaftsmathematik > Practical Computer Science I: Data Analytics (Gemulla 2014-)
|
|
Lizenz:
|
Creative Commons Namensnennung 4.0 International (CC BY 4.0)
|
|
Fachgebiet:
|
004 Informatik
|
|
Abstract:
|
In this study, we compare token representations constructed from visual features
(i.e., pixels) with standard lookup-based
embeddings. Our goal is to gain insight
about the challenges of encoding a text
representation from low-level features,
e.g. from characters or pixels. We focus on Chinese, which—as a logographic
language—has properties that make a representation via visual features challenging
and interesting. To train and evaluate different models for the token representation,
we chose the task of character-based neural machine translation (NMT) from Chinese to English. We found that a token
representation computed only from visual
features can achieve competitive results to
lookup embeddings. However, we also
show different strengths and weaknesses
in the models’ performance in a part-of-
speech tagging task and also a semantic
similarity task. In summary, we show that
it is possible to achieve a
text representation
only from pixels. We hope that this
is a useful stepping stone for future studies that exclusively rely on visual input, or
aim at exploiting visual features of written language.
|
 | Dieser Eintrag ist Teil der Universitätsbibliographie. |
 | Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt. |
 Suche Autoren in
BASE:
Broscheit, Samuel
;
Gemulla, Rainer
;
Keuper, Margret
Google Scholar:
Broscheit, Samuel
;
Gemulla, Rainer
;
Keuper, Margret
ORCID:
Broscheit, Samuel, Gemulla, Rainer  ORCID: https://orcid.org/0000-0003-2762-0050 and Keuper, Margret
Sie haben einen Fehler gefunden? Teilen Sie uns Ihren Korrekturwunsch bitte hier mit: E-Mail
Actions (login required)
 |
Eintrag anzeigen |
|
|
