Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Projecting Embeddings for Domain Adaption : Joint Modeling of Sentiment Analysis in Diverse Domains

Publication

Projecting Embeddings for Domain Adaption : Joint Modeling of Sentiment Analysis in Diverse Domains

Barnes, Jeremy; Klinger, Roman; Schulte im Walde, Sabine (2018): Projecting Embeddings for Domain Adaption : Joint Modeling of Sentiment Analysis in Diverse Domains, in: Emily M. Bender, Leon Derczynski, Pierre Isabelle, u. a. (Hrsg.), Proceedings of the 27th International Conference on Computational Linguistics, Association for Computational Linguistics, S. 818–830.

Details

Faculty/Chair
Faculty/Professorship
Author
Barnes, Jeremy
Schulte im Walde, Sabine
Title of the compilation
Proceedings of the 27th International Conference on Computational Linguistics
Editors
Bender, Emily M.
Derczynski, Leon
Isabelle, Pierre
Conference
27th International Conference on Computational Linguistics, Santa Fe, New Mexico, USA
Publisher Information
Association for Computational Linguistics
Year of publication
2018
Language
English
URL
Abstract

Domain adaptation for sentiment analysis is challenging due to the fact that supervised classifiers are very sensitive to changes in domain. The two most prominent approaches to this problem are structural correspondence learning and autoencoders. However, they either require long training times or suffer greatly on highly divergent domains. Inspired by recent advances in cross-lingual sentiment analysis, we provide a novel perspective and cast the domain adaptation problem as an embedding projection task. Our model takes as input two mono-domain embedding spaces and learns to project them to a bi-domain space, which is jointly optimized to (1) project across domains and to (2) predict sentiment. We perform domain adaptation experiments on 20 source-target domain pairs for sentiment classification and report novel state-of-the-art results on 11 domain pairs, including the Amazon domain adaptation datasets and SemEval 2013 and 2016 datasets. Our analysis shows that our model performs comparably to state-of-the-art approaches on domains that are similar, while performing significantly better on highly divergent domains. Our code is available at https://github.com/jbarnesspain/domain_blse

GND Keywords
Maschinelles Lernen
Sprachverarbeitung
Keywords
Projecting Embeddings
DDC Classification
004 Computer science
RVK Classification
ST 306
Peer Reviewed
yes
International Distribution
yes
Open Access Journal
yes
Type
Conferenceobject
URI
Activation date
2024-03-14

Permalink: https://fis.uni-bamberg.de/handle/uniba/93965 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.