Discovery of Discourse-Related Language Contrasts through Alignment Discrepancies in English-German Translation

TitleDiscovery of Discourse-Related Language Contrasts through Alignment Discrepancies in English-German Translation
Publication TypeConference Paper
Year of Publication2017
AuthorsLapshinova-Koltunski E, Hardmeier C
Conference NameProceedings of the Third Workshop on Discourse in Machine Translation (DiscoMT 2017) at EMNLP-2017
PublisherACL
Conference LocationCopenhagen, Denmark
Abstract

In this paper, we analyse alignment discrepancies
for discourse structures in
English-German parallel data – sentence
pairs, in which discourse structures in target
or source texts have no alignment in
the corresponding parallel sentences. The
discourse-related structures are designed
in form of linguistic patterns based on
the information delivered by automatic
part-of-speech and dependency annotation.
In addition to alignment errors (existing
structures left unaligned), these alignment
discrepancies can be caused by language
contrasts or through the phenomena
of explicitation and implicitation in
the translation process. We propose a new
approach including new type of resources
for corpus-based language contrast analysis
and apply it to study and classify
the contrasts found in our English-German
parallel corpus. As unaligned discourse
structures may also result in the loss of
discourse information in the MT training
data, we hope to deliver information in
support of discourse-aware machine translation
(MT).

URLhttp://www.aclweb.org/anthology/W17-4810