A Topic-Based Approach for Post-processing Correction of Automatic Translations

Abstract : We present the LIA systems for the machine translation evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2014 for the English-to-Slovene and English-to-Polish translation tasks. The proposed approach takes into account word context; first, it maps sentences into a latent Dirichlet allocation (LDA) topic space, then it chooses from this space words that are thematically and grammatically close to mistranslated words. This original post-processing approach is compared with a fac-tored translation system built with MOSES. While this post-processing method does not allow us to achieve better results than a state-of-the-art system, this should be an interesting way to explore, for example by adding this topic space information at an early stage in the translation process.
Document type :
Conference papers
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02021817
Contributor : Stéphane Huet <>
Submitted on : Saturday, February 16, 2019 - 7:24:16 PM
Last modification on : Friday, March 22, 2019 - 11:34:07 AM
Long-term archiving on : Friday, May 17, 2019 - 2:34:18 PM

File

IWSLT14.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02021817, version 1

Collections

Citation

Mohamed Morchid, Stéphane Huet, Richard Dufour. A Topic-Based Approach for Post-processing Correction of Automatic Translations. 11th International Workshop on Spoken Language Translation (IWSLT), 2014, South Lake Tahoe, NV, United States. ⟨hal-02021817⟩

Share

Metrics

Record views

9

Files downloads

6