Harnessing the Redundant Results of Translation Spotting

Abstract : Translation spotting consists in automatically identifying the translations of a user query inside a bitext. This task, when it relies solely on statistical word alignment algorithms, fails to achieve excellent results. In this paper, we show that identifying the translations of a query during a first translation spotting stage provides relevant information that can be used in a second stage to improve the precision of the results. This method is similar to the relevance feedback used in the information retrieval domain to enhance retrieval.
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02021884
Contributor : Stéphane Huet <>
Submitted on : Saturday, February 16, 2019 - 9:11:35 PM
Last modification on : Wednesday, April 17, 2019 - 12:15:36 PM
Long-term archiving on : Friday, May 17, 2019 - 2:08:53 PM

File

MTSummit09.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02021884, version 1

Citation

Stéphane Huet, Julien Bourdaillet, Philippe Langlais, Guy Lapalme. Harnessing the Redundant Results of Translation Spotting. 12th Machine Translation Summit (MT Summit), 2009, Ottawa, Canada. ⟨hal-02021884⟩

Share

Metrics

Record views

8

Files downloads

5