Word-aligned parallel text : a new resource for contrastive language studies

Martin Volk, Anne Göhring, Stéphanie Lehner, Annette Rios, Rico Sennrich, Heli Uibo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

This paper describes the opportunities that arise from automatic word alignment for bilingual concordances and contrastive language studies. We introduce our parallel corpus of Alpine texts in French and German and our web-based alignment search system. We explain how we have reduced the number of erroneous alignments in the output by distinguishing between dominant and miscellaneous translations. We are currently in the process of extending the system to a new language pair Spanish-Quechua. This poses special problems because of the scarcity of resources for Quechua but also because of the wide typological gap between the languages.
Original languageEnglish
Title of host publicationSupporting Digital Humanities, Conference 2011
Place of PublicationCopenhagen, Denmark
Publication statusPublished - 1 Nov 2011
EventSupporting Digital Humanities, Conference 2011 - Copenhagen, Denmark
Duration: 17 Nov 201118 Nov 2011

Conference

ConferenceSupporting Digital Humanities, Conference 2011
Country/TerritoryDenmark
CityCopenhagen
Period17/11/1118/11/11

Fingerprint

Dive into the research topics of 'Word-aligned parallel text : a new resource for contrastive language studies'. Together they form a unique fingerprint.

Cite this