Reordering space design in statistical machine translation.
In Statistical Machine Translation (SMT), the constraints on word reorderings have a great impact on the set of potential translations that is explored during search. Notwithstanding computational issues, the reordering space of a SMT system needs to be designed with great care: if a larger search s...
| Published in: | Language Resources & Evaluation Vol. 50; no. 2; pp. 375 - 411 |
|---|---|
| Main Authors: | , , , |
| Format: | Article |
| Published: |
Springer Nature
Jun2016
|
| Subjects: | |
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=116036663&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 116036663 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 1574020X 179V jtl: Language Resources & Evaluation issn: 1574020X maglogo: N pubinfo: dt: Jun2016 vid: 50 iid: 2 pid: 237 pub: Springer Nature artinfo: ui: 116036663 10.1007/s10579-016-9353-8 ppf: 375 ppct: 36 formats: fmt: @attributes: type: P size: 1.2MB tig: atl: Reordering space design in statistical machine translation. aug: au: Pécheux, Nicolas Allauzen, Alexandre Niehues, Jan Yvon, François affil: LIMSI, CNRS, Univ Paris-Sud, Université Paris-Saclay, rue John Von Neumann, Campus Universitaire d'Orsay 91403 Orsay Cedex France Karlsruhe Institute of Technology, Institute for Anthropomatics and Robotics - Adenauerring 2, 76131 Karlsruhe Germany su: Machine translating Translating machines Translating of English language English language -- Translating into German French language -- Translating sug: subj: Machine translating Translating machines Translating of English language English language -- Translating into German French language -- Translating ab: In Statistical Machine Translation (SMT), the constraints on word reorderings have a great impact on the set of potential translations that is explored during search. Notwithstanding computational issues, the reordering space of a SMT system needs to be designed with great care: if a larger search space is likely to yield better translations, it may also lead to more decoding errors, because of the added ambiguity and the interaction with the pruning strategy. In this paper, we study the reordering search space, using a state-of-the art translation system, where all reorderings are represented in a permutation lattice prior to decoding. This allows us to directly explore and compare different reordering schemes and oracle settings. We also study in detail a rule-based preordering system, varying the length and number of rules, the tagset used, as well as contrasting with purely combinatorial subsets of permutations. We carry out experiments on three language pairs in both directions: English-French, a close language pair; English-German and English-Czech, two much more challenging pairs. We show that even though it might be desirable to design better reordering spaces, model and search errors seem to be the most important issues. Therefore, improvements of the reordering space should come along with improvements of the associated models to be really effective. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: Language Resources & Evaluation is a copyright of Springer, 2016. All Rights Reserved. item: Language Resources & Evaluation holder: Springer Nature dt: @attributes: year: 2016 holdings: @attributes: islocal: N |
|---|