Quick Search:

is currently disabled due to reindexing of the ZORA database. Please use Advanced Search.
uzh logo
Browse by:
bullet
bullet
bullet
bullet

Zurich Open Repository and ArchiveĀ 

Permanent URL to this publication: http://dx.doi.org/10.5167/uzh-38464

Sennrich, R; Volk, M (2010). MT-based sentence alignment for OCR-generated parallel texts. In: The Ninth Conference of the Association for Machine Translation in the Americas (AMTA 2010), Denver, 31 October 2010 - 4 November 2010.

[img]
Preview
PDF
1MB

Abstract

The performance of current sentence alignment tools varies according to the to-be-aligned texts. We have found existing tools unsuitable for hard-to-align parallel texts and describe an alternative alignment algorithm. The basic idea is to use machine translations of a text and BLEU as a similarity score to find reliable alignments which are used as anchor points. The gaps between these anchor points are then filled using BLEU-based and length-based heuristics. We show that this approach outperforms state-of-the-art algorithms in our alignment task, and that this improvement in alignment quality translates into better SMT performance. Furthermore, we show that even length-based alignment algorithms profit from having a machine translation as a point of comparison.

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
DDC:410 Linguistics
000 Computer science, knowledge & systems
Language:English
Event End Date:4 November 2010
Deposited On:14 Dec 2010 13:48
Last Modified:09 Jul 2012 04:29
Funders:Swiss National Science Foundation
Official URL:http://amta2010.amtaweb.org/AMTA/papers/2-14-SennrichVolk.pdf
Citations:Google Scholarā„¢

Users (please log in): suggest update or correction for this item

Repository Staff Only: item control page