Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/88461
Full metadata record
DC FieldValueLanguage
dc.contributor.authorJoty, Shafiqen
dc.contributor.authorGuzmán, Franciscoen
dc.contributor.authorMàrquez, Lluísen
dc.contributor.authorNakov, Preslaven
dc.date.accessioned2018-12-12T08:08:35Zen
dc.date.accessioned2019-12-06T17:03:49Z-
dc.date.available2018-12-12T08:08:35Zen
dc.date.available2019-12-06T17:03:49Z-
dc.date.issued2017en
dc.identifier.citationJoty, S., Guzmán, F., Màrquez, L., & Nakov, P. (2017). Discourse structure in machine translation evaluation. Computational Linguistics, 43(4), 683-722. doi:10.1162/COLI_a_00298en
dc.identifier.issn0891-2017en
dc.identifier.urihttps://hdl.handle.net/10356/88461-
dc.description.abstractIn this article, we explore the potential of using sentence-level discourse structure for machine translation evaluation. We first design discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory (RST). Then, we show that a simple linear combination with these measures can help improve various existing machine translation evaluation metrics regarding correlation with human judgments both at the segment level and at the system level. This suggests that discourse information is complementary to the information used by many of the existing evaluation metrics, and thus it could be taken into account when developing richer evaluation metrics, such as the WMT-14 winning combined metric DiscoTKparty. We also provide a detailed analysis of the relevance of various discourse elements and relations from the RST parse trees for machine translation evaluation. In particular, we show that (i) all aspects of the RST tree are relevant, (ii) nuclearity is more useful than relation type, and (iii) the similarity of the translation RST tree to the reference RST tree is positively correlated with translation quality.en
dc.format.extent40 p.en
dc.language.isoenen
dc.relation.ispartofseriesComputational Linguisticsen
dc.rights© 2017 Association for Computational Linguistics. Published under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) licenseen
dc.subjectComputer Aided Language Translationen
dc.subjectMachine Translation Evaluationen
dc.subjectDRNTU::Engineering::Computer science and engineeringen
dc.titleDiscourse structure in machine translation evaluationen
dc.typeJournal Articleen
dc.contributor.schoolSchool of Computer Science and Engineeringen
dc.identifier.doi10.1162/COLI_a_00298en
dc.description.versionPublished versionen
item.fulltextWith Fulltext-
item.grantfulltextopen-
Appears in Collections:SCSE Journal Articles
Files in This Item:
File Description SizeFormat 
Discourse structure in machine translation evaluation.pdf937.07 kBAdobe PDFThumbnail
View/Open

SCOPUSTM   
Citations 20

4
checked on Sep 5, 2020

WEB OF SCIENCETM
Citations 50

2
checked on Sep 17, 2020

Page view(s) 50

65
checked on Sep 24, 2020

Download(s) 50

22
checked on Sep 24, 2020

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.