File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/s10590-017-9202-6
- Scopus: eid_2-s2.0-85034095709
- WOS: WOS:000435533400010
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Cross-lingual sentiment transfer with limited resources
Title | Cross-lingual sentiment transfer with limited resources |
---|---|
Authors | |
Keywords | Direct transfer Cross-lingual sentiment Low-resource Annotation projection |
Issue Date | 2018 |
Citation | Machine Translation, 2018, v. 32, n. 1-2, p. 143-165 How to Cite? |
Abstract | We describe two transfer approaches for building sentiment analysis systems without having gold labeled data in the target language. Unlike previous work that is focused on using only English as the source language and a small number of target languages, we use multiple source languages to learn a more robust sentiment transfer model for 16 languages from different language families. Our approaches explore the potential of using an annotation projection approach and a direct transfer approach using cross-lingual word representations and neural networks. Whereas most previous work relies on machine translation, we show that we can build cross-lingual sentiment analysis systems without machine translation or even high quality parallel data. We have conducted experiments assessing the availability of different resources such as in-domain parallel data, out-of-domain parallel data, and in-domain comparable data. Our experiments show that we can build a robust transfer system whose performance can in some cases approach that of a supervised system. |
Persistent Identifier | http://hdl.handle.net/10722/303543 |
ISSN | 2023 Impact Factor: 2.1 2023 SCImago Journal Rankings: 0.340 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Rasooli, Mohammad Sadegh | - |
dc.contributor.author | Farra, Noura | - |
dc.contributor.author | Radeva, Axinia | - |
dc.contributor.author | Yu, Tao | - |
dc.contributor.author | McKeown, Kathleen | - |
dc.date.accessioned | 2021-09-15T08:25:32Z | - |
dc.date.available | 2021-09-15T08:25:32Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | Machine Translation, 2018, v. 32, n. 1-2, p. 143-165 | - |
dc.identifier.issn | 0922-6567 | - |
dc.identifier.uri | http://hdl.handle.net/10722/303543 | - |
dc.description.abstract | We describe two transfer approaches for building sentiment analysis systems without having gold labeled data in the target language. Unlike previous work that is focused on using only English as the source language and a small number of target languages, we use multiple source languages to learn a more robust sentiment transfer model for 16 languages from different language families. Our approaches explore the potential of using an annotation projection approach and a direct transfer approach using cross-lingual word representations and neural networks. Whereas most previous work relies on machine translation, we show that we can build cross-lingual sentiment analysis systems without machine translation or even high quality parallel data. We have conducted experiments assessing the availability of different resources such as in-domain parallel data, out-of-domain parallel data, and in-domain comparable data. Our experiments show that we can build a robust transfer system whose performance can in some cases approach that of a supervised system. | - |
dc.language | eng | - |
dc.relation.ispartof | Machine Translation | - |
dc.subject | Direct transfer | - |
dc.subject | Cross-lingual sentiment | - |
dc.subject | Low-resource | - |
dc.subject | Annotation projection | - |
dc.title | Cross-lingual sentiment transfer with limited resources | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1007/s10590-017-9202-6 | - |
dc.identifier.scopus | eid_2-s2.0-85034095709 | - |
dc.identifier.volume | 32 | - |
dc.identifier.issue | 1-2 | - |
dc.identifier.spage | 143 | - |
dc.identifier.epage | 165 | - |
dc.identifier.eissn | 1573-0573 | - |
dc.identifier.isi | WOS:000435533400010 | - |