Header

UZH-Logo

Maintenance Infos

Combining multi-engine machine translation and online learning through dynamic phrase tables


Sennrich, R (2011). Combining multi-engine machine translation and online learning through dynamic phrase tables. In: EAMT-2011: the 15th Annual Conference of the European Association for Machine Translation, Leuven, Belgium, 30 May 2011 - 31 May 2011.

Abstract

Extending phrase-based Statistical Machine Translation systems with a second, dynamic phrase table has been done for multiple purposes.
Promising results have been reported for hybrid or multi-engine machine translation, i.e.\ building a phrase table from the knowledge of external MT systems, and for online learning.
We argue that, in prior research, dynamic phrase tables are not scored optimally because they may be of small size, which makes the Maximum Likelihood Estimation of translation probabilities unreliable.
We propose basing the scores on frequencies from both the dynamic corpus and the primary corpus instead, and show that this modification significantly increases performance.
We also explore the combination of multi-engine MT and online learning.

Abstract

Extending phrase-based Statistical Machine Translation systems with a second, dynamic phrase table has been done for multiple purposes.
Promising results have been reported for hybrid or multi-engine machine translation, i.e.\ building a phrase table from the knowledge of external MT systems, and for online learning.
We argue that, in prior research, dynamic phrase tables are not scored optimally because they may be of small size, which makes the Maximum Likelihood Estimation of translation probabilities unreliable.
We propose basing the scores on frequencies from both the dynamic corpus and the primary corpus instead, and show that this modification significantly increases performance.
We also explore the combination of multi-engine MT and online learning.

Statistics

Citations

Downloads

175 downloads since deposited on 10 May 2011
28 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Language:English
Event End Date:31 May 2011
Deposited On:10 May 2011 09:01
Last Modified:19 Sep 2017 07:20
Funders:Swiss National Science Foundation

Download

Download PDF  'Combining multi-engine machine translation and online learning through dynamic phrase tables'.
Preview
Content: Accepted Version
Filetype: PDF
Size: 1MB