Header

UZH-Logo

Maintenance Infos

Promoting Flexible Translations in Statistical Machine Translation - Zurich Open Repository and Archive


Sennrich, Rico (2013). Promoting Flexible Translations in Statistical Machine Translation. In: Proceedings of the XIV Machine Translation Summit , Nice, 2 September 2013 - 6 September 2013, 207-214.

Abstract

While SMT systems can learn to translate multiword expressions (MWEs) from parallel text, they typically have no notion of non-compositionality, and thus overgeneralise translations that are only used in certain contexts. This paper describes a novel approach to measure the flexibility of a phrase pair, i.e. its tendency to occur in many contexts, in contrast to phrase pairs that are only valid in one or a few fixed expressions. The measure learns from the parallel training text, is simple to implement and language independent. We argue that flexible phrase pairs should be preferred over inflexible ones, and present experiments with phrase-based and hierarchical translation models in which we observe performance gains of up to 0.9 BLEU points.

Abstract

While SMT systems can learn to translate multiword expressions (MWEs) from parallel text, they typically have no notion of non-compositionality, and thus overgeneralise translations that are only used in certain contexts. This paper describes a novel approach to measure the flexibility of a phrase pair, i.e. its tendency to occur in many contexts, in contrast to phrase pairs that are only valid in one or a few fixed expressions. The measure learns from the parallel training text, is simple to implement and language independent. We argue that flexible phrase pairs should be preferred over inflexible ones, and present experiments with phrase-based and hierarchical translation models in which we observe performance gains of up to 0.9 BLEU points.

Downloads

146 downloads since deposited on 19 Sep 2013
26 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:6 September 2013
Deposited On:19 Sep 2013 12:48
Last Modified:05 Apr 2016 16:59
Free access at:Official URL. An embargo period may apply.
Official URL:http://www.mtsummit2013.info/files/proceedings/main/mt-summit-2013-sennrich.pdf

Download

Preview Icon on Download
Preview
Content: Published Version
Language: English
Filetype: PDF
Size: 632kB
Licence: Creative Commons: Attribution-NoDerivs 3.0 Unported (CC BY-ND 3.0)

TrendTerms

TrendTerms displays relevant terms of the abstract of this publication and related documents on a map. The terms and their relations were extracted from ZORA using word statistics. Their timelines are taken from ZORA as well. The bubble size of a term is proportional to the number of documents where the term occurs. Red, orange, yellow and green colors are used for terms that occur in the current document; red indicates high interlinkedness of a term with other terms, orange, yellow and green decreasing interlinkedness. Blue is used for terms that have a relation with the terms in this document, but occur in other documents.
You can navigate and zoom the map. Mouse-hovering a term displays its timeline, clicking it yields the associated documents.

Author Collaborations